Perf MCP Server

by perf-ai Your server? Claim it

local only

Perf MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 30 installs a week from npm. Last commit 19 Feb 2026.

Fact-check and fix AI outputs. Hallucination detection, schema validation, auto-repair.

Installs per day peak 26 · avg 7 · +12% w/w

a month agotoday

Installs / week

npm · perf-mcp

Stars

0 open issues

19 Feb 2026

Last commit

0 releases in 90 days

MIT

License

TypeScript

Nothing serious here today

Today is the operative word: we check Perf MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add perf-mcp -- npx -y perf-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "perf-mcp": {
      "args": [
        "-y",
        "perf-mcp"
      ],
      "command": "npx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.perf-mcp]
command = "npx"
args = ["-y", "perf-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "perf-mcp": {
      "args": [
        "-y",
        "perf-mcp"
      ],
      "command": "npx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "perf-mcp": {
      "args": [
        "-y",
        "perf-mcp"
      ],
      "command": "npx"
    }
  }
}

This one needs environment variables set before it will start: PERF_API_KEY (Your Perf API key (get one at dashboard.withperf.pro)). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Perf MCP

same job, measured the same way

VeriGhost-Clarity

by evozim

Hallucination validator and factual grounding checker for LLM outputs.

answering

Arkheiaai

by arkheiaai

Detect fabrication and hallucination in any LLM output. 30+ models supported.

46 installs/wk local only

x402 JSON Repair

by ktcod

Pay-per-call JSON repair + JSON Schema validation for AI agents (USDC on Base, x402).

21 tools answering

Understand Quickly

by looptech-ai

Public registry of code-knowledge graphs for AI agents with schema validation and drift detection.

32 installs/wk local only

HallucC — Hallucination & Safety Guardian

by fredyee

Hallucination & safety checks for LLM/Agent outputs: claim-level fact-check with citations.

answering

Qc Validator

by mdfifty50-boop

Output quality control and validation for AI agents

36 installs/wk local only

retriEVAL

by hcarrillo001

LLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.

local only

Doc Extract MCP

by koraynar

Document tooling for AI agents: PDF/text reading, chunking, schema-validated JSON output.

local only

Perf MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Perf MCP?

Perf MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package perf-mcp was installed 30 times last week.

How do I connect Perf MCP?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls perf-mcp straight from npm; nothing to host, nothing to sign up for.

How many people use Perf MCP?

The npm package perf-mcp was installed 30 times in the last week. Week over week that is +12%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Perf MCP open source?

Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.