Freshrss MCP Server

freshrss-mcp

A Model Context Protocol server for FreshRSS, the self-hosted RSS and Atom feed aggregator.

It speaks the Google Reader compatible API that FreshRSS exposes at /api/greader.php, and it hides that API's quirks behind tool arguments an assistant can actually use: numeric feed ids, category and label names, ISO dates and decimal article ids instead of user/-/state/com.google/… stream identifiers and hexadecimal item tags.

📖 Full documentation: freshrss-mcp.ni-c.de

Requirements

• Node.js 22 or newer
• A FreshRSS instance (developed against 1.29) with
  • the API enabled: Settings → Authentication → "Allow API access"
  • an API password set for the user: Settings → Profile → API management. This is a separate password from the web login.

Configuration

The server starts without credentials so its tools stay listable; every call then fails with these setup instructions.

Claude Code

claude mcp add freshrss -- npx -y @ni-c/freshrss-mcp

Claude Desktop

{
  "mcpServers": {
    "freshrss": {
      "command": "npx",
      "args": ["-y", "@ni-c/freshrss-mcp"],
      "env": {
        "FRESHRSS_URL": "https://rss.example.com",
        "FRESHRSS_USER": "alice",
        "FRESHRSS_API_PASSWORD": "…"
      }
    }
  }
}

Codex

[mcp_servers.freshrss]
command = "npx"
args = ["-y", "@ni-c/freshrss-mcp"]
env = { FRESHRSS_URL = "https://rss.example.com", FRESHRSS_USER = "alice", FRESHRSS_API_PASSWORD = "…" }

Tools

Reading

Writing

Not registered when FRESHRSS_READ_ONLY=true.

No search

FreshRSS does not offer full-text search over its API — the Google Reader endpoints filter by stream, read state and date only. list_articles therefore has no query parameter; narrow the result with feed_id/category and since/until and filter the returned articles yourself.

Safety

• Article text is untrusted input. Everything this server returns from FreshRSS was written by a third party on the internet, so responses that carry article text, titles or feed names are explicitly marked as data, never as instructions.
• Destructive tools are two-step. They return a single-use confirmation token bound to the exact target; the second call has to carry it. A plain boolean could be set on the very first call, or be talked into it by text hidden in a feed. The confirmation messages deliberately never quote titles or names coming from the API.
• Response budgets. FreshRSS returns up to 500 000 characters of HTML per article. Article text is converted to plain text, capped per article and against a per-response budget, and is opt-in in listings.
• Credentials are read once, removed from process.env afterwards and never written to disk. Requests never follow redirects, which would resend the authorization header to another host, and relaxed TLS validation is scoped to this connection instead of the whole process.
• Feed URLs are redacted. FreshRSS stores HTTP-auth feeds as https://user:password@host/feed. The userinfo part is stripped before a feed URL reaches a tool result or the OPML export, so list_feeds cannot print the password of a paid or private feed into the transcript.
• subscribe_feed refuses internal targets. FreshRSS fetches the URL server-side, which makes the tool an SSRF primitive reachable from text inside an article. Loopback and link-local addresses — including cloud metadata endpoints — are rejected. Private LAN addresses stay allowed, because self-hosted setups legitimately subscribe to feeds on their own network.
• import_opml refuses a <!DOCTYPE>. No XML is parsed in this process, but the document is handed to FreshRSS, where a document type declaration is the carrier for entity-expansion and external-entity attacks. OPML never needs one.
• FRESHRSS_READ_ONLY=true does not register the write tools at all rather than refusing them at call time.

Which tools are gated by a confirmation token: mark_all_as_read, unsubscribe_feed, delete_category_or_label and import_opml. mark_articles is deliberately not gated — the caller names each of at most 100 articles explicitly and every field can be set back — but it is declared destructive, so a client may still prompt for it.

Container

docker run --rm -i \
  -e FRESHRSS_URL=https://rss.example.com \
  -e FRESHRSS_USER=alice \
  -e FRESHRSS_API_PASSWORD=... \
  ghcr.io/ni-c/freshrss-mcp:latest

The image is published for linux/amd64 and linux/arm64 with an SBOM and build provenance. It runs as the unprivileged node user and carries no npm, so the only thing in it is Node, the runtime dependencies and dist/.

Development

npm install
npm run lint && npm run build && npm test
npm run test:coverage

See CONTRIBUTING.md for a throwaway FreshRSS to develop against. The full documentation lives at freshrss-mcp.ni-c.de.

Releasing

1. Move the [Unreleased] entries in CHANGELOG.md under the new version and bump version in package.json.
2. npm run lint && npm run build && npm run test:coverage.
3. Commit, then tag: git tag -s vX.Y.Z -m vX.Y.Z && git push origin main vX.Y.Z.

The tag triggers release.yml, which verifies the tag matches package.json, publishes to npm via Trusted Publishing with provenance (no token involved), creates the GitHub release from the CHANGELOG section, and publishes the entry to the MCP Registry. If only the registry step fails, fix it on main and re-run mcp-registry.yml by hand — never re-run the tagged job, which would check out the old tree.

License

MIT