What it does

Stores and retrieves product knowledge — decisions, specs, context — so an agent can answer 'why is this built this way' without reading six months of tickets. The value is entirely proportional to what you put in. An empty knowledge base produces confident nonsense.

Install

Terminal

npx -y @productbrain/mcp

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "productbrain": {
      "command": "npx",
      "args": [
        "-y",
        "@productbrain/mcp"
      ]
    }
  }
}

Use it for

Keeping product decisions queryable next to the code

Skip it if

Teams whose product knowledge lives in a wiki nobody updates

When to use it

Reach for this when the task needs product inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

Product Brain MCP