# agenticweb.wiki > Reference map of the agentic web's standards layer: nine lifecycle steps, one record per protocol, every claim sourced. ## Start here - [What the agentic web is](https://agenticweb.wiki/agentic-web/index.md) - [The map](https://agenticweb.wiki/map/index.md) - [Methodology](https://agenticweb.wiki/methodology/index.md) - [Resources](https://agenticweb.wiki/resources/index.md) - [Instances](https://agenticweb.wiki/instances/index.md) - [News](https://agenticweb.wiki/news/index.md) - [Agentic web daily digest](https://agenticweb.wiki/digest/index.md) ## Data & Bulk Exports - [Bulk data manifest & SHA-256 provenance](https://agenticweb.wiki/data/manifest.json) - [Spec versions, canonical paths & deprecations JSON](https://agenticweb.wiki/data/versions.json) - [All records JSON](https://agenticweb.wiki/data/standards.json) - [All records NDJSON (DuckDB ready)](https://agenticweb.wiki/data/standards.ndjson) - [CSV](https://agenticweb.wiki/data/standards.csv) - [Latest 211-domain readiness panel JSON](https://agenticweb.wiki/data/panel-latest.json) - [Latest 211-domain readiness panel NDJSON](https://agenticweb.wiki/data/panel-latest.ndjson) - [Probe rules](https://agenticweb.wiki/data/probes.json) - [Changes](https://agenticweb.wiki/data/changes.json) - [Freshness](https://agenticweb.wiki/data/freshness.json) - [News feed (JSON)](https://agenticweb.wiki/news/feed.json) - [OpenAPI](https://agenticweb.wiki/openapi.json) - [Every article as one Markdown file](https://agenticweb.wiki/llms-full.txt) - [Markdown sitemap](https://agenticweb.wiki/sitemap.md) - [Open Knowledge Format (OKF v0.2) bundle index](https://agenticweb.wiki/okf/index.md) - [Update log (OKF log.md)](https://agenticweb.wiki/log.md) - [AGENTS.md](https://agenticweb.wiki/AGENTS.md) - [Authentication policy (auth.md)](https://agenticweb.wiki/auth.md) - [MCP server card](https://agenticweb.wiki/mcp/server-card) - [Connect an agent over MCP](https://agenticweb.wiki/connect/index.md) - [Check a domain's agent readiness](https://agenticweb.wiki/check/index.md) (JSON: https://agenticweb.wiki/check//index.json; concise views: ?brief=1, ?compact=1, ?manifest=) - [Service status & release channels](https://agenticweb.wiki/status/index.md) - [Errata log (data & scoring corrections)](https://agenticweb.wiki/errata/index.md) - [Security disclosure policy](https://agenticweb.wiki/security/index.md) - [Skill for coding agents](https://agenticweb.wiki/static/skill/SKILL.md) - [Submit a listing or correction](https://agenticweb.wiki/submit/index.md) ## Daily Digest - [Daily digest hub](https://agenticweb.wiki/digest/index.md) - [Daily digest, latest (JSON)](https://agenticweb.wiki/digest/latest.json) - [Daily digest index (JSON)](https://agenticweb.wiki/digest/index.json) - [Daily digest JSON Feed](https://agenticweb.wiki/digest/feed.json) ## Top Head-to-Head Comparisons - [Standards compared head-to-head (all pairs)](https://agenticweb.wiki/compare/index.md) - [OpenAPI & REST APIs vs Model Context Protocol (MCP)](https://agenticweb.wiki/compare/openapi-vs-mcp/index.md) - [sitemap.xml vs llms.txt & ARD](https://agenticweb.wiki/compare/sitemap-xml-vs-llms-txt/index.md) - [robots.txt (Allow/Disallow) vs Content-Signal, AIPREF & TDMRep](https://agenticweb.wiki/compare/robots-txt-vs-content-signal/index.md) - [User-Agent & IP Allowlists vs Web Bot Auth (RFC 9421)](https://agenticweb.wiki/compare/user-agent-vs-web-bot-auth/index.md) - [OAuth 2.0 Consent & DCR vs CIMD & Agent OAuth Metadata](https://agenticweb.wiki/compare/oauth-vs-cimd/index.md) - [3-D Secure & Card Checkout vs AP2, ACP & UCP](https://agenticweb.wiki/compare/3d-secure-vs-ap2/index.md) - [API Keys & Subscriptions vs x402 & MPP (HTTP 402)](https://agenticweb.wiki/compare/api-keys-vs-x402/index.md) - [HTML DOM & RSS vs Accept: text/markdown & OKF](https://agenticweb.wiki/compare/html-dom-vs-markdown-for-agents/index.md) - [DOM Browser Automation vs WebMCP & MCP](https://agenticweb.wiki/compare/browser-automation-vs-webmcp/index.md) - [Webhooks & RPC vs Agent2Agent Protocol (A2A)](https://agenticweb.wiki/compare/webhooks-vs-a2a/index.md) - [DNS (A/SRV) & WHOIS vs AID & DNS-AID](https://agenticweb.wiki/compare/dns-whois-vs-aid/index.md) - [Iframes & Server-Driven UI vs MCP Apps, AG-UI & A2UI](https://agenticweb.wiki/compare/iframes-vs-mcp-apps/index.md) - [Cookies, Syslog & T&Cs vs Agent Attribution, OTel GenAI & SCITT](https://agenticweb.wiki/compare/cookies-syslog-vs-agent-audit-trail/index.md) - [Agent2Agent Protocol vs Model Context Protocol](https://agenticweb.wiki/compare/a2a-vs-mcp/index.md) - [x402 vs Agent Payments Protocol](https://agenticweb.wiki/compare/x402-vs-ap2/index.md) - [x402 vs Machine Payments Protocol](https://agenticweb.wiki/compare/x402-vs-mpp/index.md) - [x402 vs L402](https://agenticweb.wiki/compare/x402-vs-l402/index.md) - [Agent Payments Protocol vs Agentic Commerce Protocol](https://agenticweb.wiki/compare/ap2-vs-agentic-commerce-protocol/index.md) - [Universal Commerce Protocol vs Agentic Commerce Protocol](https://agenticweb.wiki/compare/ucp-vs-agentic-commerce-protocol/index.md) - [llms.txt vs AGENTS.md](https://agenticweb.wiki/compare/llms-txt-vs-agents-md/index.md) - [Agentic Resource Discovery vs llms.txt](https://agenticweb.wiki/compare/ard-vs-llms-txt/index.md) - [AGENTS.md vs agents.txt](https://agenticweb.wiki/compare/agents-md-vs-agents-txt/index.md) - [Agentic Resource Discovery vs api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs](https://agenticweb.wiki/compare/ard-vs-api-catalog-rfc9727/index.md) - [Agentic Resource Discovery vs AI Catalog well-known file](https://agenticweb.wiki/compare/ard-vs-ai-catalog-well-known-file/index.md) - [Agent2Agent Protocol vs MCP Server Cards (SEP-2127)](https://agenticweb.wiki/compare/a2a-vs-mcp-server-cards/index.md) - [Content Signals Policy vs Web Bot Auth HTTP Message Signatures](https://agenticweb.wiki/compare/cloudflare-content-signals-policy-vs-webbotauth/index.md) - [Agent Skills vs Model Context Protocol](https://agenticweb.wiki/compare/anthropic-agent-skills-format-vs-mcp/index.md) - [Agent Client Protocol vs Agentic Commerce Protocol](https://agenticweb.wiki/compare/agent-client-protocol-vs-agentic-commerce-protocol/index.md) - [Model Context Protocol vs WebMCP](https://agenticweb.wiki/compare/mcp-vs-webmcp/index.md) - [Model Context Protocol vs Agent Client Protocol](https://agenticweb.wiki/compare/mcp-vs-agent-client-protocol/index.md) - [A2UI (Agent to UI) Protocol vs Agent-User Interaction Protocol](https://agenticweb.wiki/compare/a2ui-vs-ag-ui/index.md) - [MCP Apps vs OpenAI Plugins (formerly Apps SDK)](https://agenticweb.wiki/compare/mcp-apps-vs-openai-apps-sdk-manifests/index.md) - [MCP Server Cards (SEP-2127) vs Agentic Resource Discovery](https://agenticweb.wiki/compare/mcp-server-cards-vs-ard/index.md) - [Web Bot Auth HTTP Message Signatures vs HTTP Message Signatures](https://agenticweb.wiki/compare/webbotauth-vs-http-message-signatures/index.md) - [Web Bot Auth HTTP Message Signatures vs SPIFFE (Secure Production Identity Framework for Everyone)](https://agenticweb.wiki/compare/webbotauth-vs-spiffe/index.md) - [SPIFFE (Secure Production Identity Framework for Everyone) vs Workload Identity in Multi System Environments (WIMSE) Architecture](https://agenticweb.wiki/compare/spiffe-vs-wimse/index.md) - [Agent Identity and Discovery vs DNS for AI Discovery](https://agenticweb.wiki/compare/aid-vs-dns-aid/index.md) - [Agent Identity and Discovery vs Agent2Agent Protocol](https://agenticweb.wiki/compare/aid-vs-a2a/index.md) - [Text and Data Mining Reservation Protocol vs AIPREF Vocabulary](https://agenticweb.wiki/compare/tdmrep-vs-aipref-vocabulary/index.md) - [Really Simple Licensing vs AIPREF Vocabulary](https://agenticweb.wiki/compare/rsl-vs-aipref-vocabulary/index.md) - [Content Signals Policy vs AIPREF Vocabulary](https://agenticweb.wiki/compare/cloudflare-content-signals-policy-vs-aipref-vocabulary/index.md) - [AI Crawler User-Agent Tokens in robots.txt vs agent-permissions.json](https://agenticweb.wiki/compare/ai-crawler-tokens-robots-vs-agent-permissions-json/index.md) - [Cloudflare Pay per crawl vs x402](https://agenticweb.wiki/compare/cloudflare-pay-per-crawl-vs-x402/index.md) - [OAuth Protected Resource and Authorization Server Metadata (as used for agent authorization) vs auth.md](https://agenticweb.wiki/compare/oauth-metadata-for-agents-vs-auth-md/index.md) - [Agent Audit Trail vs AI Agent Execution Profile of SCITT](https://agenticweb.wiki/compare/agent-audit-trail-vs-scitt-ai-agent-execution/index.md) - [NLWeb vs Model Context Protocol](https://agenticweb.wiki/compare/nlweb-vs-mcp/index.md) - [Agent Readability Spec vs llms.txt](https://agenticweb.wiki/compare/vercel-agent-readability-vs-llms-txt/index.md) - [llms.txt vs agents.txt](https://agenticweb.wiki/compare/llms-txt-vs-agents-txt/index.md) - [Web Bot Auth HTTP Message Signatures vs Visa Trusted Agent Protocol](https://agenticweb.wiki/compare/webbotauth-vs-tap/index.md) - [Open Knowledge Format vs llms.txt](https://agenticweb.wiki/compare/okf-vs-llms-txt/index.md) - [Markdown for Agents vs llms.txt](https://agenticweb.wiki/compare/cloudflare-markdown-for-agents-vs-llms-txt/index.md) - [Agent2Agent Protocol vs Agent Network Protocol](https://agenticweb.wiki/compare/a2a-vs-anp/index.md) - [Verifiable Intent vs Agent Payments Protocol](https://agenticweb.wiki/compare/vi-vs-ap2/index.md) - [AIPREF Content-Usage Attachment vs AIPREF Vocabulary](https://agenticweb.wiki/compare/aipref-content-usage-attachment-vs-aipref-vocabulary/index.md) ## Categories - [1 Discover](https://agenticweb.wiki/category/discover/index.md): What is here, and where? - [2 Identify](https://agenticweb.wiki/category/identify/index.md): Who is this agent? Who is this site? - [3 Permit](https://agenticweb.wiki/category/permit/index.md): What may the agent do here? - [4 Read](https://agenticweb.wiki/category/read/index.md): Give me the content - [5 Act](https://agenticweb.wiki/category/act/index.md): Do something for me - [6 Coordinate](https://agenticweb.wiki/category/coordinate/index.md): Talk to another agent - [7 Pay](https://agenticweb.wiki/category/pay/index.md): Settle the bill - [8 Present](https://agenticweb.wiki/category/present/index.md): Show a human the result - [9 Account](https://agenticweb.wiki/category/account/index.md): Prove what happened; be judged ## Protocols - [A Framework for Agent Discovery in DAWN](https://agenticweb.wiki/protocols/dawn-agent-discovery-framework/index.md): How can a client discover the minimum public information about AI agents across local and cross-organizational boundaries while preserving each site's data sovereignty? - [A Server-Side Model for Gating Agent-Initiated Human-Sourced Asynchronous HTTP Tasks on Payment or Entitlement](https://agenticweb.wiki/protocols/agentic-payments-gating-model/index.md): How should a server gate paid, agent-initiated asynchronous HTTP tasks on payment or entitlement so that fulfilment never precedes validation and retries do not create duplicate tasks or gate acceptances? - [A2UI (Agent to UI) Protocol](https://agenticweb.wiki/protocols/a2ui/index.md): How can an agent describe and stream a framework-neutral, declarative UI to a renderer? - [AAuth (Hardt)](https://agenticweb.wiki/protocols/aauth-hardt/index.md): How does an agent obtain and present authorisation to act at a resource, using signed HTTP requests? - [AAuth Rich Resource Requests](https://agenticweb.wiki/protocols/aauth-r3/index.md): How can an agent request an API's named operations, and a person approve one exact call, without relying on opaque scope strings? - [Ad Context Protocol](https://agenticweb.wiki/protocols/adcp/index.md): How can an AI agent discover ad inventory, execute a media buy, sync creative, and report performance across many ad platforms through one protocol? - [Agent Attribution Protocol](https://agenticweb.wiki/protocols/agent-attribution-protocol/index.md): When an AI agent recommends a product and a sale happens later, on another device or session, can anyone prove which agent (and which recommendation) actually drove it? - [Agent Audit Trail](https://agenticweb.wiki/protocols/agent-audit-trail/index.md): Is there a standard, tamper-evident log format any autonomous AI agent can write its actions to, so a regulator, auditor or victim can later reconstruct exactly what it did and why? - [Agent Authorization Envelope](https://agenticweb.wiki/protocols/agent-authorization-envelope/index.md): How can a relying party verify offline, without calling the issuer, that an agent holds a mandate with limits, an expiry and a bounded delegation chain? - [Agent Authorization Grant](https://agenticweb.wiki/protocols/aauth/index.md): How can a conversational AI agent, reached over a channel without browser redirect (phone, SMS), obtain a properly scoped OAuth access token without impersonating the user? - [Agent Authorization Profile](https://agenticweb.wiki/protocols/aap/index.md): How can OAuth 2.0/JWT claims carry structured agent identity, task context, operational constraints, delegation chains, and human-oversight requirements for machine-to-machine agent calls? - [Agent Client Protocol](https://agenticweb.wiki/protocols/agent-client-protocol/index.md): How does a code editor invoke and converse with an interchangeable coding agent it did not build? - [Agent Commerce Kit (ACK)](https://agenticweb.wiki/protocols/agent-commerce-kit/index.md): How can an agent prove who owns it and pay another party, on any rail, with a receipt both sides can verify? - [Agent Communication Protocol](https://agenticweb.wiki/protocols/agent-communication-protocol/index.md): How did agents, applications, and people exchange multimodal REST messages before merging into A2A? - [Agent Connect Protocol (AGNTCY)](https://agenticweb.wiki/protocols/agent-connect-protocol/index.md): How does one agent (or an orchestrator) invoke and configure a remote agent it did not build, over a plain HTTP API? - [Agent Context Interchange Protocol](https://agenticweb.wiki/protocols/acip/index.md): How can a coding-agent host resolve organization, project, task, user, and vendor instruction sources into one deterministic set of rules with defined precedence, path scoping, enforceability, and an audit receipt? - [Agent Decision Commitments for Payments](https://agenticweb.wiki/protocols/agent-decision-commitment/index.md): How can an agent's payment decision, including the content it gave the model, be committed to before payment and later disclosed to dispute participants for verification? - [Agent Delegation Receipts](https://agenticweb.wiki/protocols/agent-delegation-receipts/index.md): How can a human principal's authorization of an AI agent (scope, boundaries, validity window, and operator instruction hash) be recorded as a signed, verifiable receipt that can be checked before the agent acts? - [Agent Directory Service](https://agenticweb.wiki/protocols/ads/index.md): Given a required skill, which agents provide it, where are they, and how can I fetch a verifiable, content-addressed record describing them? - [Agent Discovery Protocol](https://agenticweb.wiki/protocols/adp/index.md): How does an agent escalate from a cheap DNS lookup, to a well-known JSON metadata document, to a real-time WebSocket session, using only as much machinery as the task needs? - [Agent Identity and Discovery](https://agenticweb.wiki/protocols/aid/index.md): Given a domain, where is the agent and which protocol should I speak, with cryptographic proof the endpoint controls the matching key? - [Agent Identity Protocol (AIP)](https://agenticweb.wiki/protocols/aip/index.md): How can an autonomous agent prove a decentralized identity and a verifiable chain of delegated authority from its human or organizational principal? - [Agent Identity Protocol (AIP): Verifiable Delegation for AI Agent Systems](https://agenticweb.wiki/protocols/aip-delegation-chain/index.md): How can a relying party verify from a token and the issuer's public key who delegated authority, which agents it passed through, and that no hop widened it, when no authorization server is on the path? - [Agent Name Service v2 (ANS)](https://agenticweb.wiki/protocols/ans/index.md): What domain-anchored identity belongs to an autonomous agent, and at what assurance tier can that identity be trusted? - [Agent Network Protocol](https://agenticweb.wiki/protocols/anp/index.md): How can decentralized agents from different platforms authenticate, discover, and message each other without a central registry? - [Agent Payments Protocol](https://agenticweb.wiki/protocols/ap2/index.md): Did the user actually authorize what this agent is about to buy and pay for, and can the merchant prove it later? - [Agent Protocol](https://agenticweb.wiki/protocols/agent-protocol-aief/index.md): How does a client or dev-tool start a task on an autonomous agent, step it, and fetch results, regardless of which framework built the agent? - [Agent Readability Spec](https://agenticweb.wiki/protocols/vercel-agent-readability/index.md): How readable is this site's content for AI agents, and what specifically should be fixed? - [Agent Registration and Discovery Protocol](https://agenticweb.wiki/protocols/ardp/index.md): How can an autonomous agent register a stable identity, advertise its capabilities and current endpoints with a TTL, and be discovered by others with minimal metadata leakage? - [Agent Skills](https://agenticweb.wiki/protocols/anthropic-agent-skills-format/index.md): How can reusable, on-demand procedural instructions and bundled resources be packaged so any compatible agent can load and run them? - [Agent Transfer Protocol](https://agenticweb.wiki/protocols/agtp/index.md): How can AI agent traffic be identified, authenticated, and governed as a distinct application-layer protocol rather than blending into ordinary HTTP? - [Agent-Channel Frame for Identity-Keyed Fan-Out Delivery to Concurrent Sessions](https://agenticweb.wiki/protocols/agent-channel-fan-out/index.md): How can concurrent agent sessions of one identity-bound principal (or members of an organisation) exchange short structured messages through identity-keyed fan-out delivery rather than a shared-file fallback? - [agent-permissions.json](https://agenticweb.wiki/protocols/agent-permissions-json/index.md): Which page-level interactions (clicking, form submission, file upload, media control, script execution) may an agent perform while driving a web page's UI, as opposed to just fetching it? - [Agent-to-Wallet Protocol for Digital Credentials](https://agenticweb.wiki/protocols/a2wp/index.md): How can an AI agent hand a credential offer or presentation request to a wallet unchanged, so that credentials and keys never reach the agent, and still resume its task from the outcome and continuation? - [Agent-User Interaction Protocol](https://agenticweb.wiki/protocols/ag-ui/index.md): How does an agent stream state, generative UI, messages, and tool activity into a user-facing application in real time? - [Agent2Agent Protocol](https://agenticweb.wiki/protocols/a2a/index.md): How do two independent agents, built on different frameworks, discover each other and delegate a task to completion? - [Agentic Advertising Management Protocols](https://agenticweb.wiki/protocols/aamp/index.md): How do a buyer's agent and a seller's agent discover each other's inventory, negotiate terms and hand off a transaction inside the existing ad-tech stack? - [Agentic Authority Graph Validation](https://agenticweb.wiki/protocols/aagv/index.md): How can an implementer represent a delegated-authority graph in JSON and deterministically validate that declared revocation cuts disconnect all authority roots from all consequential sinks, without accepting vacuous or incomplete graphs? - [Agentic Commerce Protocol](https://agenticweb.wiki/protocols/agentic-commerce-protocol/index.md): How do a buyer's agent and a merchant complete a deterministic, programmatic checkout without the agent becoming the merchant of record? - [Agentic Mobile Protocol (AMP)](https://agenticweb.wiki/protocols/amp-ant/index.md): How can an AI agent shop and pay through a person's mobile wallet, within limits the person signed in advance, and have each step checked against that permission? - [Agentic Real Time Framework](https://agenticweb.wiki/protocols/artf/index.md): How does a host advertising platform invoke a third party's agent service, deployed as a container inside its own infrastructure, to mutate a bid request in real time? - [Agentic Resource Discovery](https://agenticweb.wiki/protocols/ard/index.md): Where are an organization's discoverable agentic resources (MCP servers, A2A agents, skills, registries), and how can they be found by search rather than pre-installed one at a time? - [agents.json](https://agenticweb.wiki/protocols/agents-json/index.md): How does an agent learn which multi-step API call sequences ("flows") a service supports, on top of its raw OpenAPI surface? - [AGENTS.md](https://agenticweb.wiki/protocols/agents-md/index.md): What build, test, and convention instructions should a coding agent follow in this repository? - [agents.txt](https://agenticweb.wiki/protocols/agents-txt/index.md): Which agent-facing protocols (payments, auth, MCP, skills, A2A) does this site speak, and where? - [Agora (agent marketplace protocol)](https://agenticweb.wiki/protocols/agora-commerce-protocol/index.md): How can an AI agent discover, hire, and pay another AI agent for a paid job, with escrowed on-chain settlement? - [Agora Protocol](https://agenticweb.wiki/protocols/agora-protocol/index.md): How can two heterogeneous LLM agents communicate efficiently, moving from expensive natural-language negotiation to a cheap, mutually agreed structured protocol? - [AI Agent Authentication and Authorization (AIMS)](https://agenticweb.wiki/protocols/aiagent-auth/index.md): Is there an IETF-endorsed way to authenticate and authorize an AI agent, and has the WIMSE working group actually taken this on? - [AI Agent Execution Profile of SCITT](https://agenticweb.wiki/protocols/scitt-ai-agent-execution/index.md): How can an agent operator produce independently verifiable, tamper-evident records of an AI agent's material actions using SCITT signed statements and an independent transparency service? - [AI Catalog well-known file](https://agenticweb.wiki/protocols/ai-catalog-well-known-file/index.md): Which AI-capable artifacts and registries does this domain publish? (superseded question -- see ard) - [AI Crawler User-Agent Tokens in robots.txt](https://agenticweb.wiki/protocols/ai-crawler-tokens-robots/index.md): Which named AI crawler or agent user-agent tokens may a website allow or disallow in robots.txt, and what does each token actually control (search indexing, AI training, or live user-triggered fetches)? - [ai.txt](https://agenticweb.wiki/protocols/ai-txt/index.md): May AI systems train on, scrape, index, or cache this site's content, and under what per-agent or per-path conditions? - [AIPREF Content-Usage Attachment](https://agenticweb.wiki/protocols/aipref-content-usage-attachment/index.md): How does a publisher attach its AI-use preferences to content served over HTTP, so an automated system can find them? - [AIPREF Vocabulary](https://agenticweb.wiki/protocols/aipref-vocabulary/index.md): What controlled set of values expresses a publisher's AI-use preferences, independent of how they are attached to content? - [AITP (Agent Interaction & Transaction Protocol)](https://agenticweb.wiki/protocols/aitp/index.md): How do two agents representing different, mutually untrusted people or businesses (e.g. a personal assistant and an airline's booking agent) talk to each other, exchange forms and payment requests, and not just plain text? - [An Audit Record Format for AI Agent Authorization Decisions](https://agenticweb.wiki/protocols/wimse-agent-audit-record/index.md): What should a tamper-evident record of an agent's authorization decision contain? - [Anonymous Bot Authentication](https://agenticweb.wiki/protocols/anonymous-bot-auth/index.md): How can a site tell authorised, well-behaved bots from others, and rate-limit them, without learning which bot sent each request? - [AP2 Checkout Mandate](https://agenticweb.wiki/protocols/ap2-checkout-mandate/index.md): What exactly did the user approve for checkout? - [Apache Ossie (formerly Open Semantic Interchange)](https://agenticweb.wiki/protocols/osi/index.md): How can an AI agent or BI tool read a metric or data-model definition and get the same meaning another tool intended? - [api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs](https://agenticweb.wiki/protocols/api-catalog-rfc9727/index.md): Given a publisher's domain, where is the machine-readable list of the APIs it exposes? - [Attenuated Delegation Profile for Automated Agents](https://agenticweb.wiki/protocols/oauth-agent-delegation/index.md): How can an automated agent pass on a user's authority so that each hop can only narrow scope, floors, and expiry? - [auth.md](https://agenticweb.wiki/protocols/auth-md/index.md): How does an AI agent register a new account for its user on a service, without a human filling out a sign-up form or an OAuth redirect flow existing to authorize it? - [Cloudflare Pay per crawl](https://agenticweb.wiki/protocols/cloudflare-pay-per-crawl/index.md): How can a site charge an AI crawler per request, and how does the crawler agree to pay? - [CoMP (Content Monetization Protocols)](https://agenticweb.wiki/protocols/iab-comp/index.md): How does a licensed AI system ask a publisher or content marketplace for content, saying who it is, how it authenticates and what it will use the content for? - [Content Signals Policy](https://agenticweb.wiki/protocols/cloudflare-content-signals-policy/index.md): May content fetched under a robots.txt allow rule also be used for search indexing, as live input to an AI answer, or for AI model training? - [Coral Protocol (CoralOS)](https://agenticweb.wiki/protocols/coral-protocol/index.md): How do independently-built agents from a public marketplace get orchestrated together into one multi-agent system, with privacy isolation and built-in payment budgets, on top of MCP? - [Credential Delegation Protocol for AI Agents in Multi-System Environments](https://agenticweb.wiki/protocols/credential-delegation-protocol-wimse/index.md): How can a human user delegate scoped, attenuated, revocable credentials to AI agents across multiple service providers without exposing the underlying OAuth tokens to the agents? - [Discovery of Model Context Protocol Servers via DNS TXT Records](https://agenticweb.wiki/protocols/mcp-dns-discovery/index.md): How can a client discover an MCP server's endpoint, the operating organisation's identity, and a signed ~handle identity envelope using DNS TXT records under a domain? - [DNS for AI Discovery](https://agenticweb.wiki/protocols/dns-aid/index.md): Given a domain, where is its agent endpoint, what protocol does it speak, and how can that be verified via DNSSEC/DANE? - [DNS-Based Agent Naming](https://agenticweb.wiki/protocols/dan/index.md): Given a domain, which AI agents does it publish, and how can I locate and cryptographically bind to their service endpoint using DNS alone? - [EMV Agentic Payments – Framework for Specifications](https://agenticweb.wiki/protocols/emv-agentic-payments/index.md): When a card network, issuer, merchant, or wallet sees an AI-agent-initiated card payment, how do they consistently find out what the consumer actually authorised — recurring purchase, spending cap, post-transaction change — rather than each building a bespoke, one-off signal? - [ERC-8001: Agent Coordination Framework](https://agenticweb.wiki/protocols/erc-8001/index.md): How can several agents agree on-chain that a coordinated action may run only once every required participant has signed an acceptance? - [ERC-8004: Trustless Agents](https://agenticweb.wiki/protocols/erc-8004/index.md): Who is an agent, and what onchain identity, reputation and validation record does it carry? - [ERC-8126: AI Agent Verification](https://agenticweb.wiki/protocols/erc-8126/index.md): How can an agent registered under ERC-8004 be put through standard security checks and carry a comparable risk score? - [ERC-8183: Agentic Commerce](https://agenticweb.wiki/protocols/erc-8183/index.md): How can two agents (a client and a provider) settle a job on-chain, with funds held in escrow and released only once an evaluator attests the work was done? - [ERC-8196: AI Agent Authenticated Wallet](https://agenticweb.wiki/protocols/erc-8196/index.md): How can an asset owner let an AI agent transact from a wallet only within a policy the owner set, with proof and an audit trail for every action? - [ERC-8226 Regulated Agent Mandate](https://agenticweb.wiki/protocols/erc-8226/index.md): What scoped, time-bounded, and financially capped authority may an on-chain agent exercise on a regulated asset holder's behalf? - [ERC-8444: Agentic Resource Discovery (ARD) Onchain](https://agenticweb.wiki/protocols/erc-8444/index.md): How can on-chain skills, task bounties and agent identities be found through ordinary ARD search, without the searcher needing a wallet or an RPC endpoint? - [GB/Z 185 Artificial intelligence — Agent interconnection (人工智能 智能体互联)](https://agenticweb.wiki/protocols/gbz-185-agent-interconnection/index.md): How do AI agents built by different Chinese companies identify, describe, find and call each other, and invoke tools, under one national framework? - [High-Assurance Agent Control Envelope](https://agenticweb.wiki/protocols/haace/index.md): How can a relying party gate an exact agent action at execution time so that missing, stale, or indeterminate identity, authorization, evidence, revocation, or human-approval prerequisites fail closed? - [HTTP Message Signatures](https://agenticweb.wiki/protocols/http-message-signatures/index.md): How can HTTP messages carry end-to-end component integrity and proof of possession, independent of transport-layer security? - [ID MANDAT: A Machine-Readable Credential for the Agents of a Company](https://agenticweb.wiki/protocols/idmandat-credential/index.md): How can a recipient find out which company stands behind an agent and what that agent is declared to be allowed and not allowed to do on the company's behalf? - [Identity Assertion JWT Authorization Grant](https://agenticweb.wiki/protocols/identity-assertion-authz-grant/index.md): How can an app or AI agent, already SSO-federated to a user's enterprise identity provider, obtain scoped access to a third-party API or MCP server without a fresh consent screen at that third party? - [Identity Continuation Assertion for OAuth 2.0 Token Exchange](https://agenticweb.wiki/protocols/oauth-id-continuation/index.md): How can a workload obtain an ID-JAG for another service after the user who started the session is no longer present? - [JAFAR: A JSON-Based Format for Publishing IP Ranges of Automated HTTP Clients](https://agenticweb.wiki/protocols/jafar/index.md): How can a crawler or bot operator publish the IP ranges its automated clients use, in one machine-readable format that sites can check traffic against? - [KYA-OS (Know Your Agent Operating System)](https://agenticweb.wiki/protocols/kya-os/index.md): How can an MCP server tell which agent is calling, on whose authority it acts, and keep signed proof of what it did? - [KYAPay Token](https://agenticweb.wiki/protocols/kyapay-token/index.md): How can an authorization or resource server from one vendor check which agent is calling and accept its payment token, when the token was issued by another vendor? - [L402](https://agenticweb.wiki/protocols/l402/index.md): How can a client pay for, and then authenticate to, a metered API resource over the Lightning Network with no accounts or database-backed sessions? - [llms.txt](https://agenticweb.wiki/protocols/llms-txt/index.md): Where can an agent find a concise, curated map of a site's content, written for language models rather than browsers? - [LMOS (Language Model Operating System)](https://agenticweb.wiki/protocols/lmos/index.md): How does an agent or tool from one organization describe itself and get discovered by agents from another organization, across network boundaries? - [LWS 1.0 Authentication Suite: Self-signed Identity using Controlled Identifiers](https://agenticweb.wiki/protocols/lws10-authn-ssi-cid/index.md): How can an agent that signs its own JWT identity tokens authenticate to a Linked Web Storage server, with verifiers validating the token against the agent's controlled identifier document? - [Machine Payments Protocol](https://agenticweb.wiki/protocols/mpp/index.md): How can a machine client (an agent, script, or another server) pay for an HTTP resource using any payment network, not just one? - [Markdown for Agents](https://agenticweb.wiki/protocols/cloudflare-markdown-for-agents/index.md): Can an agent ask a site for a Markdown version of an HTML page, instead of parsing the HTML itself? - [MCP Apps](https://agenticweb.wiki/protocols/mcp-apps/index.md): How does an MCP tool deliver an interactive UI (chart, form, dashboard) that renders inline in a chat client? - [MCP Server Cards (SEP-2127)](https://agenticweb.wiki/protocols/mcp-server-cards/index.md): How can a client learn what an MCP server offers before connecting to it? - [Model Context Protocol](https://agenticweb.wiki/protocols/mcp/index.md): How does an AI application call tools and pull structured context, prompts, and data from an external server? - [Natural Language Interaction Protocol](https://agenticweb.wiki/protocols/nlip/index.md): Can this agent or service exchange natural-language, multi-modal messages using a shared, vendor-neutral envelope instead of a bespoke API? - [NLWeb](https://agenticweb.wiki/protocols/nlweb/index.md): How can a site expose a natural-language question-answering interface grounded in its own Schema.org-structured content, for both humans and agents? - [OAuth Client ID Metadata Document](https://agenticweb.wiki/protocols/oauth-cimd/index.md): How can an authorization server accept an OAuth client, such as an MCP client, that it has never seen before, without pre-registration or Dynamic Client Registration? - [OAuth Profile for Delegated AI Agent Authorization](https://agenticweb.wiki/protocols/daap/index.md): How can a human user delegate constrained, attenuable, revocable authority to an AI agent using standard OAuth mechanisms, with no new endpoints or claims required? - [OAuth Protected Resource and Authorization Server Metadata (as used for agent authorization)](https://agenticweb.wiki/protocols/oauth-metadata-for-agents/index.md): How does an agent (or an MCP client acting for it) discover which authorization server protects a resource, and what that authorization server's endpoints and capabilities are, before requesting access? - [Official MCP Registry](https://agenticweb.wiki/protocols/mcp-registry/index.md): Where can an agent or client find a catalogue of public MCP servers, and how do sub-registries mirror it? - [Open Agentic Schema Framework](https://agenticweb.wiki/protocols/oasf/index.md): How can an agent's skills, domains, deployment modules and identity be described using a shared, versioned taxonomy so registries can classify and filter it consistently? - [Open Knowledge Format](https://agenticweb.wiki/protocols/okf/index.md): How can an organization package durable, structured knowledge (schemas, metrics, playbooks, runbooks) so both humans and agents can read, produce, and trust it without a bespoke SDK? - [Open Responses Specification](https://agenticweb.wiki/protocols/open-responses/index.md): How can an agent or application call LLM inference and server-side tool loops across multiple providers using a single vendor-neutral wire format? - [OpenA2A Agent Authorization Protocol](https://agenticweb.wiki/protocols/opena2a-aap/index.md): How does an agent present identity, a scoped grant, a delegation, and an attestation when it calls another agent or a tool? - [OpenAI Plugins (formerly Apps SDK)](https://agenticweb.wiki/protocols/openai-apps-sdk-manifests/index.md): How does a developer publish a tool with an optional interactive UI that ChatGPT and Codex can call? - [OpenTelemetry GenAI Semantic Conventions (agents and MCP)](https://agenticweb.wiki/protocols/otel-genai-semconv/index.md): What span, metric and attribute names should agent frameworks and MCP clients and servers emit, so traces of agent runs and tool calls line up across vendors? - [Per-Call Proof for Local Tool Invocation by AI Agents](https://agenticweb.wiki/protocols/local-tool-call-proof/index.md): How can a local tool server (for example an MCP stdio server) verify that each invocation from an AI agent passed a policy decision, without reusable credentials in the agent process? - [Personal Agent Protocol (Poppy)](https://agenticweb.wiki/protocols/personal-agent-protocol/index.md): How does a customer's personal agent identify itself to a business and show it has the customer's permission to act? - [Really Simple Licensing](https://agenticweb.wiki/protocols/rsl/index.md): What machine-readable license, price, and authorization terms govern how AI systems and crawlers may access or reuse a publisher's content? - [s402](https://agenticweb.wiki/protocols/s402/index.md): How can an agent pay a Sui-native resource using six payment schemes (including prepaid batching and escrow), while staying wire-compatible with plain x402 clients? - [Secure Low-Latency Interactive Messaging](https://agenticweb.wiki/protocols/slim/index.md): How can agents send secure, low-latency, group-aware messages (point-to-point, pub/sub, fire-and-forget, streaming) as a transport underneath higher-level protocols like A2A and MCP? - [Security Principal and Verifier Binding for Agent Communication Protocols](https://agenticweb.wiki/protocols/agent-principal-binding/index.md): How can an agent communication protocol state, for each security-relevant claim (user authority, agent instance, tool identity, delegation, session, action evidence), which field carries it, which party verifies it, and what happens when it is absent, stale, or unverifiable? - [Signature Agent Card (Web Bot Auth registry)](https://agenticweb.wiki/protocols/web-bot-auth-signature-agent-card/index.md): What identity, purpose, rate expectations and cryptographic keys belong to a signed bot? - [SPIFFE (Secure Production Identity Framework for Everyone)](https://agenticweb.wiki/protocols/spiffe/index.md): Which workload instance — potentially including an AI agent process — is making this request, verifiable independent of network location? - [Text and Data Mining Reservation Protocol](https://agenticweb.wiki/protocols/tdmrep/index.md): Has a rights holder reserved text-and-data-mining rights over this content, and what policy governs any permitted mining? - [The 'knowledge-linkset' Well-Known URI for Publishing Knowledge Artefacts](https://agenticweb.wiki/protocols/knowledge-linkset/index.md): How can a web origin publish, at one well-known location, a checkable list of the knowledge artefacts it offers (graph serializations, JSON-LD context, text file, chunk export, change ledger) so that agents can find them and verify digests? - [The Agent Identity Document: A Hosted, Accountable Public Record for AI Agents](https://agenticweb.wiki/protocols/agent-identity-document/index.md): How can a counterparty look up who an agent is, who is accountable for it, what the provider has checked about its operator, and whether it has been withdrawn, when the operator has no domain or PKI of their own? - [Universal Commerce Protocol](https://agenticweb.wiki/protocols/ucp/index.md): Can an agent discover a business's commerce capabilities, build a cart, and check out interoperably across shopping, lodging, and food ordering? - [VCAP: Verified Commerce for Agent Protocols](https://agenticweb.wiki/protocols/vcap/index.md): How can two autonomous agent-run marketplaces settle a payment only once independent evidence shows the purchased work was actually delivered? - [Verifiable Intent](https://agenticweb.wiki/protocols/vi/index.md): After an agent completes a purchase on a user's behalf, can the merchant, issuer and consumer all point to the same cryptographic record of what the user actually authorized? - [Visa Trusted Agent Protocol](https://agenticweb.wiki/protocols/tap/index.md): How does a merchant recognize that an approved commerce agent, rather than a crawler or fraudulent bot, is interacting with its site or API? - [Web Agent Protocol (WAP)](https://agenticweb.wiki/protocols/web-agent-protocol/index.md): How does a recorded human browsing session get replayed reliably by an agent later, or turned into a reusable tool another agent can call? - [Web Bot Auth HTTP Message Signatures](https://agenticweb.wiki/protocols/webbotauth/index.md): Which automated client made this HTTP request, and can the origin verify it cryptographically? - [WebMCP](https://agenticweb.wiki/protocols/webmcp/index.md): What JavaScript tools can a web page register so an in-browser AI agent can call them directly instead of scraping the DOM? - [WIMSE AI Identity Management System](https://agenticweb.wiki/protocols/wimse-aims/index.md): What are the best practices for authenticating and authorising interactions between AI agents and the services they call? - [Workload Authorization Grant](https://agenticweb.wiki/protocols/workload-authz-grant/index.md): How can a workload, such as an AI agent, obtain an access token from a third party's authorization server without a per-workload administrator step? - [Workload Identity in Multi System Environments (WIMSE) Architecture](https://agenticweb.wiki/protocols/wimse/index.md): How do workloads — including, per a related draft, AI agents — authenticate to each other and to services across platforms and trust domains? - [Workload Identity Metadata](https://agenticweb.wiki/protocols/wimse-workload-identity-metadata/index.md): How can a workload's group, role, and entitlement attributes be conveyed to relying parties without encoding them in the workload identifier? - [x401: HTTP Proof Requirement Protocol](https://agenticweb.wiki/protocols/x401/index.md): How can a resource ask an agent to prove something about the person behind it, such as being a verified human, before serving a request? - [x402](https://agenticweb.wiki/protocols/x402/index.md): How can an HTTP client pay per-request or per-resource, in stablecoins, without accounts, API keys, or signup? ## Terms & Concepts - [All terms glossary](https://agenticweb.wiki/glossary/index.md) - [A2A Task](https://agenticweb.wiki/terms/a2a-task/index.md): An A2A Task is the core stateful unit of work in the Agent2Agent (A2A) protocol. - [ACP (four protocols)](https://agenticweb.wiki/terms/acp/index.md): ACP refers to four distinct specifications from four groups across three steps of the map. - [Agent Card](https://agenticweb.wiki/terms/agent-card/index.md): An Agent Card is a JSON document that an A2A server publishes to describe itself to other agents: its identity (name, description… - [Agent skill](https://agenticweb.wiki/terms/agent-skill/index.md): An Agent Skill is a portable, self-contained folder of domain instructions, workflow rules, and helper scripts—anchored by a SKILL.md file… - [Agent2Agent (A2A)](https://agenticweb.wiki/terms/agent-to-agent/index.md): Agent2Agent (A2A) is an open protocol—launched by Google in April 2025 and stewarded by the Linux Foundation Agentic AI Foundation… - [Agentic EoR (Employer / Entity of Record)](https://agenticweb.wiki/terms/agentic-eor/index.md): An Agentic EoR (Employer of Record or Entity of Record) is a legal, financial, and cryptographic intermediary that acts as the accountable… - [Agentic Resource Discovery (ARD) manifest](https://agenticweb.wiki/terms/ard-manifest/index.md): An ARD manifest (/.well-known/ard.json, superseding /.well-known/ai-catalog.json in ARD v0.91) is a JSON document published at an origin's… - [Agentic web](https://agenticweb.wiki/terms/agentic-web/index.md): The agentic web is the ordinary web plus a layer of conventions that let software agents, rather than people in browsers, discover what a… - [Agentmap directive](https://agenticweb.wiki/terms/agentmap/index.md): Agentmap is a line a publisher can add to robots.txt, of the form Agentmap: https://example.com/entries.json, that points a crawler at a… - [AI agent](https://agenticweb.wiki/terms/ai-agent/index.md): An AI agent (or software agent) is an autonomous or semi-autonomous program that pursues a user-delegated goal by planning across steps… - [AI crawler tokens](https://agenticweb.wiki/terms/ai-crawler-tokens/index.md): AI crawler tokens are the User-agent names AI companies document for use in robots.txt under RFC 9309, split by purpose rather than… - [API Catalog (RFC 9727)](https://agenticweb.wiki/terms/api-catalog/index.md): api-catalog (RFC 9727, published June 2025) is an IANA-registered well-known URI (/.well-known/api-catalog) and HTTP link relation… - [Audit record](https://agenticweb.wiki/terms/audit-record/index.md): An audit record in the agentic web is a structured, tamper-evident log entry capturing what action an agent took, which tool or endpoint… - [Buyer of Record & Merchant of Record (Agentic Commerce)](https://agenticweb.wiki/terms/buyer-of-record/index.md): In agentic commerce, the Buyer of Record (BoR) and Merchant of Record (MoR) define which legal entities bear tax, chargeback, refund, and… - [Coding agent instruction files](https://agenticweb.wiki/terms/coding-agent-instructions/index.md): AGENTS.md is an open repository and origin convention (agents.md, stewarded under the Linux Foundation AAIF) for placing machine-targeted… - [Content usage preference](https://agenticweb.wiki/terms/content-usage-preference/index.md): A content usage preference is a machine-readable declaration by a publisher stating how automated systems may use a resource—for example… - [Content-Signal directive](https://agenticweb.wiki/terms/content-signal/index.md): Content-Signal is a machine-readable policy directive introduced by Cloudflare's Content Signals Policy that publishers place in… - [Context compaction](https://agenticweb.wiki/terms/context-compaction/index.md): Context compaction is the set of protocol and runtime patterns used to keep an AI agent's working context window bounded across multi-turn… - [Dynamic Client Registration & Client ID Metadata](https://agenticweb.wiki/terms/dynamic-client-registration/index.md): Dynamic Client Registration (DCR, RFC 7591) and OAuth Client ID Metadata Documents allow an AI agent or MCP host to authenticate with a… - [Elicitation](https://agenticweb.wiki/terms/elicitation/index.md): Elicitation (elicitation/create) is a capability in the Model Context Protocol (MCP) that lets an MCP server pause mid-execution and ask… - [Expired Internet-Draft](https://agenticweb.wiki/terms/expired-internet-draft/index.md): An Internet-Draft that has not been revised within 185 days. - [Facilitator](https://agenticweb.wiki/terms/facilitator/index.md): A facilitator in the x402 protocol is an optional third-party service that verifies and settles blockchain payments on behalf of a… - [Generative UI](https://agenticweb.wiki/terms/generative-ui/index.md): Generative UI is an interaction pattern in which an AI agent returns structured, declarative user-interface components—such as interactive… - [HTTP 402 Payment Required](https://agenticweb.wiki/terms/http-402-payment-required/index.md): HTTP 402 Payment Required is a standard HTTP status code (reserved since HTTP/1.1 and defined in RFC 9110 §15.5.3) indicating that a… - [HTTP Message Signatures](https://agenticweb.wiki/terms/rfc-9421/index.md): HTTP Message Signatures (RFC 9421, published February 2024 by the IETF HTTP Working Group) define a standard mechanism for creating… - [Human Not Present](https://agenticweb.wiki/terms/human-not-present/index.md): Human Not Present (HNP) is an execution mode in Google's Agent Payments Protocol (AP2) and FIDO-aligned agentic commerce frameworks in… - [Idempotency-Key header](https://agenticweb.wiki/terms/idempotency-key/index.md): An Idempotency-Key is a unique client-generated token attached to an HTTP POST/PATCH request or agent payment invocation so that if an… - [Interrupt](https://agenticweb.wiki/terms/interrupt/index.md): In AG-UI (Agent-User Interaction Protocol) and stateful agent runtimes, an interrupt is a structured lifecycle event where an agent pauses… - [Know Your Agent](https://agenticweb.wiki/terms/know-your-agent/index.md): Know Your Agent (KYA) means verifying which agent, and which operator behind it, is transacting before trusting it. - [llms.txt](https://agenticweb.wiki/terms/llms-txt-file/index.md): llms.txt is a Markdown index file placed at /llms.txt (with an optional expanded companion at /llms-full.txt) proposed by Jeremy Howard… - [Mandate](https://agenticweb.wiki/terms/mandate/index.md): A mandate in Google's Agent Payments Protocol (AP2) is a cryptographically signed, verifiable credential that authorises an agent to act… - [Markdown twin](https://agenticweb.wiki/terms/markdown-twin/index.md): A Markdown twin is a clean text/markdown representation of an HTML web page served either at a predictable sibling URL (such as… - [MCP](https://agenticweb.wiki/terms/model-context-protocol/index.md): The Model Context Protocol (MCP) is an open JSON-RPC 2.0 standard—originated by Anthropic in November 2024 and stewarded under the Linux… - [MCP Prompt](https://agenticweb.wiki/terms/mcp-prompt/index.md): An MCP Prompt is a reusable, parameterized prompt template or workflow slash-command exposed by an MCP server via prompts/list and… - [MCP Registry](https://agenticweb.wiki/terms/official-mcp-registry/index.md): The Official MCP Registry (modelcontextprotocol/registry) is the community-governed catalogue and HTTP API of public Model Context… - [MCP Resource](https://agenticweb.wiki/terms/mcp-resource/index.md): An MCP Resource is a URI-addressed piece of read-only context data—such as a file, database record, documentation page, or live telemetry… - [MCP Server Card](https://agenticweb.wiki/terms/server-card/index.md): A Server Card is a proposed static, discoverable document that describes an MCP server: what it is, who publishes it, and how to reach it… - [Origin trial](https://agenticweb.wiki/terms/origin-trial/index.md): An origin trial is Chrome's mechanism for shipping an experimental web-platform feature to real sites for a limited time before deciding… - [Pay per crawl](https://agenticweb.wiki/terms/pay-per-crawl/index.md): Pay per crawl is an HTTP monetization model where web publishers charge AI crawlers and retrieval agents per request using HTTP 402… - [Protected Resource Metadata](https://agenticweb.wiki/terms/protected-resource-metadata/index.md): OAuth 2.0 Protected Resource Metadata (RFC 9728, published April 2025) is a discovery document served at… - [Roots](https://agenticweb.wiki/terms/roots/index.md): Roots (roots/list) in the Model Context Protocol (MCP) are URI boundaries—typically file:// workspace directories or repository paths—that… - [Sampling](https://agenticweb.wiki/terms/sampling/index.md): Sampling (sampling/createMessage) is a client-exposed capability in the Model Context Protocol (MCP) that allows an MCP server to request… - [Signed agent](https://agenticweb.wiki/terms/signed-agent/index.md): A signed agent is an automated HTTP client or AI agent that cryptographically signs its outbound requests using RFC 9421 HTTP Message… - [SKILL.md](https://agenticweb.wiki/terms/skill-md/index.md): SKILL.md is the entrypoint manifest of an Agent Skill folder (agentskills.io). - [Streamable HTTP](https://agenticweb.wiki/terms/streamable-http/index.md): Streamable HTTP is the primary remote transport for the Model Context Protocol (MCP), replacing the early dual-endpoint HTTP+SSE transport… - [Subagent](https://agenticweb.wiki/terms/subagent/index.md): A subagent is an isolated child agent invocation spawned by a parent orchestrator agent to execute a bounded subtask in its own context… - [Tool](https://agenticweb.wiki/terms/tool/index.md): In the Model Context Protocol (MCP), a tool is a named, JSON-Schema-typed function exposed by an MCP server (tools/list and tools/call)… - [Verifiable Intent](https://agenticweb.wiki/terms/verifiable-intent/index.md): Verifiable Intent is a cryptographic trust specification—developed by Mastercard and contributed to the FIDO Alliance Payments Technical… - [Web Bot Auth](https://agenticweb.wiki/terms/web-bot-auth/index.md): Web Bot Auth is Cloudflare and IETF-draft profile of RFC 9421 HTTP Message Signatures whereby an AI crawler or agent signs its outbound… - [Well-known URI](https://agenticweb.wiki/terms/well-known/index.md): A well-known URI is a path beginning /.well-known/ at the root of an origin, reserved by RFC 8615 (May 2019, obsoleting RFC 5785) so that… - [Workload identity](https://agenticweb.wiki/terms/workload-identity/index.md): Workload identity is a cryptographic identity issued to a software process—such as a microservice, container, or autonomous AI… - [x402 Payment Payload](https://agenticweb.wiki/terms/x402-payment-payload/index.md): An x402 Payment Payload is the base64-encoded JSON credential carried in the HTTP X-PAYMENT (v1) or PAYMENT-SIGNATURE (v2) request header…