io.chainchoice/rankings

endpoint

https://chainchoice.io/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 io.chainchoice/rankings live?

Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.

Is io.chainchoice/rankings free to use?

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

What tools does io.chainchoice/rankings have?

7 tools: get_ranking_for_country, verify_receipt, search, hand_off, get_evidence, get_ranking, list_categories.

Is io.chainchoice/rankings 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.

• list_categories open 1h ago

  Every category ChainChoice ranks, with how many products it ranks, how many it assessed and left out with a reason, its leader, and its page.

  mcp-tool

  12345

  {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  }

  arguments 5 lines copy
• get_ranking_for_country unknown never probed

  The category's products as a reader in one country sees them: those available there, in order, with each one's published score and rank beside it. When nothing passes the country's availability filter, resultMode is "fallback" and the rows are the published order, none confirmed for that country.

  mcp-tool

  12345678910111213141516171819202122232425

  {
    "type": "object",
    "required": [
      "category",
      "country"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "maximum": 50,
        "minimum": 1,
        "description": "How many rows, from the top (default 10)."
      },
      "country": {
        "type": "string",
        "pattern": "^[A-Z]{2}$",
        "description": "ISO 3166-1 alpha-2, e.g. \"DE\"."
      },
      "category": {
        "type": "string",
        "description": "A category id from list_categories, e.g. \"exchange\" or \"hardware_wallet\"."
      }
    },
    "additionalProperties": false
  }

  arguments 25 lines copy
• verify_receipt unknown never probed

  Checks a signed receipt (as ChainChoice serves it, or an issuer envelope) against the keys ChainChoice publishes: whether its content hash matches and its signature is valid. The same verifier as POST /api/v1/verify.

  mcp-tool

  12345678910111213

  {
    "type": "object",
    "required": [
      "receipt"
    ],
    "properties": {
      "receipt": {
        "type": "object",
        "description": "The receipt JSON, with its signature."
      }
    },
    "additionalProperties": false
  }

  arguments 13 lines copy
• search unknown never probed

  Reads a query exactly as ChainChoice's search bars do (the same resolver as the homepage, the navigation field and the command palette) and returns that reading: the page it opens (a category's ranked list with the country, monthly volume, sort and filters read from the words, a product's verdict, a two-product compare, a guide), or the question it asks with at most three options, each with the page it opens; `answer`, the card the bars show before a page opens (the published #1 or the named product, its ChainChoice Score and rank, the margin, why it leads, its main trade-off, the list's page and a link to watch it), every figure from the published ranking; `readBy` when a model read a sentence the rules could not (only while ChainChoice's model tier is on and released by its measured eval); plus `open`, the homepage address that runs the same search. `country` applies a reader's country to a ranked list when the words name none; a country in the words wins. Nobody pays for a place in any answer.

  mcp-tool

  1234567891011121314151617181920

  {
    "type": "object",
    "required": [
      "query"
    ],
    "properties": {
      "query": {
        "type": "string",
        "maxLength": 120,
        "minLength": 1,
        "description": "The words a reader would type, e.g. \"kraken or coinbase\" or \"best exchange for a German user\"."
      },
      "country": {
        "type": "string",
        "pattern": "^[A-Z]{2}$",
        "description": "ISO 3166-1 alpha-2, e.g. \"DE\" (optional)."
      }
    },
    "additionalProperties": false
  }

  arguments 20 lines copy
• hand_off unknown never probed

  Once the reader has agreed to go to a provider (consent: true), returns what to hand over: the provider's own address as ChainChoice's catalog records it (never a referral or affiliate link; ChainChoice earns nothing from it), the product's published rank and ChainChoice Score, the reader's country and monthly volume, the ranked list's page with that setup, whether the provider serves that country, and a receipt signed with ChainChoice's published key (check it with verify_receipt) recording exactly what was handed over. A provider that does not serve the reader's country is not handed off: handedOff is false with the reason. It does not open anything, log the reader or change any ranking.

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637383940

  {
    "type": "object",
    "required": [
      "category",
      "product",
      "consent"
    ],
    "properties": {
      "vol": {
        "type": "integer",
        "maximum": 10000000,
        "minimum": 1,
        "description": "The reader's monthly amount (optional)."
      },
      "query": {
        "type": "string",
        "maxLength": 120,
        "description": "The reader's words, if the hand-off follows a search (optional, kept in the receipt)."
      },
      "consent": {
        "type": "boolean",
        "const": true,
        "description": "true only once the reader has agreed to be sent to this provider."
      },
      "country": {
        "type": "string",
        "pattern": "^[A-Z]{2}$",
        "description": "The reader's country, ISO 3166-1 alpha-2, e.g. \"DE\" (optional)."
      },
      "product": {
        "type": "string",
        "description": "A product id from get_ranking or a search answer."
      },
      "category": {
        "type": "string",
        "description": "A category id from list_categories, e.g. \"exchange\" or \"hardware_wallet\"."
      }
    },
    "additionalProperties": false
  }

  arguments 40 lines copy
• get_evidence unknown 1h ago

  For one category (and optionally one product id): each criterion, its weight, and per product the score with the quoted passage, its source URL and the day it was read.

  mcp-tool

  1234567891011121314151617

  {
    "type": "object",
    "required": [
      "category"
    ],
    "properties": {
      "product": {
        "type": "string",
        "description": "A product id from get_ranking (optional)."
      },
      "category": {
        "type": "string",
        "description": "A category id from list_categories, e.g. \"exchange\" or \"hardware_wallet\"."
      }
    },
    "additionalProperties": false
  }

  arguments 17 lines copy
• get_ranking unknown 1h ago

  The published order of one category: rank, product id, name and ChainChoice Score, with the methodology version, the dimension weights and what was assessed. The same order the category page and rankings.json publish.

  mcp-tool

  12345678910111213141516171819

  {
    "type": "object",
    "required": [
      "category"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "maximum": 50,
        "minimum": 1,
        "description": "How many rows, from the top (default 10)."
      },
      "category": {
        "type": "string",
        "description": "A category id from list_categories, e.g. \"exchange\" or \"hardware_wallet\"."
      }
    },
    "additionalProperties": false
  }

  arguments 19 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.