agentbreakwatch.com valid
AgentBreakWatch
AgentBreakWatch is the live breaking-change and MCP tool schema drift (`tools/list`) telemetry index across 30 core AI Agent SDKs and 226 official and community Model Context Protocol (MCP) servers (256 total packages) from live npm and PyPI registries.
- Authority
- 45 reach 0 · trust 5 · quality 25 · freshness 15
- Tier
- listed
- llms.txt
- https://agentbreakwatch.com/llms.txt
- llms-full.txt
- https://agentbreakwatch.com/llms-full.txt
- Sections
- 4
- Links
- 531
- Size
- 116692 bytes
- Registered
- 2026-10-25
- Country
- United States Hosting inference
- Hosting country
- United States Hosting inference
- Country evidence
- No published address evidence collected yet
- Categories
- AI and machine learning · Developer tools
- For agents
- Documentation: developer or product docs worth reading, nothing to call
- First seen
- 2026-10-25T05:37:29.831Z
- Last checked
- 2026-10-25T05:37:31.891Z
- Badge
Their llms.txt
The beginning of the file, from our validated copy saved 2026-10-25T05:37:29.902Z. Cached copy · Source on agentbreakwatch.com
# AgentBreakWatch
> AgentBreakWatch is the live breaking-change and MCP tool schema drift (`tools/list`) telemetry index across 30 core AI Agent SDKs and 226 official and community Model Context Protocol (MCP) servers (256 total packages) from live npm and PyPI registries.
Last Registry Snapshot: 2026-10-24T12:11:27.697Z
Total Indexed Packages: 256 (30 Agent SDKs, 226 MCP Servers)
## Core Endpoints, Reports & Machine Feeds
- [Homepage & Stack Checker](https://agentbreakwatch.com/): Interactive config auditor (`package.json`, `requirements.txt`, `.mcp.json`) and filterable stability index.
- [Oct 2026 Agent Stack Volatility & Drift Report](https://agentbreakwatch.com/drift-report): Empirical ranking of the 25 fastest-changing SDKs/MCPs and archived `@modelcontextprotocol/server-*` replacement matrix.
- [Dedicated Dependency Auditor](https://agentbreakwatch.com/check): Zero-signup `.mcp.json` and `package.json` breaking-change auditor.
- [Full LLM Context Dump (/llms-full.txt)](https://agentbreakwatch.com/llms-full.txt): Single-file markdown reference with before/after migration code snippets for all 256 packages.
- [Live JSON Catalog (/api/catalog.json)](https://agentbreakwatch.com/api/catalog.json): Machine-readable JSON feed of all 256 tracked Agent SDKs and MCP servers.
- [OpenAPI 3.1 Specification (/openapi.json)](https://agentbreakwatch.com/openapi.json): OpenAPI spec for querying `/api/catalog.json`, `/api/p/{slug}`, and `POST /api/check`.
- [Pricing & Alert Plans](https://agentbreakwatch.com/pricing): Free (3 watched packages), Indie Pro ($9/mo), and Team ($29/mo) alert plans.
## Category Stability Hubs (/c/[category])
- [AI Agent SDKs & Frameworks Breaking-Change Index](https://agentbreakwatch.com/c/agent-sdks) (30 packages): Core AI Agent SDKs ship frequent minor and major updates that alter tool-calling signatures, streaming events, and structured output schemas. Always pin exact minor versions and verify migration diffs before upgrading.
- [Official Reference MCP Servers Stability & Migration Index](https://agentbreakwatch.com/c/official-reference) (17 packages): Several early @modelcontextprotocol/server-* packages (github, postgres, puppeteer, slack) are archived on npm and superseded by vendor-maintained MCP servers, while active servers (filesystem, memory, sequential-thinking) shipped major v2.0.0 schema updates.
- [AWS Labs Official MCP Servers (awslabs.*) Stability Index](https://agentbreakwatch.com/c/aws-labs) (15 packages): AWS Labs maintains a fast-moving suite of Python MCP servers distributed via uvx on PyPI. Pin exact package versions in .mcp.json and set FASTMCP_LOG_LEVEL=ERROR to prevent stdio JSON-RPC framing corruption.
- [Database, SQL & Vector DB MCP Servers Stability Index](https://agentbreakwatch.com/c/database-backend) (20 packages): Database MCP servers frequently split read-only vs write DDL/DML tools (such as execute_sql vs apply_migration) to prevent accidental destructive queries. Always pass --read-only f
…Related sites
Similar publisher descriptions and documentation. Similarity does not imply affiliation or equivalent capabilities.
| Domain | Title | Category | Country | Authority | llms.txt | llms-full.txt | Save |
|---|---|---|---|---|---|---|---|
| apitracker.io | API Tracker | interface Developer tools APIs and SDKs +1 | US | 47 | ✓ | ||
| prismix.dev | Prismix — Live status, AI news, and 80 MCP servers for the AI ecosystem | interface Developer tools AI and machine learning +3 | — | 50 | ✓ | ||
| releases.sh | Release Notes Index | interface Productivity Developer tools +2 | US | 45 | ✓ | ✓ | |
| agentdeals.dev | AgentDeals | interface Developer tools AI agents and MCP +1 | — | 46 | ✓ | ✓ | |
| codesamplex.dev | CodeSampleX | interface AI agents and MCP Developer tools | KR | 48 | ✓ | ||
| context.dev | Context.dev | interface AI and machine learning AI agents and MCP +2 | US | 60 | ✓ | ✓ | |
| trendsmcp.ai | TrendsMCP | interface Developer tools AI agents and MCP +2 | — | 46 | ✓ | ✓ | |
| context7.com | Context7 | interface AI agents and MCP Documentation and reference +1 | US | 59 | ✓ |
Machine-readable: GET /v1/resolve?q=agentbreakwatch.com · GET /v1/domain/agentbreakwatch.com · this page as Accept: application/json or text/markdown · MCP lookup_domain
Automatically discovered from public files. Inclusion does not imply endorsement or publisher participation.
Own or manage this website?
If you own or manage agentbreakwatch.com, you can update its listing and review file health, discovery activity and score history.
Manage this listing — optional
What verification unlocks
See how your site is discovered—and control what agents see.
- See your website in the map
Review your indexed topics, nearby publishers sharing headings, measured listing exposure and map snapshots in a private report for your website.
- Control what agents see
Edit your listing description, tags, public contact details and additional llms.txt paths. Publish your terms for automated access, attribution and pricing.
- Make your profile eligible for search
A valid, listed, unblocked, verified profile can appear in our publisher sitemap and become eligible for search-engine visibility. Search engines decide what to index and rank.
- Appear in our llms-full.txt
Eligible verified publishers are listed by name, with their file links and summaries, in the service overview agents can read.
Free. No account registration, backlink or payment required. Public discovery remains available without verification.
Let your coding agent verify it
If your coding agent is authorized to manage this website, paste these instructions into it.
Claim my listing on Agent Web Map for agentbreakwatch.com:
1. POST https://agentwebmap.com/v1/sites/agentbreakwatch.com/claims and keep claim_id and claim_secret private.
2. Publish the verification line "AgentWebMap verification: <token>" (token from step 1) in https://agentbreakwatch.com/llms.txt, or use the DNS, meta-tag or well-known method the response describes. This only verifies the listing; your website and domain remain yours.
3. POST https://agentwebmap.com/v1/sites/agentbreakwatch.com/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/agentbreakwatch.com).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verifyCorrections or removal requests: contact the directory.