{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_4yzfzshxj9ax","handle":"agenthive-mcp","url":"https://wellknown.network/agents/agenthive-mcp","links":{"self":"https://wellknown.network/agents/agenthive-mcp/record.json","html":"https://wellknown.network/agents/agenthive-mcp","markdown":"https://wellknown.network/agents/agenthive-mcp/record.md","api":"https://wellknown.network/api/v1/agents/agenthive-mcp","status":"https://wellknown.network/api/v1/agents/agenthive-mcp/status","claim":"https://wellknown.network/agents/agenthive-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/agenthive-mcp/claim.json","badge":"https://wellknown.network/agents/agenthive-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/agenthive-mcp/history","tools":"https://wellknown.network/api/v1/agents/agenthive-mcp/tools"},"ard":{"identifier":"urn:air::server:agenthive-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"agenthive-mcp","summary":"MCP server exposing AgentHive's shared team memory as native tools for Cursor and Claude Code","description":"# agenthive-mcp\n\n![agenthive-mcp hero](docs/hero.svg)\n\n[![CI](https://github.com/polarpoint-io/agenthive-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/polarpoint-io/agenthive-mcp/actions/workflows/ci.yml)\n[![License](https://img.shields.io/github/license/polarpoint-io/agenthive-mcp)](LICENSE)\n\nA Model Context Protocol (MCP) server that exposes [AgentHive](https://github.com/polarpoint-io/agenthive)'s shared, reviewed team memory to LLM clients (Claude Desktop, Claude Code, Cursor, VS Code, etc.) - `retrieve_context`, `log_session`, `create_agent`, `list_agents`, `create_task`, and `list_tasks` as native tools, instead of a `CLAUDE.md` / `.cursor/rules` instruction block that calls AgentHive's HTTP API by hand.\n\n> **PyPI**: `pip install agenthive-mcp` &nbsp;·&nbsp; **Image**: `ghcr.io/polarpoint-io/agenthive-mcp:latest` &nbsp;·&nbsp; **Repo**: <https://github.com/polarpoint-io/agenthive-mcp>\n\n## Table of contents\n\n- [Quick start](#quick-start)\n- [Configuration](#configuration)\n- [Client integrations](#client-integrations)\n- [Tool reference](#tool-reference)\n- [Wiring an agent up to actually use these tools](#wiring-an-agent-up-to-actually-use-these-tools)\n- [Why a separate repo from AgentHive](#why-a-separate-repo-from-agenthive)\n- [Running from source](#running-from-source)\n- [Development](#development)\n- [Publishing](#publishing)\n- [Security notes](#security-notes)\n\n## Quick start\n\nYou need an AgentHive team and a personal token first - see [AgentHive's onboarding guide](https://github.com/polarpoint-io/agenthive/blob/main/ONBOARDING.md) if you don't have one yet.\n\n### 1. pip (no Docker)\n\n```bash\npip install agenthive-mcp\nexport AGENTHIVE_URL=https://your-agenthive-host\nexport AGENTHIVE_TOKEN=your_personal_token\nexport AGENTHIVE_TEAM_ID=your_team_id\n\nagenthive-mcp                                 # stdio\nTRANSPORT=http HTTP_PORT=8000 agenthive-mcp   # HTTP/SSE\n```\n\n### 2. Docker (stdio — launched by your MCP client)\n\n```bash\ndocker pull ghcr.io/polarp…","publisher":{"name":"Surj Bains","url":null},"homepage":"https://github.com/polarpoint-io/agenthive-mcp","repository":"https://github.com/polarpoint-io/agenthive","version":"1.2.0","license":"MIT License\n        \n        Copyright (c) 2026 Surj Bains\n    …","protocols":["mcp"],"tags":["mcp","agenthive","memory","coding-agents","platform-engineering"],"pricing":null,"endpoints":[{"url":"pypi:agenthive-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":"knowledge.memory","name":"Agent Memory","confidence":1,"provenance":"declared"},{"slug":"dev.docs-lookup","name":"Documentation Lookup","confidence":0.791,"provenance":"derived"},{"slug":"code.generation","name":"Code Generation","confidence":0.75,"provenance":"derived"}],"categories":["code","dev","knowledge"],"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":"agenthive-mcp","registry":"pypi","observedAt":"2026-10-30T19:26:43.810Z","publishedAt":"2026-10-17T16:14:41.587276Z","latestVersion":"1.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"agenthive-mcp","url":"https://pypi.org/project/agenthive-mcp/","firstSeenAt":"2026-09-18T08:26:15.694Z","fetchedAt":"2026-10-30T19:24:32.921Z","normalizedAt":"2026-10-30T19:24:32.921Z"}]},"firstSeenAt":"2026-09-18T08:26:15.694Z","updatedAt":"2026-10-30T19:26:43.810Z"}