Perf MCP
About
Fact-check and fix AI outputs. MCP server for hallucination detection, schema validation, and output correction.
Details
- Author
- Perf-Technology
- Downloads
- 166
- Categories
- Developer Tools, AI, Other, Knowledge Base, Search
Jump to
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Perf MCPCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Add Perf MCP to your MCP client config by running npx -y perf-mcp with the environment variable PERF_API_KEY. Then invoke its tools — `per
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"perf mcp": {
"perf-mcp": {
"command": "npx",
"args": [
"-y",
"perf-mcp"
],
"env": {
"PERF_API_KEY": "<YOUR_API_KEY>"
}
}
}
}
}McpServers
{
"perf-mcp": {
"command": "npx",
"args": [
"-y",
"perf-mcp"
],
"env": {
"PERF_API_KEY": "<YOUR_API_KEY>"
}
}
}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.
{ "mcpServers": { "perf": { "command": "npx", "args": ["-y", "perf-mcp"], "env": { "PERF_API_KEY": "pk_live_xxx" } } } }
Get your API key atdashboard.withperf.pro— 200 free verifications, no credit card.
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)
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
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)
Route LLM requests to the optimal model automatically. Selects between GPT-4o, Claude, Gemini, and 20+ models based on task complexity. OpenAI-compatible format.
{ "mcpServers": { "perf": { "command": "npx", "args": ["-y", "perf-mcp"], "env": { "PERF_API_KEY": "pk_live_xxx" } } } }
{ "mcpServers": { "perf": { "command": "npx", "args": ["-y", "perf-mcp"], "env": { "PERF_API_KEY": "pk_live_xxx" } } } }
Add to~/.codeium/windsurf/mcp_config.json:
{ "mcpServers": { "perf": { "command": "npx", "args": ["-y", "perf-mcp"], "env": { "PERF_API_KEY": "pk_live_xxx" } } } }
1 tool call = 1 credit. Get started atdashboard.withperf.pro.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
MCP servers for Deephaven to orchestrate data workers and power documentation Q&A with LLMs, enabling AI-driven data workflows.
Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server
MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent
MCP server that gives AI assistants on-demand access to 1,500+ amCharts docs, ~300 code examples, and 1000+ class API references.
Predict anything with Chronulus AI forecasting and prediction agents.
Equip AI agents with evaluation and self-improvement capabilities with Root Signals.
Interaction profile registry for AI agents — log interactions, build a behavioral profile, query it through behavioral lenses. 21 tools, zero-config.
An AI-powered system that converts Acceptance Criteria (AC) from QA specifications into automated browser testing workflows.
Adversarial AI quality review for LLM pipelines. Dual-reviewer consensus with anti-gaming protection. BYOK — works with Claude Code, Claude Desktop, and any MCP client.
A high-performance MCP server providing structured, real-time price data for AI hardware across global marketplaces, built with a focus on agent-native discovery over hardcoded endpoints.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
