~/ domain/fark.com.mdTHE AGENT-READABLE WEB

fark.com valid

Fark.com

Fark is a human-curated news aggregator, online since 1999. Readers submit links all day; Fark editors greenlight a fraction of them by hand, and every greenlit link gets its own comment thread. The editorial pick and the discussion under it are the content -- the article at the far end of the link

Visit publisher ↗

For agents: Fark is a human-curated news aggregator since 1999; editors greenlight submitted links, each with its own comment thread.

news aggregatorhuman-curated linkscomment threadsnews discussioneditorial picks

Authority
49 reach 17 · trust 5 · quality 12 · freshness 15
Tier
listed
llms.txt
https://www.fark.com/llms.txt
Sections
5
Links
0
Size
5400 bytes
Popularity rank
#10019
Registered
1997-09-23
Categories
Media · Community
For agents
Informational: content or services for people, nothing to operate
Audience
consumers · agents can: search content · en
First seen
2026-10-18T15:08:52.923Z
Last checked
2026-10-18T15:26:37.474Z
Badge
Agent Web Map badge for fark.com

Their llms.txt

The beginning of the file, from our validated copy saved 2026-10-21T14:08:25.121Z. Cached copy · Source on fark.com

# Fark.com

Fark is a human-curated news aggregator, online since 1999. Readers submit
links all day; Fark editors greenlight a fraction of them by hand, and every
greenlit link gets its own comment thread. The editorial pick and the
discussion under it are the content -- the article at the far end of the link
belongs to somebody else.

## MCP server

Fark runs a Model Context Protocol server. If you can attach connectors,
attach it and stop parsing our HTML.

- Endpoint: https://www.fark.com/mcp
- Transport: one stateless JSON-RPC endpoint over HTTP POST. No sessions, no
  SSE stream, no GET.
- Protocol revision: 2026-07-28, and only that one. An 'initialize' handshake
  from an older revision is answered with an error naming the revision we do
  speak.
- Every request carries BOTH of these in params._meta:
    "io.modelcontextprotocol/protocolVersion": "2026-07-28"
    "io.modelcontextprotocol/clientCapabilities": {}    (an object, may be empty)
  and mirrors them into request headers, which we check against the body. A
  header that is missing or does not match is HTTP 400 with JSON-RPC code
  -32020:
    MCP-Protocol-Version: 2026-07-28     (the same version; every request)
    Mcp-Method: tools/call               (the method in the body; every request)
    Mcp-Name: fark_headlines             (params.name; REQUIRED on tools/call)
  Mcp-Name is the one clients forget. It is not optional: a tools/call without
  it is refused 400 even when the other two headers are correct.
- Also send Content-Type: application/json -- another media type is refused
  415 -- and a User-Agent naming your client: Fark's perimeter turns away
  default toolkit user agents before the request reaches the endpoint (plain
  curl, with no -A, gets a 403).
- Open with server/discover.
- A worked call. This exact request returns HTTP 200 and the five newest
  headlines on the main tab:

    curl https://www.fark.com/mcp \
      -A 'YourAgent/1.0' \
      -H 'Content-Type: application/json' \
      -H 'MCP-Protocol-Version: 2026-07-28' \
      -H 'Mcp-Method: tools/call' \
      -H 'Mcp-Name: fark_headlines' \
      -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{
             "name":"fark_headlines",
             "arguments":{"tab":"main","limit":5},
             "_meta":{"io.modelcontextprotocol/protocolVersion":"2026-07-28",
                      "io.modelcontextprotocol/clientCapabilities":{}}}}'

- Server name and version: Fark MCP 1.0.0
- On claude.ai: add https://www.fark.com/mcp as a custom connector.
  In Claude Code: claude mcp add --transport http fark https://www.fark.com/mcp
- Machine-readable version of this section:
  https://www.fark.com/.well-known/mcp.json

## Tools

- fark_tabs: lists the Fark sections (tabs) this server serves, with their
  display names. Start here; every other tool takes a tab name or a link id.
…

Related sites

Other listed sites in Media. See the whole category →

DomainTitleCategoryCountryAuthorityllms.txtllms-full.txtSave
wordpress.org WordPress transactional Media Ecommerce US 77 ✓
apple.com Apple Podcasts documentation Media US 73 ✓
bilibili.com Bilibili / 哔哩哔哩 informational Media Entertainment and streaming CN 71 ✓
weather.com Weather.com informational Media FR 71 ✓
businessinsider.com Business Insider informational Media 70 ✓
commondreams.org Common Dreams documentation Healthcare Media US 70 ✓ ✓
conviva.com Conviva informational AI and machine learning Data and analytics +2 US 70 ✓ ✓
foxnews.com Fox News informational Media AI and machine learning GB 70 ✓

Machine-readable: GET /v1/resolve?q=fark.com · GET /v1/domain/fark.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 fark.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.

  • 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.

Verify your website—free

Preview the owner dashboard · All verification benefits

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 fark.com:
1. POST https://agentwebmap.com/v1/sites/fark.com/claims and keep claim_id and claim_secret private.
2. Publish the proof: add the line "AgentWebMap ownership: <token>" (token from step 1) to https://fark.com/llms.txt, or use the DNS, meta-tag or well-known method the response describes.
3. POST https://agentwebmap.com/v1/sites/fark.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/fark.com).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verify

Corrections or removal requests: contact the directory.

agent web map / a clearer way in.API & MCP · Contact