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.
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.
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.
perf_verifyDetect 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_validateValidate 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_correctGeneral-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_chatRoute LLM requests to the optimal model automatically. Selects between GPT-4o, Claude, Gemini, and 20+ models based on task complexity. OpenAI-compatible format.
Add to your project's .mcp.json:
{
"mcpServers": {
"perf": {
"command": "npx",
"args": ["-y", "perf-mcp"],
"env": {
"PERF_API_KEY": "pk_live_xxx"
}
}
}
}
Settings → MCP → Add Server:
{
"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"
}
}
}
}
| Variable | Required | Description |
|---|---|---|
PERF_API_KEY | Yes | Your Perf API key (pk_live_xxx) |
PERF_BASE_URL | No | Override API URL (for testing) |
| 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.
MIT
PERF_API_KEY*secretYour Perf API key (get one at dashboard.withperf.pro)