{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_vfnc8km52vcr","handle":"mcp-scoring-engine","url":"https://wellknown.network/agents/mcp-scoring-engine","links":{"self":"https://wellknown.network/agents/mcp-scoring-engine/record.json","html":"https://wellknown.network/agents/mcp-scoring-engine","markdown":"https://wellknown.network/agents/mcp-scoring-engine/record.md","api":"https://wellknown.network/api/v1/agents/mcp-scoring-engine","status":"https://wellknown.network/api/v1/agents/mcp-scoring-engine/status","claim":"https://wellknown.network/agents/mcp-scoring-engine/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-scoring-engine/claim.json","badge":"https://wellknown.network/agents/mcp-scoring-engine/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-scoring-engine/history","tools":"https://wellknown.network/api/v1/agents/mcp-scoring-engine/tools"},"ard":{"identifier":"urn:air::server:mcp-scoring-engine","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-scoring-engine","summary":"Scoring engine for MCP server quality assessment","description":"# mcp-scoring-engine\n\nA standalone scoring engine for evaluating the quality of [Model Context Protocol (MCP)](https://modelcontextprotocol.io) servers. Pure Python, no framework dependencies — just dataclasses, scoring logic, and network probes.\n\nUsed in production by [MCP Scoreboard](https://mcpscoreboard.com) to grade thousands of MCP servers.\n\n## Installation\n\n```bash\npip install mcp-scoring-engine\n```\n\n## Quick Start\n\n### Score a server from its GitHub repo (static analysis)\n\n```python\nfrom mcp_scoring_engine import ServerInfo, analyze_repo, compute_score\n\nserver = ServerInfo(\n    name=\"my-mcp-server\",\n    description=\"A tool server for doing useful things\",\n    repo_url=\"https://github.com/owner/my-mcp-server\",\n)\n\nstatic = analyze_repo(server.repo_url)\nresult = compute_score(server, static_result=static)\n\nprint(result.composite_score)  # 0–100\nprint(result.grade)            # \"A+\", \"B\", \"D\", etc.\nprint(result.score_type)       # \"partial\" (1 tier) or \"full\" (2+ tiers)\n```\n\n### Probe a running server\n\n```python\nfrom mcp_scoring_engine import (\n    ServerInfo, probe_server, deep_probe_server, compute_score\n)\n\n# Fast health check (~10s) — connection, initialize, ping\nfast = probe_server(\"https://my-server.example.com/mcp\")\nprint(fast.is_reachable, fast.connection_ms)\n\n# Deep protocol probe (~30s) — schema validation, error handling, fuzz testing\ndeep = deep_probe_server(\"https://my-server.example.com/mcp\")\nprint(deep.tools_count, deep.schema_valid, deep.fuzz_score)\n\n# Score with the probe results\nserver = ServerInfo(name=\"my-server\", description=\"...\", repo_url=\"...\")\nstatic = analyze_repo(server.repo_url)\nresult = compute_score(server, static_result=static, deep_probe=deep)\nprint(result.grade)\n```\n\n### Probe a stdio server\n\n```python\nfrom mcp_scoring_engine import probe_server_stdio, deep_probe_server_stdio\n\nfast = probe_server_stdio([\"npx\", \"-y\", \"@modelcontextprotocol/server-memory\"])\ndeep = deep_probe_server_stdio([\"python\", \"-m\", \"my_mcp_server\"])\n```\n\n### …","publisher":null,"homepage":"https://mcpscoreboard.com","repository":"https://github.com/Brightwing-Systems-LLC/mcp-scoring-engine","version":"0.9.0","license":null,"protocols":["mcp"],"tags":["ai","mcp","model-context-protocol","quality","scoring"],"pricing":null,"endpoints":[{"url":"pypi:mcp-scoring-engine","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":1,"provenance":"declared"}],"categories":["ai"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-scoring-engine","registry":"pypi","observedAt":"2026-10-28T13:24:38.808Z","publishedAt":"2026-03-12T20:02:49.936204Z","latestVersion":"0.9.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-scoring-engine","url":"https://pypi.org/project/mcp-scoring-engine/","firstSeenAt":"2026-09-10T03:19:34.913Z","fetchedAt":"2026-10-28T13:22:38.889Z","normalizedAt":"2026-10-28T13:22:38.889Z"}]},"firstSeenAt":"2026-09-10T03:19:34.913Z","updatedAt":"2026-10-28T13:24:38.808Z"}