About Perf MCP
Perf MCP is an MCP server for checking and correcting AI outputs, aimed at developers who need to verify facts and JSON structure. It offers fact-checking, schema-based validation and repair, general correction, and model routing tools.
Key features
- 01Detect and repair factual errors
- 02Validate and repair JSON against schemas
- 03Classify and correct several output errors
- 04Route models by task complexity
Use cases
- 01Check facts before delivering AI-generated content
- 02Repair JSON that does not match a schema
- 03Correct semantic inconsistencies or instruction drift
- 04Select an LLM based on task complexity
MCP support
It exposes perf_verify, perf_validate, perf_correct, and perf_chat tools to MCP clients for checking or correcting outputs and routing LLM requests.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y perf-mcpPERF_API_KEYSecretYour Perf API key (get one at dashboard.withperf.pro)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
4Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | No | Force a specific model (e.g., 'gpt-4o', 'claude-sonnet'). Omit for automatic selection. |
| messages | array | Yes | Chat messages in OpenAI format. |
| max_tokens | integer | No | Maximum tokens in the response. |
| temperature | number | No | Sampling temperature (0-2). |
| response_format | object | No | Set to {"type": "json_object"} for JSON mode. |
| response_format.type | string | Yes |
Details
From the project READMEperf-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.
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:
{
"mcpServers": {
"perf": {
"command": "npx",
"args": ["-y", "perf-mcp"],
"env": {
"PERF_API_KEY": "pk_live_xxx"
}
}
}
}
Cursor
Settings → MCP → Add Server:
{
"mcpServers": {
"perf": {
"command": "npx",
"args": ["-y", "perf-mcp"],
"env": {
"PERF_API_KEY": "pk_live_xxx"
}
}
}
}
Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"perf": {
"command": "npx",
"args": ["-y", "perf-mcp"],
"env": {
"PERF_API_KEY": "pk_live_xxx"
}
}
}
}
Environment Variables
| Variable | Required | Description |
|---|---|---|
PERF_API_KEY | Yes | Your Perf API key (pk_live_xxx) |
PERF_BASE_URL | No | Override API URL (for testing) |
Pricing
| Plan | Credits | Price |
|---|---|---|
| Free | 200 verifications | $0 (never expires) |
| Pro | 1,000/mo | $19/mo |
| Pay-as-you-go | Unlimited | $0.02/verification |
1 tool call = 1 credit. Get started at dashboard.withperf.pro.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.