neurohive
by AdelElo13
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HIVEMIND_AGENT | No | Agent identifier (e.g. Agent-Backend, Agent-DevOps) | |
| OPENAI_API_KEY | No | Required when using OpenAI embeddings (NEUROMCP_EMBEDDING_PROVIDER=openai) | |
| HIVEMIND_COMPANY | No | Company/project name. Sets the shared namespace to company-<name> | |
| NEUROMCP_DB_PATH | No | SQLite database path | ~/.neuromcp/memory.db |
| NEUROMCP_LOG_LEVEL | No | Log level: debug, info, warn, error | info |
| HIVEMIND_AGENT_ROLE | No | Agent role label for priming context | |
| HIVEMIND_PAPERCLIP_URL | No | Paperclip API URL for auto-detection | http://localhost:3100 |
| HIVEMIND_PRIMING_COUNT | No | Number of top memories to include in priming context | 10 |
| HIVEMIND_PRIMING_CATEGORIES | No | Comma-separated categories to prioritize in priming | |
| NEUROMCP_EMBEDDING_PROVIDER | No | Embedding provider: local, openai, ollama | local |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues