llms-txt

endpoint

https://llms-txt.dsh.sh/mcp

protocol

http-sse ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is llms-txt live?

Yes — it answered the hub's last check (checked 2h ago). It answered 99% of checks over the last 30 days.

Is llms-txt free to use?

Yes — the hub reached it with no key and no payment.

What tools does llms-txt have?

3 tools: llms_search, llms_index, llms_page.

Is llms-txt safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• llms_search reads unknown 6h ago

  Search the llms.txt indexes this server has parsed (section headings ×3, link titles ×2, notes ×1) and get the matching docs links with their covering index; pass site to search one site (it is indexed on demand). Use to jump straight to the right page of a docs set instead of reading the whole index.

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637383940

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "query",
      "task_context"
    ],
    "properties": {
      "site": {
        "type": "string",
        "maxLength": 2000,
        "description": "Restrict to one site (indexed via llms_index if not yet cached)."
      },
      "limit": {
        "type": "integer",
        "default": 10,
        "maximum": 50,
        "minimum": 1
      },
      "query": {
        "type": "string",
        "maxLength": 200,
        "minLength": 1,
        "description": "Words to match against section headings, link titles and notes."
      },
      "max_bytes": {
        "type": "integer",
        "default": 200000,
        "maximum": 500000,
        "minimum": 10000,
        "description": "Byte cap on the results array."
      },
      "task_context": {
        "type": "string",
        "maxLength": 500,
        "minLength": 1,
        "description": "One sentence on what the user is ultimately trying to do (the task this call serves). Required; it tunes the result and is how this free service learns what agents need."
      }
    }
  }

  arguments 40 lines copy
• llms_index reads unknown 6h ago

  Find and parse the llms.txt that covers a site or page URL: title, summary, H2 sections of [title](url) links with notes, the Optional section, and (HEAD-probed only) whether an llms-full.txt exists. Use first, before llms_page, whenever the user needs a product or library's own docs; every rung tried is returned so a miss is diagnosable.

  mcp-tool

  123456789101112131415161718192021222324252627

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "site",
      "task_context"
    ],
    "properties": {
      "site": {
        "type": "string",
        "maxLength": 2000,
        "minLength": 3,
        "description": "Site or page URL, e.g. \"docs.stripe.com\" or \"https://hono.dev/docs/\". The most specific covering llms.txt wins."
      },
      "refresh": {
        "type": "boolean",
        "default": false,
        "description": "Bypass the 24 h cache and fetch again."
      },
      "task_context": {
        "type": "string",
        "maxLength": 500,
        "minLength": 1,
        "description": "One sentence on what the user is ultimately trying to do (the task this call serves). Required; it tunes the result and is how this free service learns what agents need."
      }
    }
  }

  arguments 27 lines copy
• llms_page reads unknown 6h ago

  Return one docs page as markdown, paginated: tries Accept: text/markdown negotiation, the page's rel="alternate" markdown mirror, the .md / .html.md / index.md conventions, then a bounded HTML-to-markdown conversion. Use on the URLs llms_index returns, or on any docs URL you already hold.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "url",
      "task_context"
    ],
    "properties": {
      "url": {
        "type": "string",
        "format": "uri",
        "maxLength": 2000,
        "description": "Page URL (http/https)."
      },
      "offset": {
        "type": "integer",
        "default": 0,
        "maximum": 9007199254740991,
        "minimum": 0,
        "description": "Character offset to continue from (use next_offset from a truncated result)."
      },
      "max_chars": {
        "type": "integer",
        "default": 60000,
        "maximum": 200000,
        "minimum": 1000,
        "description": "Characters of markdown to return in this call."
      },
      "task_context": {
        "type": "string",
        "maxLength": 500,
        "minLength": 1,
        "description": "One sentence on what the user is ultimately trying to do (the task this call serves). Required; it tunes the result and is how this free service learns what agents need."
      }
    }
  }

  arguments 36 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.

• dephealth.dsh.sh dephealth mcp · 3 tools
• rss-feed.dsh.sh rss-feed mcp · 3 tools
• mcpfinder.dsh.sh mcpfinder mcp · 2 tools
• wayback-machine.dsh.sh wayback-machine mcp · 2 tools