{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_2e6c9h9fvfju","handle":"agentmesh-mcp-server","url":"https://wellknown.network/agents/agentmesh-mcp-server","links":{"self":"https://wellknown.network/agents/agentmesh-mcp-server/record.json","html":"https://wellknown.network/agents/agentmesh-mcp-server","markdown":"https://wellknown.network/agents/agentmesh-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/agentmesh-mcp-server","status":"https://wellknown.network/api/v1/agents/agentmesh-mcp-server/status","claim":"https://wellknown.network/agents/agentmesh-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/agentmesh-mcp-server/claim.json","badge":"https://wellknown.network/agents/agentmesh-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/agentmesh-mcp-server/history","tools":"https://wellknown.network/api/v1/agents/agentmesh-mcp-server/tools"},"ard":{"identifier":"urn:air::server:agentmesh-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"agentmesh-mcp-server","summary":"MCP Server for Claude Desktop - Agent OS kernel primitives including code safety verification, CMVK multi-model review, and IATP trust","description":"# MCP Kernel Server\n\n> **Part of [Agent OS](https://github.com/microsoft/agent-governance-toolkit)** - Kernel-level governance for AI agents\n\n**Native Safety for Claude Desktop - Agent OS kernel primitives via Model Context Protocol (MCP)**\n\nThis server exposes Agent OS capabilities through MCP, enabling Claude Desktop and other MCP-compatible clients to use kernel-level AI agent governance.\n\n## The Problem\n\nClaude generates code without safety guarantees. It can suggest:\n- `DROP TABLE users` - deleting production data\n- Hardcoded API keys and secrets\n- `rm -rf /` - destructive file operations\n\n## The Solution\n\nAgent OS MCP Server provides safety verification that Claude calls **before** executing code:\n\n```\n[Claude generates code]\n        ↓\n[Calls verify_code_safety tool]\n        ↓\n[Agent OS returns: BLOCKED - Destructive SQL]\n        ↓\n[Claude explains why and suggests safer alternative]\n```\n\n## Quick Start\n\n### Claude Desktop Integration (60 seconds)\n\n1. Install the server:\n```bash\npip install agent-os-kernel[mcp]\n```\n\n2. Add to Claude Desktop config:\n\n**macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json`\n**Windows:** `%APPDATA%\\Claude\\claude_desktop_config.json`\n\n```json\n{\n  \"mcpServers\": {\n    \"agent-os\": {\n      \"command\": \"mcp-kernel-server\",\n      \"args\": [\"--stdio\"]\n    }\n  }\n}\n```\n\n3. Restart Claude Desktop. You now have access to 8 safety tools!\n\n## Available Tools\n\n### `verify_code_safety` - Code Safety Check ⭐ NEW\n**The primary tool for Claude Desktop.** Checks if code is safe before execution.\n\n```json\n{\n  \"name\": \"verify_code_safety\",\n  \"arguments\": {\n    \"code\": \"await db.query('DROP TABLE users')\",\n    \"language\": \"javascript\"\n  }\n}\n```\n\nReturns:\n```json\n{\n  \"safe\": false,\n  \"violations\": [\n    {\n      \"rule\": \"drop_table\",\n      \"severity\": \"critical\",\n      \"message\": \"Destructive SQL: DROP operation detected\",\n      \"alternative\": \"Consider using soft delete or archiving instead of DROP\"\n    }\n  ],\n  \"blocked_reason\": \"Des…","publisher":null,"homepage":"https://github.com/microsoft/agent-governance-toolkit","repository":"https://github.com/microsoft/agent-governance-toolkit/tree/main/agent-governance-python/agent-os/modules/mcp-kernel-server","version":"3.7.0","license":"MIT","protocols":["mcp"],"tags":["mcp","model-context-protocol","agent-os","ai-safety","kernel","claude-desktop","code-safety"],"pricing":null,"endpoints":[{"url":"pypi:agentmesh-mcp-server","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":"data.database","name":"Databases","confidence":0.733,"provenance":"derived"}],"categories":["data"],"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-server","registry":"pypi","observedAt":"2026-10-27T18:27:39.081Z","publishedAt":"2026-05-18T22:51:47.424820Z","latestVersion":"3.7.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"agentmesh-mcp-server","url":"https://pypi.org/project/agentmesh-mcp-server/","firstSeenAt":"2026-09-09T08:21:10.801Z","fetchedAt":"2026-10-27T18:26:48.661Z","normalizedAt":"2026-10-27T18:26:48.661Z"}]},"firstSeenAt":"2026-09-09T08:21:10.801Z","updatedAt":"2026-10-27T18:27:39.081Z"}