Perf Mcp

perf-technology/perf-mcp

Adds four tools to catch and fix AI mistakes before they hit production. perf_verify detects factual hallucinations using multi-channel verification beyond simple LLM checks, perf_validate enforces JSON schemas with auto-repair for type errors and malformed enums, perf_correct handles general output issues by classifying error types, and perf_chat routes requests to the optimal model from GPT-4o, Claude, Gemini, and 20+ others. Requires a Perf API key with 200 free verifications to start. Useful when you're building agents or workflows where AI outputs feed into structured systems and bad data causes downstream failures.

tools: 4
auth: Secret needed
transport: STDIO
env var: 1
last updated: Feb 19, 2026

View on GitHub

Tools

4 tools

Public tool metadata for what this MCP can expose to an agent.

perf_verifyDetect and repair hallucinations in LLM-generated text. Uses multi-channel verification (web search, NLI models, cross-reference) — not just another LLM check.

Detect and repair hallucinations in LLM-generated text. Uses multi-channel verification (web search, NLI models, cross-reference) — not just another LLM check.

No parameter schema in public metadata yet.

perf_validateValidate LLM-generated JSON against a schema and auto-repair violations. Fixes malformed enums, wrong types, missing fields, hallucinated properties.

Validate LLM-generated JSON against a schema and auto-repair violations. Fixes malformed enums, wrong types, missing fields, hallucinated properties.

No parameter schema in public metadata yet.

perf_correctGeneral-purpose output correction. Classifies the error type and applies the right fix — hallucination, schema violation, semantic inconsistency, or instruction drift.

General-purpose output correction. Classifies the error type and applies the right fix — hallucination, schema violation, semantic inconsistency, or instruction drift.

No parameter schema in public metadata yet.

perf_chatRoute LLM requests to the optimal model automatically. Selects between GPT-4o, Claude, Gemini, and 20+ models based on task complexity. OpenAI-compatible format.

Route LLM requests to the optimal model automatically. Selects between GPT-4o, Claude, Gemini, and 20+ models based on task complexity. OpenAI-compatible format.

No parameter schema in public metadata yet.

Configuration

PERF_API_KEY*secret

Your Perf API key (get one at dashboard.withperf.pro)

Readme

perf-mcp

Fact-check and fix AI outputs. Catches hallucinations, repairs broken JSON, corrects errors — before they reach users.

Works with Claude Code, Cursor, Windsurf, Cline, and any MCP-compatible client.

Quick Start

Add to your MCP client config:

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

Get your API key at dashboard.withperf.pro — 200 free verifications, no credit card.

Tools

`perf_verify`

Detect and repair hallucinations in LLM-generated text. Uses multi-channel verification (web search, NLI models, cross-reference) — not just another LLM check.

perf_verify({ content: "The Eiffel Tower was built in 1887." })
→ Corrected: "built in 1887" → "inaugurated in 1889" (89% confidence)

`perf_validate`

Validate LLM-generated JSON against a schema and auto-repair violations. Fixes malformed enums, wrong types, missing fields, hallucinated properties.

View the full README on GitHub

Details

Repository: github.com/perf-technology/perf-mcp
Package: perf-mcp
Transport: STDIO
Auth: Required
Registry: MCP registry, active