Kernal is a local-first MCP server that stores and queries a professional knowledge graph from natural-language notes about meetings, calls, and other interactions. It uses Claude to extract people, organizations, activities, actions, topics, and relationships into a SQLite-backed graph.
From the registry: Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP.
$ npx kernal-mcp initPlease install the `kernal-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js and npm** — Install Node.js and npm to run the MCP server via npx.
- **Initialize Kernal database** — Run the init command once to create the local SQLite database at ~/.kernal/kernal.db and generate the initial MCP setup info. Run: `npx kernal-mcp init`
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","kernal-mcp","serve"]
Note: The README's primary MCP setup uses stdio transport via `kernal serve`. The cloud server and dashboard are separate self-hosting features, not required for the MCP client configuration. Kernal uses a local SQLite database created during `npx kernal-mcp init`.
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.KERNAL_API_KEYrequiredAPI key used for authentication for the cloud server.AI 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.