neurohive is a multi-agent memory intelligence server that enables shared knowledge, expertise tracking, and conflict detection for AI agent teams.
From the registry: Multi-agent memory intelligence with expertise tracking and conflict detection
Please install the `neurohive` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js 18+** — Node.js 18 or higher (https://nodejs.org/)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["neurohive"]
- required environment variables:
- `HIVEMIND_COMPANY`: Company/project name used as the shared namespace (example: `my-project`)
- `HIVEMIND_AGENT`: Agent identifier (example: `Agent-Backend`)
- optional environment variables:
- `HIVEMIND_AGENT_ROLE`: Agent role label for priming (example: `backend`)
- `HIVEMIND_PAPERCLIP_URL`: Paperclip API URL for auto-detection (example: `http://localhost:3100`)
- `NEUROMCP_DB_PATH`: Shared SQLite database path (example: `~/.neuromcp/memory.db`)
Note: Multi-agent memory intelligence layer on top of neuromcp. Shared knowledge, expertise tracking, conflict detection. Not supported on Windows (native). All neuromcp tools pass through unchanged.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.HIVEMIND_COMPANYrequiredCompany/project name. Sets the shared namespace to company-<name>HIVEMIND_AGENTrequiredAgent identifier (e.g. Agent-Backend, Agent-DevOps)HIVEMIND_AGENT_ROLErequiredAgent role label for priming contextOPENAI_API_KEYRequired when using OpenAI embeddingsAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.