{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_k47ahy9a3agx","handle":"trustscore-mcp","url":"https://wellknown.network/agents/trustscore-mcp","links":{"self":"https://wellknown.network/agents/trustscore-mcp/record.json","html":"https://wellknown.network/agents/trustscore-mcp","markdown":"https://wellknown.network/agents/trustscore-mcp/record.md","api":"https://wellknown.network/api/v1/agents/trustscore-mcp","status":"https://wellknown.network/api/v1/agents/trustscore-mcp/status","claim":"https://wellknown.network/agents/trustscore-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/trustscore-mcp/claim.json","badge":"https://wellknown.network/agents/trustscore-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:trustscore-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"trustscore-mcp","summary":"Trust and reputation scores for AI agent service selection","description":"# TrustScore\n\n[![CI](https://github.com/bensargotest-sys/bensargotest-sys/actions/workflows/ci.yml/badge.svg)](https://github.com/bensargotest-sys/bensargotest-sys/actions/workflows/ci.yml)\n\n**Trust and reputation scores for AI agent service selection.**\n\nTrustScore is an MCP server that helps AI agents make better decisions about which service providers to trust. Think of it as a credit score for APIs, agents, and tools.\n\n## Prerequisites\n\n- **Python 3.10 or higher** ([download](https://python.org))\n- pip 20.0+ (included with Python)\n- 10GB disk space (for database and logs)\n- Internet connection (for initial database seeding)\n\nVerify your setup:\n```bash\npython3 --version  # Should show 3.10+\npip3 --version     # Should show 20.0+\n```\n\n## Quick Start\n\n```bash\n# 1. Clone repository\ngit clone https://github.com/bensargotest-sys/trustscore.git\ncd trustscore\n\n# 2. Create virtual environment (recommended)\npython3 -m venv venv\nsource venv/bin/activate  # On Windows: venv\\Scripts\\activate\n\n# 3. Install package\npip install -e .\n\n# 4. Seed database with 200+ MCP servers\npython scripts/seed_database.py\n\n# 5. Run as MCP server\npython -m src.server\n\n# 6. Verify it's working\npython -m tests.test_basic\n```\n\n## What Problem Does This Solve?\n\nAI agents need to call external services: APIs, other agents, databases, DeFi protocols. But how do you know which ones are reliable? \n\n- **Uniswap** might have 99% uptime\n- **SketchySwap** might fail 80% of the time\n- **SlowAPI** might timeout constantly\n\nWithout trust data, agents pick randomly or rely on hard-coded preferences. TrustScore fixes this with real behavioral data.\n\n## How It Works\n\n1. **Agents report outcomes** after calling a service\n2. **TrustScore aggregates** success rates, latency, failure patterns\n3. **Other agents query** TrustScore before picking a provider\n4. **Network effect:** More users = better data = better decisions\n\n## MCP Tools\n\n### `trustscore_rank`\nRank multiple providers by trust score.\n\n```json\n{\n  \"provid…","publisher":{"name":"bensargotest-sys","url":null},"homepage":"https://github.com/bensargotest-sys/trustscore#readme","repository":"https://github.com/bensargotest-sys/trustscore#readme","version":"0.1.0","license":"MIT License\n        \n        Copyright (c) 2026 TrustScore Cont…","protocols":["mcp"],"tags":["mcp","trust","reputation","ai","agents","scoring"],"pricing":null,"endpoints":[{"url":"pypi:trustscore-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":1,"provenance":"declared"},{"slug":"data.database","name":"Databases","confidence":0.791,"provenance":"derived"},{"slug":"dev.monitoring","name":"Monitoring & Observability","confidence":0.756,"provenance":"derived"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":0.688,"provenance":"derived"}],"categories":["ai","data","dev"],"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":"trustscore-mcp","registry":"pypi","observedAt":"2026-09-10T14:24:37.624Z","publishedAt":"2026-02-12T00:05:48.669092Z","latestVersion":"0.1.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"trustscore-mcp","url":"https://pypi.org/project/trustscore-mcp/","firstSeenAt":"2026-09-10T14:23:25.453Z","fetchedAt":"2026-09-10T14:23:25.453Z","normalizedAt":"2026-09-10T14:23:25.453Z"}]},"firstSeenAt":"2026-09-10T14:23:25.453Z","updatedAt":"2026-09-10T14:24:37.624Z"}