{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_awgwtqktccbn","handle":"agentmesh-mcp-trust","url":"https://wellknown.network/agents/agentmesh-mcp-trust","links":{"self":"https://wellknown.network/agents/agentmesh-mcp-trust/record.json","html":"https://wellknown.network/agents/agentmesh-mcp-trust","markdown":"https://wellknown.network/agents/agentmesh-mcp-trust/record.md","api":"https://wellknown.network/api/v1/agents/agentmesh-mcp-trust","status":"https://wellknown.network/api/v1/agents/agentmesh-mcp-trust/status","claim":"https://wellknown.network/agents/agentmesh-mcp-trust/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/agentmesh-mcp-trust/claim.json","badge":"https://wellknown.network/agents/agentmesh-mcp-trust/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/agentmesh-mcp-trust/history","tools":"https://wellknown.network/api/v1/agents/agentmesh-mcp-trust/tools"},"ard":{"identifier":"urn:air::server:agentmesh-mcp-trust","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"agentmesh_mcp_trust","summary":"MCP server exposing AgentMesh trust management tools for Claude, GPT, and other AI agents","description":"# MCP Trust Server for AgentMesh\n\nMCP server that exposes AgentMesh trust management as tools for AI agents via the [Model Context Protocol](https://modelcontextprotocol.io). Compatible with Claude, GPT, and any MCP-capable client.\n\n## What it does\n\nProvides six trust-management tools over MCP:\n\n| Tool | Description |\n|------|-------------|\n| `check_trust` | Check if an agent is trusted — returns trust score |\n| `get_trust_score` | Detailed trust score breakdown |\n| `establish_handshake` | Initiate a cryptographic trust handshake with a peer |\n| `verify_delegation` | Verify a scope chain is valid |\n| `record_interaction` | Record an interaction outcome to update trust |\n| `get_identity` | Get this server's DID, public key, and capabilities |\n\nTrust is scored across multiple dimensions (0–1000 each).\n\n## Getting Started\n\nPrerequisites: Python 3.11 or newer, `pip`, and an MCP-capable client such as Claude Desktop.\n\n```bash\npython -m venv .venv\nsource .venv/bin/activate\npip install mcp-trust-server\nAGENTMESH_AGENT_NAME=my-trust-server mcp-trust-server\n```\n\nThe server starts with in-memory storage by default. Set `AGENTMESH_MIN_TRUST_SCORE` or `AGENTMESH_STORAGE_BACKEND` before launch to customize the local policy.\n\n## Installation\n\n```bash\npip install mcp-trust-server\n```\n\nOr install from the repository:\n\n```bash\ncd agent-governance-python/agent-mesh/packages/mcp-trust-server\npip install -e \".[dev]\"\n```\n\n## Configuration\n\n| Environment Variable | Description | Default |\n|---------------------|-------------|---------|\n| `AGENTMESH_AGENT_NAME` | Agent name for this server instance | `mcp-trust-agent` |\n| `AGENTMESH_MIN_TRUST_SCORE` | Minimum trust threshold (0–1000) | `500` |\n| `AGENTMESH_STORAGE_BACKEND` | Storage backend (`memory` or `redis`) | `memory` |\n\n## Usage\n\n### Run directly\n\n```bash\npython -m mcp_trust_server\n```\n\nOr via the console script:\n\n```bash\nmcp-trust-server\n```\n\n### Claude Desktop\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": …","publisher":null,"homepage":"https://github.com/microsoft/agent-governance-toolkit/tree/main/agent-governance-python/agent-mesh/packages/mcp-trust-server","repository":"https://github.com/microsoft/agent-governance-toolkit/tree/main/agent-governance-python/agent-mesh/packages/mcp-trust-server","version":"3.7.0","license":"Apache-2.0","protocols":["mcp"],"tags":["agentmesh","ai-agents","cryptography","identity","mcp","model-context-protocol","security","trust"],"pricing":null,"endpoints":[{"url":"pypi:agentmesh_mcp_trust","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"}},"derived":{"capabilities":[{"slug":"security.identity","name":"Identity & Access","confidence":1,"provenance":"declared"}],"categories":["security"],"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":"agentmesh_mcp_trust","registry":"pypi","observedAt":"2026-10-27T18:27:39.128Z","publishedAt":"2026-05-19T23:07:09.174305Z","latestVersion":"3.7.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"agentmesh_mcp_trust","url":"https://pypi.org/project/agentmesh_mcp_trust/","firstSeenAt":"2026-09-09T08:21:11.051Z","fetchedAt":"2026-10-27T18:26:48.816Z","normalizedAt":"2026-10-27T18:26:48.816Z"}]},"firstSeenAt":"2026-09-09T08:21:11.051Z","updatedAt":"2026-10-27T18:27:39.128Z"}