{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_fjess4t2dpwm","handle":"agentmesh-mcp","url":"https://wellknown.network/agents/agentmesh-mcp","links":{"self":"https://wellknown.network/agents/agentmesh-mcp/record.json","html":"https://wellknown.network/agents/agentmesh-mcp","markdown":"https://wellknown.network/agents/agentmesh-mcp/record.md","api":"https://wellknown.network/api/v1/agents/agentmesh-mcp","status":"https://wellknown.network/api/v1/agents/agentmesh-mcp/status","claim":"https://wellknown.network/agents/agentmesh-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/agentmesh-mcp/claim.json","badge":"https://wellknown.network/agents/agentmesh-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:agentmesh-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"agentmesh-mcp","summary":"Multi-agent framework with persistent expert sessions and context isolation — MCP server for Claude Code","description":"# agentmesh\n\nMulti-agent framework with persistent expert sessions and context isolation — runs as an **MCP server for Claude Code**.\n\n## The problem\n\nWhen investigating complex bugs or features that span multiple domains (permissions, database, frontend...), a single Claude Code session accumulates too much context. It gets slow, expensive, and loses focus.\n\n### Why existing approaches don't fully solve it\n\n**Documentation files (SKILL.md, README, notes)** give the agent orientation — but they load into *your* context, not a separate one. Every file you add to help Claude understand a domain is context your session consumes. And they're static: they don't update as Claude investigates.\n\n**Memory files** have the same problem. They're summaries you write manually after the fact. They help with orientation but they don't capture the actual investigation — the grep results, the file reads, the chain of reasoning. Next session you start from the summary, not from where the investigation left off.\n\n**Neither approach isolates context.** When Claude investigates a permissions issue to answer a question about pipelines, all that permissions code ends up in the pipeline session. Context bleeds.\n\nThe real problem is: **there's no way to ask \"what does the permissions expert know?\" without loading all of that knowledge into the current session.**\n\n## How agentmesh solves it\n\nYou define **expert agents** — each specialized in one domain. When Claude Code needs to know something outside its current focus, it calls `query_expert`. The expert:\n\n1. Loads its **persistent session** (accumulated knowledge from prior investigations)\n2. **Investigates** using tools (read files, grep, find) — in its own isolated context\n3. Returns **only the answer** to Claude Code — never the investigation steps\n\nClaude Code's context stays clean. The expert's context grows richer over time.\n\n```\nClaude Code (main agent):\n  \"Why does checkout fail for guest users?\"\n  → calls query_expert(\"auth\", \"ca…","publisher":null,"homepage":"https://github.com/fedegonzalezm-coder/agentmesh","repository":"https://github.com/fedegonzalezm-coder/agentmesh","version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["ai","agents","mcp","claude","multi-agent","llm"],"pricing":null,"endpoints":[{"url":"pypi:agentmesh-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"}},"derived":{"capabilities":[{"slug":"automation.orchestration","name":"Agent Orchestration","confidence":1,"provenance":"declared"},{"slug":"code.documentation","name":"Code Documentation","confidence":0.848,"provenance":"derived"},{"slug":"security.identity","name":"Identity & Access","confidence":0.814,"provenance":"derived"},{"slug":"dev.filesystem","name":"Filesystem","confidence":0.802,"provenance":"derived"},{"slug":"data.database","name":"Databases","confidence":0.791,"provenance":"derived"}],"categories":["automation","code","data","dev","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","registry":"pypi","observedAt":"2026-09-09T08:22:32.969Z","publishedAt":"2026-06-03T10:49:20.192302Z","latestVersion":"0.1.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"agentmesh-mcp","url":"https://pypi.org/project/agentmesh-mcp/","firstSeenAt":"2026-09-09T08:21:10.366Z","fetchedAt":"2026-09-09T08:21:10.366Z","normalizedAt":"2026-09-09T08:21:10.366Z"}]},"firstSeenAt":"2026-09-09T08:21:10.366Z","updatedAt":"2026-09-09T08:22:32.969Z"}