Lenz Fact-Check

Checks the factual claims in a draft or an answer against independent sources: a quick verdict, or a deep check with sources.

View on lenz.ioTry this MCPSponsored

Hosted MCP Server

npx add-mcp 'https://lenz.io/mcp'

Installs into Claude Code, Codex, Cursor and more

Documentation

Connect Lenz to your coding tool.

Lenz is a remote Model Context Protocol server. Add it to Claude Code, Codex, Cursor, or any MCP client, and your assistant can fact-check a claim right inside the session: a quick verdict first, and a sourced verdict with citations from the deep check.

Tool	Time	What it does
assess_claim	~15 s	A quick verdict and a confidence for every claim in a text or a list, from a panel of reviewers. One credit per claim, no sources shown.
verify_claim	~90 s	Investigates one claim through the full pipeline (research, debate, panel review): verdict, score, key finding, warnings and the main sources, in about a minute or two. `depth: low` researches fewer sources for half the credits.
get_verification	—	Waits for a running `verify_claim` by task id, or fetches a completed result by verification id.
ask_followup	—	A grounded follow-up question about a completed `verify_claim`, answered from its full evidence.
select_claims	—	Chooses which claim(s) to run when a text contains several.
check_usage	—	Remaining credits, the per-tool price list, and your plan.
list_verifications	—	Your recent deep checks, newest first. Use it to get back a result that finished after the chat moved on.

These are tools, not slash commands. In a client like Claude Code, just ask in plain language (“check the facts on our pricing page with Lenz”) and the assistant calls the right tool.

Prefer to call it in code instead? The same primitives are a REST API and typed Python / TypeScript SDKs. See the developer docs

Server Hosted at lenz.io/mcp
Coding tools One command; sign in or use your key
Claude and ChatGPT Sign in, no key
Tools Seven, same ladder as the API

Ask in plain language, the client picks the tool.

Coding tools: a Bearer header with your keyClaude and ChatGPT: sign in, no key

Coding toolsNothing to install. It’s hosted at lenz.io/mcp over Streamable HTTP, and it authenticates with the same lenz_… API key as the REST API, so there’s no separate signup. Claude Code and Cursor can sign in with your Lenz account instead, with no key.

Claude and ChatGPTUsing Claude Desktop, claude.ai or ChatGPT rather than a coding tool? Connect Lenz to Claude or ChatGPT The same server, as click-paths, with no config to edit. Claude connects in one click with no key.

One command, or one block of config.

Get a free API key

No credit card required.

Get a key

Set LENZ_API_KEY

In your environment first, or have the config written for your client with the key already in it.

Generate setup instructions

Point your client at the server

Use https://lenz.io/mcp with a Bearer header, as below.

In Claude Code or Cursor you can skip the key: install below, then sign in with your Lenz account the first time Lenz is used.

# the Lenz plugin: the server plus the fact-check skill; sign in on first use
$ claude plugin marketplace add lenzhq/lenz-mcp
$ claude plugin install lenz@lenz

# or the server alone, for every project; sign in with /mcp
$ claude mcp add --scope user --transport http lenz https://lenz.io/mcp

# with an API key instead, add: --header "Authorization: Bearer ${LENZ_API_KEY}"

Full setup notes, per-client quirks, and examples live in the lenz-mcp repo ↗. Lenz is also listed in the Claude connectors directory ↗

Try free, no card.

Free

100 assessments or 10 full verifications a month, in any combination.

Plus

$7.99 / month

500 assessments or 50 full verifications a month, in any combination.

Or $6.59 a month, billed $79 a year

Pro · warranty included

$99 / month

5,000 assessments or 500 full verifications a month, in any combination. The warranty on qualifying verdicts.

Or $83 a month, billed $990 a year

Scale · warranty included

$399 / month

20,000 assessments or 2,000 full verifications a month, for production volumes. The warranty on qualifying verdicts.

Or $333 a month, billed $3,990 a year

Every plan includes 1,000 extractions a day, an extraction being one call however long the text.

Compare plans

What is the Lenz MCP server?

A remote Model Context Protocol server hosted at lenz.io/mcp. It exposes Lenz's fact-checking pipeline as MCP tools, so an AI client like Claude Code, Codex, or Cursor can verify a claim against independent sources and get a quick verdict, and a sourced one from the deep check — without leaving the session. Claude Desktop, claude.ai and ChatGPT reach the same server through their own connector screens: connect Lenz to Claude or ChatGPT.

Do I need to install anything?

No. The server is remote, over Streamable HTTP. Point your MCP client at https://lenz.io/mcp with an Authorization: Bearer header carrying your API key. Get a free key at /api-credentials.

What tools does it expose?

Seven: assess_claim (a quick 3-model verdict with a confidence, no sources shown), verify_claim (the full multi-model pipeline for one claim, with its main sources), get_verification (wait for a running verification, or fetch a completed one by id), ask_followup (grounded follow-up on a completed verification), select_claims (choose which claim to run when a text contains several), check_usage (remaining credits and plan), and list_verifications (your recent deep checks, newest first, to get back a result that finished after the chat moved on).

Is it the same key as the API?

Yes. The MCP server is a thin proxy over the same public API at lenz.io/api/v1, authenticated with the same lenz_… Bearer key from /api-credentials. No separate signup.