productboard-mcp
An MCP server that connects Claude to the ProductBoard API v2, enabling natural language management of notes, entities, members, analytics, Jira integrations, and webhooks.
README
productboard-mcp
An MCP (Model Context Protocol) server that connects Claude to the ProductBoard API v2. Ask Claude questions about your ProductBoard workspace in plain English.
What you can do
- Notes — list, search, create, update, delete feedback notes and manage their relationships to features and customers
- Entities — query and manage features, initiatives, objectives, components, releases, and more
- Members & Teams — look up members, list teams, manage team membership
- Analytics — retrieve member activity data
- Jira integrations — inspect Jira integration configs and connections
- Webhooks — list, create, and delete webhook subscriptions
35 tools in total, covering the full ProductBoard API v2 surface.
Requirements
- Claude Desktop
- Node.js 18+
- A ProductBoard account on the Pro plan or higher
- A ProductBoard API token (Settings → Workspace → API Access)
Setup
1. Clone and build
git clone https://github.com/jonnystewart/productboard-mcp
cd productboard-mcp
npm install
npm run build
2. Add your API token
mkdir -p ~/.config/productboard-mcp
echo "PRODUCTBOARD_API_TOKEN=your_token_here" > ~/.config/productboard-mcp/.env
Get your token from ProductBoard: Settings → Workspace → API Access → Generate token
3. Add to Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"productboard": {
"command": "node",
"args": ["/absolute/path/to/productboard-mcp/dist/server.js"]
}
}
}
Alternatively, pass the token directly in the config:
{
"mcpServers": {
"productboard": {
"command": "node",
"args": ["/absolute/path/to/productboard-mcp/dist/server.js"],
"env": {
"PRODUCTBOARD_API_TOKEN": "your_token_here"
}
}
}
}
4. Restart Claude Desktop
Fully quit (Cmd+Q) and relaunch. ProductBoard will appear in the connectors list.
Example prompts
- "List my 10 most recent ProductBoard notes and summarise them"
- "Show me all features in the backlog"
- "How many notes were created last week?"
- "Find all initiatives linked to our Q2 release"
- "List all members and which teams they belong to"
Development
npm run dev # Run with live reload (no build step)
npm run build # Compile TypeScript → dist/
npm run lint # ESLint
Notes on the API
- ProductBoard API v2 is currently in beta
- Rate limit: 50 requests/second per token
- Many field names are workspace-specific — use the
pb_list_note_configurationsandpb_list_entity_configurationstools to discover what's available in your workspace before creating records
Licence
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.