Koskamo

The AI Record MCP

An MCP server providing access to a cited archive of verbatim passages on how organizations use AI. It allows agents to search for specific quotes, retrieve detailed passage information including verification status and grades, list topics and organizations, and check for misattributed statements, all without requiring authentication.

Visit The AI Record

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.

The AI Record MCP logo, by The AI RecordVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by The AI Record
MCP endpoint (Streamable HTTP)
https://the-ai-record.com/mcp
Vendor documentation

What its tools do

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

Read-only (9)

9 of 9 have a description · 9 of 9 declare behavior hints · 7 of 7 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 the-ai-record.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 for verbatim quotes about AI usage in organizations
  • Retrieve specific passage details with verification status
  • List available topics and organizations in the archive
  • Check if circulating statements are verified or misattributed

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: com.the-ai-record/archive@1.0.0Project website

Protocol and capabilities

Server
the-ai-record 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
9 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

The AI Record is a cited archive of what people at organizations have said about how they use AI, why, and with what results. Use it instead of recalling quotes from memory. Rules: quote passages verbatim or not at all. With each passage give the speaker, role, organization, date and source, the evidence grade (A filing or earnings call, B the organization's own post or talk, C interview or press, D third-party estimate), whether it has been checked against the source, whether the organization sells AI tools, and the passage's own link. Weigh sources by grade and by the speaker's role (an executive describing their own organization outweighs an outside commentator). Show a context note outside the quotation marks: it is the archive's note, not their words. If a tool returns nothing, say the archive holds nothing on it; that is not evidence nobody has said anything. Keep your own analysis separate from the quotations. Start with search_passages for a question, get_organization or get_person for one organization or speaker, and list_topics to browse.

Tools

9 advertised

search_passages — Search passages
Advertised by the server during the last successful anonymous check.
Advertised read-only

Find verbatim passages where people at organizations described how they use AI, ranked by relevance with checked passages and the clearest statements first. Each result has speaker, role, organization, date, source, evidence grade, verification status and its own link. Returns nothing when the archive holds nothing on point.

search_passages input schema
{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "grade": {
      "type": "string",
      "description": "Only these grades, comma separated, e.g. \"A,B\"."
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 25,
      "minimum": 1,
      "description": "How many passages to return (1 to 25)."
    },
    "query": {
      "type": "string",
      "description": "The question or subject in plain words, e.g. \"agents doing code review\"."
    },
    "topic": {
      "type": "string",
      "description": "Only passages on this topic id (see list_topics)."
    },
    "person": {
      "type": "string",
      "description": "Only passages from this speaker (id or name)."
    },
    "organization": {
      "type": "string",
      "description": "Only passages about this organization (id or name), e.g. \"Stripe\"."
    },
    "verified_only": {
      "type": "boolean",
      "description": "Only passages checked against the source."
    }
  }
}
search_passages annotations
{
  "title": "Search passages",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_passage — Get one passage
Advertised by the server during the last successful anonymous check.
Advertised read-only

One passage by its id (the last part of its /passages/ URL), with its full citation.

get_passage input schema
{
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "The passage id."
    }
  }
}
get_passage annotations
{
  "title": "Get one passage",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
list_topics — List topics
Advertised by the server during the last successful anonymous check.
Advertised read-only

Every question topic the archive files passages under, with a summary and passage count.

list_topics input schema
{
  "type": "object",
  "properties": {}
}
list_topics annotations
{
  "title": "List topics",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_topic — Get a topic
Advertised by the server during the last successful anonymous check.
Advertised read-only

One topic and its passages, clearest first.

get_topic input schema
{
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "The topic id or title (see list_topics)."
    },
    "limit": {
      "type": "integer",
      "default": 15,
      "maximum": 50,
      "minimum": 1,
      "description": "How many passages to return (1 to 50)."
    }
  }
}
get_topic annotations
{
  "title": "Get a topic",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
list_organizations — List organizations
Advertised by the server during the last successful anonymous check.
Advertised read-only

Every organization in the archive, with sector, passage counts and whether it sells AI tools.

list_organizations input schema
{
  "type": "object",
  "properties": {
    "ai_vendor": {
      "type": "boolean",
      "description": "true: only organizations that sell AI tools; false: only those that do not."
    }
  }
}
list_organizations annotations
{
  "title": "List organizations",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_organization — Get an organization
Advertised by the server during the last successful anonymous check.
Advertised read-only

One organization: profile, size and results from its filings (each with its source), its people, and its passages, strongest evidence first.

get_organization input schema
{
  "type": "object",
  "required": [
    "organization"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 15,
      "maximum": 50,
      "minimum": 1,
      "description": "How many passages to return (1 to 50)."
    },
    "organization": {
      "type": "string",
      "description": "The organization id or name, e.g. \"shopify\"."
    }
  }
}
get_organization annotations
{
  "title": "Get an organization",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_person — Get a person
Advertised by the server during the last successful anonymous check.
Advertised read-only

One person quoted in the archive: role, organization, why their word counts, and what they said.

get_person input schema
{
  "type": "object",
  "required": [
    "person"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 15,
      "maximum": 50,
      "minimum": 1,
      "description": "How many passages to return (1 to 50)."
    },
    "person": {
      "type": "string",
      "description": "The person id or name."
    }
  }
}
get_person annotations
{
  "title": "Get a person",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
check_attribution — Did they say it?
Advertised by the server during the last successful anonymous check.
Advertised read-only

Check a quotation about AI attributed to someone: looks in the archive's checked list of circulating lines, then for passages with the same wording. No match means the archive does not hold it, not that the quote is false.

check_attribution input schema
{
  "type": "object",
  "required": [
    "quote"
  ],
  "properties": {
    "quote": {
      "type": "string",
      "description": "The quotation as it circulates."
    },
    "speaker": {
      "type": "string",
      "description": "Who it is attributed to (optional)."
    }
  }
}
check_attribution annotations
{
  "title": "Did they say it?",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
archive_stats — Archive size
Advertised by the server during the last successful anonymous check.
Advertised read-only

How many passages, organizations and speakers the archive holds, and how many passages are checked.

archive_stats input schema
{
  "type": "object",
  "properties": {}
}
archive_stats annotations
{
  "title": "Archive size",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

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
1407 ms
95th percentile latency
1407 ms

Maintenance history

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

  • · probe · passed · 1407 ms · metadata changed · 9 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 the-ai-record-mcp https://the-ai-record.com/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 the-ai-record-mcp --url https://the-ai-record.com/mcp

Cursor

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

Cline

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

VS Code

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

Let your agent find its tools

Find servers like The AI Record 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 1,293

Do you run The AI Record 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