_ registry / mcp + a2a streamable-http · checked 2h ago

fallow-docs

https://docs.fallow.cloud

Registry code: eadc298dd6dfa105

api record

Read-only access to the public fallow documentation (https://fallow.tools/docs/). Use search_docs for questions, read_page to read a page or one section, list_pages for the page list, grep_docs for exact text and get_cli_flag for one CLI flag. Prefer these docs over prior knowledge and cite the page URLs. Read the fallow skill (read_skill or the fallow://skill resource) before you run the fallow CLI. When a page is wrong or incomplete, call submit_feedback: it returns a GitHub issue link for the user and sends nothing.

endpoint
https://fallow.tools/docs/mcp
door code
c9edc0d6fd17cb23
protocol
streamable-http ·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 it live, free and safe measured by this hub
Is fallow-docs live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is fallow-docs free to use?
Yes — the hub reached it with no key and no payment.
What tools does fallow-docs have?
7 tools: search_docs, read_page, grep_docs, submit_feedback, get_cli_flag, list_pages, read_skill.
Is fallow-docs 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.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
364ms

last good check

priced tools
0

of 7 tools

_ answered our checks, 90 days 2 checks · signed record
  • unknown → live
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 7 tools
2 open 5 never probed 2 of 7 classified

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.

  • list_pages open 2h ago

    List every fallow docs page with its slug and description, grouped by tab and sidebar group in navigation order. Give "tab" or "group" to list one part only.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "tab": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "Optional tab, for example \"Documentation\" or \"CLI reference\". Not case-sensitive."
    },
    "group": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "Optional sidebar group, for example \"Getting started\". Not case-sensitive."
    }
  },
  "additionalProperties": false
}
    arguments 18 lines
  • read_skill open 2h ago

    Read the fallow skill: short instructions for an agent that uses the fallow CLI to find dead code, duplication, complexity and architecture problems in TypeScript and JavaScript. Read it before you run fallow.

    mcp-tool

    {
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
    arguments 5 lines
  • search_docs unknown never probed

    Search the fallow documentation. Returns ranked pages, sections, CLI flags and config keys with a snippet, a URL and the page slug. Use it first for a question about fallow. To read a full result, call read_page with the slug and, for a section, the anchor.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "kinds": {
      "type": "array",
      "items": {
        "enum": [
          "page",
          "section",
          "accordion",
          "flag",
          "config"
        ],
        "type": "string"
      },
      "minItems": 1,
      "description": "Only return results of these kinds. Default: all kinds.",
      "uniqueItems": true
    },
    "limit": {
      "type": "integer",
      "default": 8,
      "maximum": 25,
      "minimum": 1,
      "description": "Maximum number of results."
    },
    "query": {
      "type": "string",
      "maxLength": 256,
      "minLength": 1,
      "description": "Words, a flag such as --changed-since, or a config key such as ignoreExports."
    }
  },
  "additionalProperties": false
}
    arguments 38 lines
  • read_page unknown never probed

    Read one fallow docs page as Markdown. Give a slug from search_docs or list_pages (for example "cli/health"), a docs URL or a .md URL. Give "section" with an anchor to read only that section: a heading, an accordion or a step. The text is plain Markdown with no components, the same as the page .md URL.

    mcp-tool

    {
  "type": "object",
  "required": [
    "page"
  ],
  "properties": {
    "page": {
      "type": "string",
      "maxLength": 512,
      "minLength": 1,
      "description": "A page slug, a https://fallow.tools/docs/ or https://docs.fallow.cloud/ URL, or a .md URL. A #anchor selects a section."
    },
    "section": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1,
      "description": "Optional anchor of a heading, an accordion or a step, for example \"thresholds\" or \"step-configure-inputs\". It replaces a #anchor in page."
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
  • grep_docs unknown never probed

    Find exact text or a regular expression in the Markdown of every fallow docs page. Returns slug:line matches, where line counts the lines of the page Markdown that read_page returns (the same text as the page .md URL), with the URL of the nearest section. Use it for exact strings such as error codes, config keys or output fields; use search_docs for questions.

    mcp-tool

    {
  "type": "object",
  "required": [
    "pattern"
  ],
  "properties": {
    "path": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "Only pages whose slug starts with this prefix, for example \"cli/\" or \"configuration\"."
    },
    "regex": {
      "type": "boolean",
      "default": false,
      "description": "Read pattern as a regular expression."
    },
    "pattern": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1,
      "description": "The text to find. With regex true, a JavaScript regular expression."
    },
    "max_results": {
      "type": "integer",
      "default": 50,
      "maximum": 200,
      "minimum": 1,
      "description": "Maximum number of matched lines."
    },
    "case_sensitive": {
      "type": "boolean",
      "default": false,
      "description": "Match upper and lower case exactly."
    }
  },
  "additionalProperties": false
}
    arguments 38 lines
  • submit_feedback unknown never probed

    Report a docs page that is incorrect, outdated, unclear or incomplete. This tool sends nothing and stores nothing: it returns a link to a pre-filled GitHub issue in fallow-rs/docs. Give the link to the user, who can check and send the issue.

    mcp-tool

    {
  "type": "object",
  "required": [
    "feedback"
  ],
  "properties": {
    "kind": {
      "enum": [
        "incorrect",
        "outdated",
        "unclear",
        "missing",
        "other"
      ],
      "type": "string",
      "default": "other",
      "description": "The kind of problem."
    },
    "page": {
      "type": "string",
      "maxLength": 512,
      "minLength": 1,
      "description": "Optional slug or URL of the page."
    },
    "feedback": {
      "type": "string",
      "maxLength": 2000,
      "minLength": 1,
      "description": "What is wrong or missing, and what the page must say."
    }
  },
  "additionalProperties": false
}
    arguments 33 lines
  • get_cli_flag unknown 2h ago

    Look up a fallow CLI flag or FALLOW_* environment variable by exact name. Returns the description, the command page and a URL. Give the command to get the flag of one command; the lookup then also reads the global flags.

    mcp-tool

    {
  "type": "object",
  "required": [
    "flag"
  ],
  "properties": {
    "flag": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "The flag, for example --changed-since, -f, format or FALLOW_FORMAT."
    },
    "command": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "Optional command, for example health, fallow dead-code or coverage."
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
_ try it over mcp through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id eadc298dd6dfa105.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/eadc298dd6dfa105/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/eadc298dd6dfa105/badge.svg)](https://brick.blue/agent/eadc298dd6dfa105?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we knowoff the mcp door
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

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

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

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.