Lenz MCP Server

Lenz is a fact-checking platform. It takes a factual claim, runs it through a multi-model pipeline (framing → research → debate → panel review → conclusion) against independent sources, and returns a verdict with a confidence level. This is the official remote MCP server — a hosted Model Context Protocol endpoint that exposes Lenz's fact-checking as tools your AI assistant can call.

It verifies claims against the open web, independent of whatever context your model was given — so it complements retrieval/groundedness checkers rather than replacing them.

• Hosted, no install: point your client at https://lenz.io/mcp. Nothing to run locally.

• Auth: OAuth (no key — for clients that support it) or a free Lenz API key (Authorization: Bearer lenz_…).

• Transport: Streamable HTTP.

Tools

Verdicts are directional, not absolute — confidence is returned as bucketed language with a caveat, not a raw score. Surface it, and the link back to Lenz, to the user.

Related MCP server: Grounding Enforcer

Quickstart

Two ways to connect, depending on your client:

• OAuth — for clients that support it (e.g. Claude Desktop connectors). No key to paste; you sign in to Lenz and authorize the connection.

• API key — works with any MCP client via an Authorization header.

Connect with OAuth (no API key)

If your client supports OAuth for MCP (such as Claude Desktop's custom connectors), add the server with just its URL and no headers:

{
  "mcpServers": {
    "lenz": {
      "type": "http",
      "url": "https://lenz.io/mcp"
    }
  }
}

The first time you use it, your client walks you through a one-time sign-in: you authenticate on Lenz's own screen and authorize the connection — no key is stored in your config. Your assistant then fact-checks on your behalf against your Lenz account's quota. You can revoke the connection at any time; see the privacy policy.

Connect with an API key

1. Get a free API key at lenz.io/api-integration (format lenz_…).

2. Add the server to your client (examples below). Authenticate with Authorization: Bearer <your-key>.

Claude Code

claude mcp add --transport http lenz https://lenz.io/mcp \
  --header "Authorization: Bearer ${LENZ_API_KEY}"

Claude Desktop / any client that reads .mcp.json

{
  "mcpServers": {
    "lenz": {
      "type": "http",
      "url": "https://lenz.io/mcp",
      "headers": {
        "Authorization": "Bearer ${LENZ_API_KEY}"
      }
    }
  }
}

Cursor

One click: use the Add Lenz to Cursor button above — it adds the server and signs you in via OAuth (no key to paste).

Manual: Settings → MCP → Add new MCP server → type HTTP, URL https://lenz.io/mcp, and add a header Authorization: Bearer <your-key>. (Or drop the JSON above into .cursor/mcp.json.)

VS Code

One click: use the Install in VS Code button above (OAuth, no key). Manual, with a key:

code --add-mcp '{"name":"lenz","type":"http","url":"https://lenz.io/mcp","headers":{"Authorization":"Bearer ${LENZ_API_KEY}"}}'

MCP Inspector (try the tools by hand)

npx @modelcontextprotocol/inspector
# Transport: Streamable HTTP · URL: https://lenz.io/mcp
# Header: Authorization: Bearer <your-key>

Example

You: Is it true that honey never spoils?

The assistant calls assess_claim("Honey never spoils") and gets back: Mostly True — high confidence. Properly sealed honey can keep effectively indefinitely thanks to its low moisture and acidity; the caveat is contamination or added water. For a sourced deep-dive it can escalate with verify_claim.

Quota

Free keys include a monthly allotment of fast assess_claim checks and a smaller number of deep verify_claim checks. Call check_usage to see what's left, or see plans at lenz.io. verify_claim is the expensive path — reserve it for claims that warrant a sourced investigation.

Skills

Prefer a guided workflow to calling the tools yourself? The lenz-fact-check skill turns "is this true?" into a structured pass — it extracts the checkable claims, runs assess_claim on each, escalates high-stakes ones to a deep verify_claim, and reports verdicts with confidence and sources (with the directional-not-absolute caveat built in). Point your agent at skills/lenz-fact-check/SKILL.md.

Links

• Website: lenz.io

• Get a key: lenz.io/api-integration

• Developer docs: lenz.io/developers

• SDKs: Python · Node

Support

Questions or issues? Open an issue or get in touch.

License

Apache-2.0 © lenzhq. The Lenz name and logos (assets/) are trademarks of lenzhq and are not granted by the license — see NOTICE.