_ registry / mcp streamable-http · checked 13h ago

ransack

https://ransack.tools

Registry code: 85add9c632914927

api record

Web search & fetch MCP for AI agents: 12 engines, one key, flat $15/mo at ransack.tools.

from a public catalogue that lists it, not from the operator

endpoint
https://ransack.tools/mcp
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 ransack live?
Yes — it answered the hub's last check (checked 13h ago). It answered 100% of checks over the last 30 days.
Is ransack free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does ransack have?
8 tools: tasks_get, youtube, search_memory, ransack, get_report, search, ransack_permit_search, fetch.
Is ransack 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
562ms

last good check

priced tools
0

of 8 tools

_ answered our checks, 90 days 3 checks · signed record
  • 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 8 tools
8 auth-required 8 of 8 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.

  • tasks_get auth-required 13h ago

    Retrieve the status and result of an asynchronous task started by ransack(mode='fetch', background=true). Limits: 120/min. Error -32029 = rate limited, wait retry_after_s. See ransack(mode='help').

    mcp-tool

    {
      "type": "object",
      "title": "tasks_getArguments",
      "required": [
        "taskId"
      ],
      "properties": {
        "taskId": {
          "type": "string",
          "title": "Taskid"
        }
      }
    }
    arguments 13 lines
  • youtube auth-required 13h ago

    Retrieve the transcript from a YouTube video URL or video ID (not a keyword search). Limits: 120/min. See ransack(mode='help').

    mcp-tool

    {
      "type": "object",
      "title": "_youtube_trackedArguments",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "title": "Url"
        },
        "mode": {
          "type": "string",
          "title": "Mode",
          "default": "transcript"
        }
      }
    }
    arguments 18 lines
  • search_memory auth-required 41h ago

    Query the semantic index of prior fetched web content (pages, articles, transcripts). NOT conversational history: it recalls indexed content by meaning and keywords, not your past queries. Limits: 120/min. See ransack(mode='help').

    mcp-tool

    {
      "type": "object",
      "title": "search_memoryArguments",
      "required": [
        "query"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "title": "Limit",
          "default": 5
        },
        "query": {
          "type": "string",
          "title": "Query"
        }
      }
    }
    arguments 18 lines
  • ransack auth-required 13h ago

    Search, fetch, and research the live web. Modes: search, fetch, discover, hosts (7 keyless sources), shop, verify, help. format=markdown|json|hybrid. Every result is tagged with the engine that found it. Run mode='help' for the full manual (parameters, limits, error codes, data caveats) before guessing.

    mcp-tool

    {
      "type": "object",
      "title": "ransackArguments",
      "properties": {
        "url": {
          "type": "string",
          "title": "Url",
          "default": ""
        },
        "mode": {
          "type": "string",
          "title": "Mode",
          "default": "search"
        },
        "query": {
          "type": "string",
          "title": "Query",
          "default": ""
        },
        "crypto": {
          "type": "boolean",
          "title": "Crypto",
          "default": true
        },
        "detail": {
          "type": "string",
          "title": "Detail",
          "default": "concise"
        },
        "format": {
          "type": "string",
          "title": "Format",
          "default": "markdown"
        },
        "verbose": {
          "type": "boolean",
          "title": "Verbose",
          "default": true
        },
        "compress": {
          "type": "boolean",
          "title": "Compress",
          "default": false
        },
        "max_urls": {
          "type": "integer",
          "title": "Max Urls",
          "default": 50
        },
        "freshness": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "title": "Freshness",
          "default": null
        },
        "max_chars": {
          "type": "integer",
          "title": "Max Chars",
          "default": 200000
        },
        "background": {
          "type": "boolean",
          "title": "Background",
          "default": false
        },
        "max_results": {
          "type": "integer",
          "title": "Max Results",
          "default": 5
        },
        "must_contain": {
          "type": "string",
          "title": "Must Contain",
          "default": ""
        }
      }
    }
    arguments 83 lines
  • get_report auth-required 2d ago

    Retrieve a persisted research report and its citation map by report_id (legacy: reports produced before the research lane was retired 2026-09-20). Limits: 120/min. See ransack(mode='help').

    mcp-tool

    {
      "type": "object",
      "title": "get_reportArguments",
      "required": [
        "report_id"
      ],
      "properties": {
        "report_id": {
          "type": "string",
          "title": "Report Id"
        }
      }
    }
    arguments 13 lines
  • search auth-required 41h ago

    Search the live web. Thin alias of ransack(mode='search') for hosts that require tools literally named search and fetch (ChatGPT Deep Research); results carry the engine that found each one. Run ransack(mode='help') for the full manual.

    mcp-tool

    {
      "type": "object",
      "title": "search_aliasArguments",
      "required": [
        "query"
      ],
      "properties": {
        "query": {
          "type": "string",
          "title": "Query"
        },
        "freshness": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "title": "Freshness",
          "default": null
        },
        "max_results": {
          "type": "integer",
          "title": "Max Results",
          "default": 5
        }
      }
    }
    arguments 30 lines
  • ransack_permit_search auth-required 2d ago

    Search US government permit portals by street address. Currently accela_brevard (Brevard County FL: building permits incl. roofing/fence/pool work types, status, contractor). No browser, no captcha, keyless. Limits: 120/min. See ransack(mode='help').

    mcp-tool

    {
      "type": "object",
      "title": "ransack_permit_searchArguments",
      "required": [
        "address"
      ],
      "properties": {
        "portal": {
          "type": "string",
          "title": "Portal",
          "default": "accela_brevard"
        },
        "address": {
          "type": "string",
          "title": "Address"
        },
        "roofing_only": {
          "type": "boolean",
          "title": "Roofing Only",
          "default": false
        }
      }
    }
    arguments 23 lines
  • fetch auth-required 2d ago

    Fetch a URL and return its readable content. Thin alias of ransack(mode='fetch') for hosts that require tools literally named search and fetch (ChatGPT Deep Research). Run ransack(mode='help') for the full manual.

    mcp-tool

    {
      "type": "object",
      "title": "fetch_aliasArguments",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "title": "Url"
        },
        "max_chars": {
          "type": "integer",
          "title": "Max Chars",
          "default": 200000
        }
      }
    }
    arguments 18 lines
_ try it 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 85add9c632914927.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/85add9c632914927/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/85add9c632914927/badge.svg)](https://brick.blue/agent/85add9c632914927?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 know
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.