Perf Mcp

io.github.Perf-AIPublished by GitHub account Perf-AIv0.1.1Updated Nov 10, 2026

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

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

Fact-checks and repairs AI-generated output: detects hallucinations, validates and fixes JSON against a schema, and routes chat requests to a chosen model.

What you can do
  • Verify LLM-generated text and get corrected claims with confidence scores
  • Validate generated JSON against a schema and auto-repair type, enum and missing-field errors
  • Correct general output by classifying the error type (hallucination, schema violation, inconsistency, instruction drift)
  • Route chat requests to one of 20+ models in an OpenAI-compatible format
When to use it
Useful when assistant output is shown to users or fed into downstream systems and you want a second check for factual errors or malformed JSON before it lands. Also relevant if you want one endpoint that picks a model per request.
Requirements
Runs locally via npx, so Node.js is needed. Requires a Perf API key in the PERF_API_KEY environment variable; an optional PERF_BASE_URL overrides the API endpoint. Network access to the Perf service is required.
Before you install
Content you submit is sent to the Perf service for verification, so avoid sending secrets or regulated data. Usage is metered: one tool call equals one credit, with a free allowance of 200 verifications and paid plans or per-verification charges beyond it. Keep the API key out of shared config files.

Installation

In SourceWeft

  1. Open Perf Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

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:

json
{  "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.

perf_validate({  content: '{"name": "John", "age": "twenty"}',  target_schema: { type: "object", properties: { name: { type: "string" }, age: { type: "number" } } }})→ Rejected: /age must be number

perf_correct

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

perf_correct({ content: "The Great Wall was built in 1950.", correction_budget: "fast" })→ Corrected: temporal_error + factual_error detected (87% confidence)

perf_chat

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

Setup by Client

Claude Code

Add to your project's .mcp.json:

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

Cursor

Settings → MCP → Add Server:

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

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

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

Environment Variables

VariableRequiredDescription
PERF_API_KEYYesYour Perf API key (pk_live_xxx)
PERF_BASE_URLNoOverride API URL (for testing)

Pricing

PlanCreditsPrice
Free200 verifications$0 (never expires)
Pro1,000/mo$19/mo
Pay-as-you-goUnlimited$0.02/verification

1 tool call = 1 credit. Get started at dashboard.withperf.pro.

License

MIT

Source: README.md at commit e0e678a

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts