Stakeholders pin feedback on your live app; your AI coding agent reads it via MCP and fixes it
Stakeholders pin feedback on your live app; your AI coding agent reads it via MCP and fixes it
The implementation-context layer for AI-native development. Stakeholders drop visual pins on any page of your live app; your AI coding agent reads each pin through MCP and ships the fix — in Claude Code, Cursor, VS Code, Windsurf, or any MCP client.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| get_annotations | Retrieve annotations from .feedback/. Filter by page, component, or status. |
| search_annotations | Full-text search across all annotations, comments, selectors, and tags. |
| get_feedback_summary | High-level rollup of all feedback: counts by status, priority, page, and component. |
| get_component_feedback | Get all feedback for a specific LWC component with a plain-language summary. |
| resolve_annotation | |
| add_agent_reply | Add a reply to an annotation thread (e.g., ask clarifying questions). |
| fix_and_resolve | Combine fixing code and marking an annotation as resolved in one call. Optionally records commit / branch / PR metadata so the dashboard can backlink to what shipped. |
| get_implementation_packet | Fetch a single implementation packet for one page URL — selector list, full pin payloads, suggested branch name, and traceability config. Use when an agent wants to batch-fix one page in a single branch. |
| assign_pin_to_agent | Dispatch a pin straight to your local coding agent. Promotes the pin to ready if not already, marks pending_implementation, and writes a .feedback/.agent-queue/<id>.json trigger file that agent-loop.mjs picks up and shel |
| link_pin_deploy | Attach a deploy URL to a resolved pin. Typically called by the deploy-hook edge function once production includes the fix, but available manually too. |
{
"mcpServers": {
"pincushion": {
"command": "npx",
"args": ["pincushion-mcp", "--project-dir", "."]
}
}
}Configuration as documented by the project. Restart the client after saving.
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Git-backed long-term memory authority for AI agents via MCP.
Dust MCP Server with advanced agent conversation features
A Model Context Protocol (MCP) server that provides access to ProPublica's Nonprofit Explorer API for nonprofit organization search and analysis
MCP server para operações Pix (cash-in/cash-out) via Intra Pay.