Skip to content

Connect Lenz to your coding tool.

Lenz is a remote Model Context Protocol server. Add it to Claude Code, Cursor, VS Code, Codex, 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.

Seven tools, same depth ladder as the API
ToolTimeWhat it does
assess_claim~15 sA 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 sInvestigates 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

  • ServerHosted at lenz.io/mcp
  • Coding toolsOne command or one click
  • Sign-inYour Lenz account, or an API key
  • ToolsSeven, same ladder as the API

01How it connects

Ask in plain language, the client picks the tool.

Coding toolsNothing runs on your machine: Lenz is hosted at lenz.io/mcp over Streamable HTTP. Add it with one command or one click, then sign in with your Lenz account. There’s no key to paste. For CI, a headless agent or a shared config, the same lenz_… API key as the REST API works as a Bearer header.
Claude and ChatGPTUsing Claude Desktop, claude.ai or ChatGPT rather than a coding tool? Connect Lenz to Claude or ChatGPT

02Add the server

One command or one click, then sign in.

Add the server

One step for your client, below.

Get the steps for your tool

Sign in with your Lenz account

Your client shows the sign-in once Lenz is added; each tab says where. No account yet? Signing in creates one, with free credits.

Check it works

Ask: “Check with Lenz whether indeed 90% of startups fail within their first year.”

# the Lenz plugin: the server plus the fact-check skill; then sign in from /mcp
$ 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, export LENZ_API_KEY=lenz_… and add:
# --header "Authorization: Bearer ${LENZ_API_KEY}"

Full setup notes, per-client quirks, and examples live in the lenz-mcp repo ↗.

03Pricing

Try free, no card.

Free

$0

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

Try free
Plus

$7.99/ month

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

Or $6.59 a month, billed $79 a year

Choose Plus
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

Choose Pro
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

Choose Scale

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

Compare plans

04Questions

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.

Nothing runs on your machine: the server is hosted at https://lenz.io/mcp over Streamable HTTP. Add it to your client with one command or one click (in Claude Code, a plugin), then sign in with your Lenz account.

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).

No. Claude Code, Cursor, VS Code and Codex sign in with your Lenz account. For CI, a headless agent or a shared config, use the same lenz_… key as the REST API, from /api-credentials, as an Authorization: Bearer header. Either way it is one account and one credit pool.

Put fact-checking in your assistant.

Self-serve from day one · free tier, no card