{
  "markdown": "# perf-mcp\n\nFact-check and fix AI outputs. Catches hallucinations, repairs broken JSON, corrects errors — before they reach users.\n\nWorks with Claude Code, Cursor, Windsurf, Cline, and any MCP-compatible client.\n\n## Quick Start\n\nAdd to your MCP client config:\n\n```json\n{\n  \"mcpServers\": {\n    \"perf\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"perf-mcp\"],\n      \"env\": {\n        \"PERF_API_KEY\": \"pk_live_xxx\"\n      }\n    }\n  }\n}\n```\n\nGet your API key at [dashboard.withperf.pro](https://dashboard.withperf.pro) — 200 free verifications, no credit card.\n\n## Tools\n\n### `perf_verify`\n\nDetect and repair hallucinations in LLM-generated text. Uses multi-channel verification (web search, NLI models, cross-reference) — not just another LLM check.\n\n```\nperf_verify({ content: \"The Eiffel Tower was built in 1887.\" })\n→ Corrected: \"built in 1887\" → \"inaugurated in 1889\" (89% confidence)\n```\n\n### `perf_validate`\n\nValidate LLM-generated JSON against a schema and auto-repair violations. Fixes malformed enums, wrong types, missing fields, hallucinated properties.\n\n```\nperf_validate({\n  content: '{\"name\": \"John\", \"age\": \"twenty\"}',\n  target_schema: { type: \"object\", properties: { name: { type: \"string\" }, age: { type: \"number\" } } }\n})\n→ Rejected: /age must be number\n```\n\n### `perf_correct`\n\nGeneral-purpose output correction. Classifies the error type and applies the right fix — hallucination, schema violation, semantic inconsistency, or instruction drift.\n\n```\nperf_correct({ content: \"The Great Wall was built in 1950.\", correction_budget: \"fast\" })\n→ Corrected: temporal_error + factual_error detected (87% confidence)\n```\n\n### `perf_chat`\n\nRoute LLM requests to the optimal model automatically. Selects between GPT-4o, Claude, Gemini, and 20+ models based on task complexity. OpenAI-compatible format.\n\n## Setup by Client\n\n### Claude Code\n\nAdd to your project's `.mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"perf\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"perf-mcp\"],\n      \"env\": {\n        \"PERF_API_KEY\": \"pk_live_xxx\"\n      }\n    }\n  }\n}\n```\n\n### Cursor\n\nSettings → MCP → Add Server:\n\n```json\n{\n  \"mcpServers\": {\n    \"perf\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"perf-mcp\"],\n      \"env\": {\n        \"PERF_API_KEY\": \"pk_live_xxx\"\n      }\n    }\n  }\n}\n```\n\n### Windsurf\n\nAdd to `~/.codeium/windsurf/mcp_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"perf\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"perf-mcp\"],\n      \"env\": {\n        \"PERF_API_KEY\": \"pk_live_xxx\"\n      }\n    }\n  }\n}\n```\n\n## Environment Variables\n\n| Variable | Required | Description |\n|----------|----------|-------------|\n| `PERF_API_KEY` | Yes | Your Perf API key (`pk_live_xxx`) |\n| `PERF_BASE_URL` | No | Override API URL (for testing) |\n\n## Pricing\n\n| Plan | Credits | Price |\n|------|---------|-------|\n| Free | 200 verifications | $0 (never expires) |\n| Pro | 1,000/mo | $19/mo |\n| Pay-as-you-go | Unlimited | $0.02/verification |\n\n1 tool call = 1 credit. Get started at [dashboard.withperf.pro](https://dashboard.withperf.pro).\n\n## License\n\nMIT\n",
  "bytes": 3055,
  "sha": "42b0da14f6fc30b2898d3c6e8bea554a48e4f6ee1511879f534df5820ab7b52c",
  "repo_slug": "perf-technology/perf-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_perf_ai_perf_mcp_df8f443d/readme"
}