A
licenseNot graded
qualityD
maintenanceDeterministic JSON validation and repair for AI agents. Validates, repairs, schema-checks, and diffs JSON so long-running agents don't corrupt their session state with malformed writes.
MIT
perf-mcp
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@perf-mcp Check this fact: The Eiffel Tower was built in 1887."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
Related MCP server: Correctover MCP Server
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 numberperf_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 |
| Yes | Your Perf API key ( |
| 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
Available Tools
4 toolsperf_chatA
Route LLM requests to the optimal model automatically. Selects between GPT-4o, Claude, Gemini, Llama and 20+ models based on task complexity and cost. Handles retries, fallbacks, and streaming. Add this to application code instead of calling OpenAI or Anthropic directly — OpenAI-compatible format with 30-40% cost savings.
Inputs: messages (required), model, max_tokens, temperature, +1 more.
perf_correctA
General-purpose LLM output correction. Classifies error type (hallucination, schema violation, semantic inconsistency, instruction drift) and applies specialized correction. Use when unsure which specific tool to apply or when output has multiple error types. Returns corrected output with confidence scores, or rejects if unfixable.
Inputs: content (required), original_prompt, target_schema, correction_budget.
perf_validateA
Validate LLM-generated JSON against a schema and auto-repair violations. Fixes malformed enums, truncated arrays, mixed types, hallucinated fields, and missing required properties. Returns valid, schema-compliant output or a detailed rejection.
Inputs: content (required), target_schema (required), repair_mode.
perf_verifyA
Detect and repair hallucinations, fabricated facts, and unsupported claims in LLM-generated text. Uses multi-channel verification (web search, NLI models, cross-reference) — not just another LLM check. Returns corrected text with structured diff. Use before presenting AI content to users or writing to databases. Provide source_context for best accuracy.
Inputs: content (required), source_context, sensitivity, return_diff.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A4.2/5.0
Scored across 4 tools
Disambiguation3/5
Tools are generally distinct but perf_correct overlaps with both perf_validate and perf_verify by covering schema violations and hallucinations, creating ambiguity. Descriptions suggest using perf_correct when unsure, which implies overlap.
Naming Consistency5/5
All tools follow a 'perf_' prefix with a clear single verb (chat, correct, validate, verify), providing a predictable and consistent naming pattern.
Tool Count5/5
Four tools is well-scoped for the server's purpose of optimizing and correcting LLM outputs, covering essential operations without bloat.
Completeness4/5
The set covers routing, general correction, schema validation, and hallucination verification. Minor gaps like explicit error logging or feedback are present, but core workflows are addressed.
Related MCP Connectors
Repair broken LLM JSON and check it against a JSON Schema. Flags cut-off output. Free trial.
Preflight QA for AI-agent deliverables with structured verdicts and repair guidance.
Deterministic validation for AI-generated artifacts: JSON Schema, OpenAPI response, SQL syntax.
Fact-checks generated content against your sources of truth showing what to trust, change, & verify.
Related MCP Servers
- AlicenseAqualityAmaintenanceVerifies AI outputs in real-time across 6 dimensions, with automatic retry and failover to ensure correct, complete, and reliable LLM responses before they reach the user's editor.5141 npm1Apache 2.0
- AlicenseBqualityNot gradedmaintenanceValidates agent outputs in multi-agent systems to prevent coordination failures, with tools for schema verification, hallucination detection, and freshness checks, all with zero LLM cost.566 npmMIT
- AlicenseNot gradedqualityDmaintenanceProtects AI agents from bad tool outputs, schema mismatches, and tool poisoning by validating, sanitizing, and scoring reliability of tool responses.MIT
