Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ProductBrain MCP Server search my plan for checkout stories, then add a task under the top one"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Drive your ProductBrain plan from an MCP client — Claude Desktop, Cursor, Claude Code — with tools for search, read, mutate, the methodology workflow, and the live view.
This server is a thin transport over ProductBrain's versioned v1 REST API. Each tool is one call to an existing /api/v1 endpoint. The REST contract stays canonical:
It's stable when the MCP spec churns — the contract you depend on is the frozen v1 API, not the protocol.
You can drop to raw HTTP or bring your own LLM at any time; MCP is one front-door, not the only one.
Responses carry the same in-band _meta coaching the API returns, so your agent self-corrects.
Related MCP server: plane-mcp-server
// Claude Desktop — claude_desktop_config.json
{
"mcpServers": {
"productbrain": {
"command": "npx",
"args": ["-y", "@productbrain-com/mcp"],
"env": {
"PRODUCTBRAIN_API_KEY": "pb_your_key",
"PRODUCTBRAIN_PROJECT_ID": "your-project-id"
}
}
}
}# Claude Code
claude mcp add productbrain \
-e PRODUCTBRAIN_API_KEY=pb_your_key \
-e PRODUCTBRAIN_PROJECT_ID=your-project-id \
-- npx -y @productbrain-com/mcpCursor and other clients: add an mcpServers entry with the same command/args/env.
Var | Required | Default |
| yes | — (your |
| no | — (tools also accept a |
| no |
|
Every agent-facing /api/v1 endpoint has a tool. One tool, one endpoint, same _meta coaching passed back verbatim.
The plan
Tool | Maps to | Use |
|
| Semantic search — use first for any lookup |
|
| Bulk read, optional type/iteration filter |
|
| A node in context (ancestors/siblings/children/subtree) |
|
| Create/update/delete nodes + phases; pass |
|
| Phases; |
|
| Story-Mapping methodology (add / task-curate / phase-assign) |
|
| The plan as a portable OKF file bundle |
|
| Plan history: every add/update/delete/restore, attributed to the app or a named agent |
The view
Tool | Maps to | Use |
|
| Drive / read the live canvas |
Projects
Tool | Maps to | Use |
|
| Projects you own or are a member of; |
|
| Bootstrap a brain — seeds the system "Later" phase. Pass an explicit |
|
| Change the display name; the id is immutable |
|
| Hide/unhide without deleting (reversible) |
Webhooks
Tool | Maps to | Use |
|
| Registered hooks with |
|
| Register; returns the signing secret once |
|
| Change url/events in place, or |
|
| Remove a registration |
Share links
Tool | Maps to | Use |
|
| Mint a public read-only link; |
|
| Audit every token minted, with an |
|
| Kill a leaked or stale link |
Members and budget
Tool | Maps to | Use |
|
| Humans and agent seats on a project |
|
| Mint an agent seat; the |
|
| Passwordless guest invite, scoped to the projects you name (Team tier) |
|
| Remove a seat; an agent's key dies with its last membership |
|
| Your tier, API access, credit balance and limits — check before a large run |
|
| Tell the PB team what to improve: feature requests, friction, bugs, notes |
Full API reference: https://productbrain.com/docs/llm-guide.md.
Source: https://github.com/moxzas/productbrain-mcp (MIT). Issues and pull requests welcome there.
npm: @productbrain-com/mcp. Every release is published from the repository's tag of the same version.
MCP registry name: io.github.moxzas/productbrain (server.json in this repo is the registry manifest).
The server sends User-Agent: productbrain-mcp/<version> so you can tell MCP traffic from raw REST calls in your own logs.
Two headless scripts in the repository (src/spike-proof.ts, src/parity-proof.ts; not shipped in the npm package), both run against a real deployment. Use a throwaway project on your own account:
PRODUCTBRAIN_API_KEY=pb_your_key \
PRODUCTBRAIN_PROJECT_ID=your-sandbox-project \
npm run spike # transport + auth + one read + one write
PRODUCTBRAIN_API_KEY=pb_your_key \
npm run parity # every non-plan tool once, on a throwaway projectparity creates its own throwaway project and cleans up after itself (archiving it at the end — there is no project-delete endpoint).
The Team-tier tools (add_agent_seat, invite_contributor) return 403 team_tier_required on a Builder key, and that counts as a pass — with one caveat worth knowing. It proves the shim reached the right route and passed the error and its _meta tip straight through; it does not validate the request body, because the tier gate runs before the body is read. Run parity with a Team-tier key to check those two properly.
This server cannot be deployed
Agent-complete, permission-scoped product operations for Priorify workspaces.
Generate contextual prompts and reusable agent skills, evaluate prompts with the 16-dimension Prompt Score, and manage saved work in PromptDrive. Twelve MCP tools also provide authorized access to private Memory for source-grounded answers. Connect over Streamable HTTP using OAuth 2.1 and PKCE. Generation consumes account quota and automatically saves successful results; Memory access follows account permissions and plan limits.
ADHD-friendly tasks, notes & projects for LucidNest - 18 tools, scoped tokens, Streamable HTTP.
Create, read and live-edit visual boards, Kanban plans, Gantt timelines and diagrams with AI agents.
