Koskamo

CanonicAI MCP

A read-only hosted MCP server providing access to CanonicAI's cited Answers corpus. It allows agents to list, retrieve, and search answers and canonical data constructs with provenance, serving as a machine-readable interface for unstructured corpora transformed into queryable records.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

CanonicAI MCP logo, by PeopleAnalystVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by PeopleAnalyst
MCP endpoint (Streamable HTTP)
https://canonicai.com/api/mcp
Vendor documentation

What its tools do

6 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (6)

6 of 6 have a description · 0 of 6 declare behavior hints · 6 of 6 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to canonicai.com ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search answers in the cited corpus
  • Retrieve specific answer details by slug
  • List available canonical data domains
  • Search constructs within canons

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: com.canonicai/canonicai-answers@1.0.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
canonicai-answers 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
6 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Tools

6 advertised

list_answers
Advertised by the server during the last successful anonymous check.

List published CanonicAI answer summaries from the static Answers corpus. Returns slug, id, question, canonical URLs, and citation counts.

list_answers input schema
{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "minimum": 0,
      "description": "Maximum summaries to return."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of summaries to skip."
    }
  },
  "additionalProperties": false
}
list_answers output schema
{
  "type": "object",
  "required": [
    "count",
    "answers"
  ],
  "properties": {
    "count": {
      "type": "integer"
    },
    "answers": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "slug",
          "id",
          "question",
          "url",
          "jsonUrl",
          "citationCount"
        ],
        "properties": {
          "id": {
            "type": "string"
          },
          "url": {
            "type": "string",
            "format": "uri"
          },
          "slug": {
            "type": "string"
          },
          "jsonUrl": {
            "type": "string",
            "format": "uri"
          },
          "question": {
            "type": "string"
          },
          "citationCount": {
            "type": "integer"
          }
        }
      }
    }
  }
}
get_answer
Advertised by the server during the last successful anonymous check.

Return one Answer contract v0 record with citations for a known slug. Never fabricates content for unknown slugs.

get_answer input schema
{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Answer slug from answers/index.json."
    }
  },
  "additionalProperties": false
}
get_answer output schema
{
  "type": "object",
  "required": [
    "id",
    "slug",
    "question",
    "answer",
    "citations",
    "url"
  ],
  "properties": {
    "id": {
      "type": "string"
    },
    "url": {
      "type": "string",
      "format": "uri"
    },
    "code": {
      "enum": [
        "not_found"
      ],
      "type": "string"
    },
    "home": {
      "type": "string"
    },
    "slug": {
      "type": "string"
    },
    "answer": {
      "type": "string"
    },
    "message": {
      "type": "string"
    },
    "question": {
      "type": "string"
    },
    "citations": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "shortAnswer": {
      "type": "string"
    }
  }
}
search_answers
Advertised by the server during the last successful anonymous check.

Search CanonicAI answers by simple deterministic token scoring over question, shortAnswer, and answer fields.

search_answers input schema
{
  "type": "object",
  "required": [
    "q"
  ],
  "properties": {
    "q": {
      "type": "string",
      "description": "Search query."
    },
    "limit": {
      "type": "integer",
      "minimum": 0,
      "description": "Maximum matches to return."
    }
  },
  "additionalProperties": false
}
search_answers output schema
{
  "type": "object",
  "required": [
    "query",
    "count",
    "matches"
  ],
  "properties": {
    "count": {
      "type": "integer"
    },
    "query": {
      "type": "string"
    },
    "matches": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "score",
          "slug",
          "id",
          "question",
          "url",
          "jsonUrl",
          "citationCount"
        ],
        "properties": {
          "id": {
            "type": "string"
          },
          "url": {
            "type": "string",
            "format": "uri"
          },
          "slug": {
            "type": "string"
          },
          "score": {
            "type": "integer"
          },
          "jsonUrl": {
            "type": "string",
            "format": "uri"
          },
          "question": {
            "type": "string"
          },
          "shortAnswer": {
            "type": "string"
          },
          "citationCount": {
            "type": "integer"
          }
        }
      }
    }
  }
}
list_canons
Advertised by the server during the last successful anonymous check.

List published CanonicAI domain canons from the static canon bundle. Returns slug, action statement, construct/source counts, and canonical URLs.

list_canons input schema
{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "minimum": 0,
      "description": "Maximum summaries to return."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of summaries to skip."
    }
  },
  "additionalProperties": false
}
list_canons output schema
{
  "type": "object",
  "required": [
    "count",
    "canons"
  ],
  "properties": {
    "count": {
      "type": "integer"
    },
    "canons": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "slug",
          "action_statement",
          "n_constructs",
          "n_source_works",
          "url",
          "jsonUrl"
        ],
        "properties": {
          "url": {
            "type": "string",
            "format": "uri"
          },
          "slug": {
            "type": "string"
          },
          "jsonUrl": {
            "type": "string",
            "format": "uri"
          },
          "n_constructs": {
            "type": "integer"
          },
          "date_modified": {
            "type": "string"
          },
          "n_source_works": {
            "type": "integer"
          },
          "action_statement": {
            "type": "string"
          }
        }
      }
    }
  }
}
get_canon
Advertised by the server during the last successful anonymous check.

Return one canon-v1 record (constructs, relationships, open divergences, provenance, source works) for a known slug. Never fabricates content for unknown slugs; returns close-match slugs instead.

get_canon input schema
{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Canon slug from canons/index.json."
    }
  },
  "additionalProperties": false
}
get_canon output schema
{
  "type": "object",
  "required": [
    "slug",
    "constructs",
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri"
    },
    "code": {
      "enum": [
        "not_found"
      ],
      "type": "string"
    },
    "slug": {
      "type": "string"
    },
    "message": {
      "type": "string"
    },
    "coverage": {
      "type": "object"
    },
    "guide_url": {
      "type": "string"
    },
    "constructs": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "provenance": {
      "type": "object"
    },
    "closeMatches": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "source_works": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "relationships": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "action_statement": {
      "type": "string"
    },
    "open_divergences": {
      "type": "array",
      "items": {
        "type": "object"
      }
    }
  }
}
search_constructs
Advertised by the server during the last successful anonymous check.

Search construct names and definitions across all canons (or one canon) by deterministic token scoring.

search_constructs input schema
{
  "type": "object",
  "required": [
    "q"
  ],
  "properties": {
    "q": {
      "type": "string",
      "description": "Search query."
    },
    "canon": {
      "type": "string",
      "description": "Restrict to one canon slug."
    },
    "limit": {
      "type": "integer",
      "minimum": 0,
      "description": "Maximum matches to return."
    }
  },
  "additionalProperties": false
}
search_constructs output schema
{
  "type": "object",
  "required": [
    "query",
    "count",
    "matches"
  ],
  "properties": {
    "count": {
      "type": "integer"
    },
    "query": {
      "type": "string"
    },
    "matches": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "score",
          "canon",
          "name",
          "definition",
          "url"
        ],
        "properties": {
          "url": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "canon": {
            "type": "string"
          },
          "score": {
            "type": "integer"
          },
          "definition": {
            "type": "string"
          }
        }
      }
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
401 ms
95th percentile latency
401 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 401 ms · metadata changed · 6 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http canonicai-mcp https://canonicai.com/api/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add canonicai-mcp --url https://canonicai.com/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable canonicai-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "canonicai-mcp": {
      "url": "https://canonicai.com/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "canonicai-mcp": {
      "type": "streamableHttp",
      "url": "https://canonicai.com/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start canonicai-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "canonicai-mcp": {
      "type": "http",
      "url": "https://canonicai.com/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http canonicai-mcp https://canonicai.com/api/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://canonicai.com/api/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "canonicai-mcp": {
      "serverUrl": "https://canonicai.com/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like CanonicAI MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 1,436

Do you run CanonicAI MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing