INDIVIDUAL MCP TOOL

get_evidence

Every piece of evidence recorded for a claim: which document, which source, and the excerpt where we may redistribute it.

feedatom.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://mcp.feedatom.com//mcp

No auth detected

Connect to this endpoint to inspect the live schema for get_evidence and invoke it with your own arguments.

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.feedatom]
url = "https://mcp.feedatom.com//mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "feedatom": {
      "type": "http",
      "url": "https://mcp.feedatom.com//mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: feedatom
Remote MCP URL: https://mcp.feedatom.com//mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "feedatom": {
      "url": "https://mcp.feedatom.com//mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "feedatom": {
      "type": "http",
      "url": "https://mcp.feedatom.com//mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "feedatom",
  "transport": "streamable-http",
  "url": "https://mcp.feedatom.com//mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

list_stories — Stories ranked by what the ledger learned, each one gathering the articles that report it.
get_story — A single story: what happened, which sources reported it, and what the ledger recorded from them.
search_stories — Full-text search over stories.
list_topics — Every topic with coverage, for narrowing list_stories or search_stories.
search_claims — Answers with CLAIMS - what is asserted about a subject, by how many sources, and when it was true - rather than with links.
find_entity — Resolves a name to the entities the ledger knows, with their type and namespace.
get_dossier — The whole file on one entity: what is asserted about it by kind, how much of that is contradicted, who it appears beside, and its most recent claims with both time axes.
what_changed — The history of one subject's claims on both time axes: what was true when, and when we learned it.