This MCP server connects Cursor to a Pincushion project so agents can read stakeholder feedback pins, claim them, add replies, search annotations, and resolve pins. It is installed via the Cursor plugin and exposes several MCP tools for pin and feedback management.
From the registry: Stakeholders pin feedback on your live app; your AI coding agent reads it via MCP and fixes it
Please install the `pincushion` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Cursor with MCP support** — Cursor is required to use this MCP server from the plugin or manual MCP configuration. (https://cursor.com/)
- **Install Node.js** — Node.js is required so the server can be launched via npx.
- **Create a Pincushion account** — A Pincushion account is required to use the service. (https://pincushion.io)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["pincushion-mcp","--project-dir","."]
Note: The README provides a manual MCP configuration using npx. No environment variables are documented in the README. The server is described as a Cursor plugin, but the extracted canonical configuration is the underlying stdio command shown in the manual MCP config.
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.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.