Pincushion MCP Server

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.

What makes a Pincushion pin different

A pin isn't a feedback item — it's an agent work packet. Each one carries everything an agent needs to implement the change without a back-and-forth:

• URL + element selector — exactly what, exactly where
• Screenshot + viewport + DOM snippet — the visual and structural context
• Thread + project context — the conversation and the codebase it lives in
• Likely files + acceptance criteria — where to look, and how to know it's done

The loop closes itself: a stakeholder pins it → your agent reads it via MCP and fixes it in your IDE → the resolve records the commit, branch, and PR → an optional post-deploy critique verifies the fix actually landed.

This server is also how Pincushion AI runs design/copy/a11y critiques on a live page and writes the pins straight back onto it.

Installation

# npm
npm install -g pincushion-mcp

# pnpm
pnpm add -g pincushion-mcp

# yarn
yarn global add pincushion-mcp

Or run directly without installing:

# npm
npx pincushion-mcp --project-dir .

# pnpm
pnpm dlx pincushion-mcp --project-dir .

# yarn
yarn dlx pincushion-mcp --project-dir .

Quick Start

1. Install the Browser Extension

Download the Pincushion Chrome extension from pincushion.io/install/chrome.

2. Configure Your Agent

Pick your AI agent below and follow the configuration for your setup.

3. Start Using

Once configured, your agent can:

• See all feedback: get_feedback_summary
• Find specific pins: search_annotations
• Fix and mark as done: fix_and_resolve

Agent Configuration Guides

Cursor

File: .cursor/mcp.json

{
  "mcpServers": {
    "pincushion": {
      "command": "npx",
      "args": ["pincushion-mcp", "--project-dir", "."]
    }
  }
}

pnpm / yarn users: replace "command": "npx" with "command": "pnpm" and add "dlx" as the first arg, or use "command": "yarn" with "dlx" likewise.

With Supabase sync:

{
  "mcpServers": {
    "pincushion": {
      "command": "npx",
      "args": [
        "pincushion-mcp",
        "--project-dir", ".",
        "--sync-url", "https://your-supabase.com/api",
        "--api-key", "YOUR_API_KEY"
      ]
    }
  }
}

Claude Desktop

File: ~/.config/Claude/claude_desktop_config.json (Linux/Windows) or ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)

{
  "mcpServers": {
    "pincushion": {
      "command": "npx",
      "args": ["pincushion-mcp", "--project-dir", "/path/to/your/project"]
    }
  }
}

pnpm users:

{
  "mcpServers": {
    "pincushion": {
      "command": "pnpm",
      "args": ["dlx", "pincushion-mcp", "--project-dir", "/path/to/your/project"]
    }
  }
}

yarn users:

{
  "mcpServers": {
    "pincushion": {
      "command": "yarn",
      "args": ["dlx", "pincushion-mcp", "--project-dir", "/path/to/your/project"]
    }
  }
}

With Supabase sync:

{
  "mcpServers": {
    "pincushion": {
      "command": "npx",
      "args": [
        "pincushion-mcp",
        "--project-dir", "/path/to/your/project",
        "--sync-url", "https://your-supabase.com/api",
        "--api-key", "YOUR_API_KEY"
      ]
    }
  }
}

Claude Code (CLI)

Run this command to add Pincushion to Claude Code:

claude mcp add pincushion -- npx pincushion-mcp --project-dir .

Or with Supabase sync:

claude mcp add pincushion -- npx pincushion-mcp --project-dir . --sync-url https://your-supabase.com/api --api-key YOUR_API_KEY

VS Code (Copilot / Continue)

File: .vscode/settings.json

{
  "mcp.servers": {
    "pincushion": {
      "command": "npx",
      "args": ["pincushion-mcp", "--project-dir", "${workspaceFolder}"]
    }
  }
}

Windsurf / Codeium Windsurf

File: ~/.windsurf/mcp.json or ~/.config/windsurf/mcp.json

{
  "mcpServers": {
    "pincushion": {
      "command": "npx",
      "args": ["pincushion-mcp", "--project-dir", "."]
    }
  }
}

Antigravity

File: ~/.antigravity/mcp.json

{
  "mcpServers": {
    "pincushion": {
      "command": "npx",
      "args": ["pincushion-mcp", "--project-dir", "."]
    }
  }
}

OpenAI Codex / REST API Clients

For tools that don't support MCP directly, use the REST API wrapper:

npx pincushion-mcp --rest --port 3456

This starts an HTTP server on localhost:3456. Endpoints:

• GET /health — Check server status
• POST /call-tool — Invoke a tool
  • Body: { "toolName": "get_feedback_summary", "args": {} }

Example using curl:

curl -X POST http://localhost:3456/call-tool \
  -H "Content-Type: application/json" \
  -d '{"toolName": "get_feedback_summary", "args": {}}'

CLI Flags

npx pincushion-mcp [flags]

Examples

Local project:

npx pincushion-mcp --project-dir /path/to/project

With Supabase sync:

npx pincushion-mcp \
  --project-dir /path/to/project \
  --sync-url https://abcd1234.supabase.co/api \
  --api-key sb_project_key_abc123...

REST API server:

npx pincushion-mcp --rest --port 8080

Tools

get_annotations

Retrieve annotations from .feedback/. Filter by page, component, or status.

Parameters:

• pageUrl (string, optional) — Filter by page URL (partial match)
• componentName (string, optional) — Filter by LWC component name
• status (string, optional) — Filter by open, in-progress, or resolved

Example:

await mcp.callTool('get_annotations', {
  componentName: 'wmlHomePage',
  status: 'open'
});

search_annotations

Full-text search across all annotations, comments, selectors, and tags.

Parameters:

• query (string, required) — Search term

Example:

await mcp.callTool('search_annotations', {
  query: 'button label'
});

get_feedback_summary

High-level rollup of all feedback: counts by status, priority, page, and component.

Example:

await mcp.callTool('get_feedback_summary', {});

get_component_feedback

Get all feedback for a specific LWC component with a plain-language summary.

Parameters:

• componentName (string, required) — LWC component name

Example:

await mcp.callTool('get_component_feedback', {
  componentName: 'wmlHomePage'
});

resolve_annotation

Mark an annotation as resolved after fixing the issue.

Parameters:

• annotationId (string, required) — Annotation ID
• comment (string, optional) — Resolution message
• resolvedBy (string, optional) — Name to attribute resolution (default: "AI Agent")

Example:

await mcp.callTool('resolve_annotation', {
  annotationId: 'ann_abc123',
  comment: 'Updated button label in line 42 of wmlHomePage.js'
});

add_agent_reply

Add a reply to an annotation thread (e.g., ask clarifying questions).

Parameters:

• annotationId (string, required) — Annotation ID
• body (string, required) — Reply message
• author (string, optional) — Author name (default: "AI Agent")

Example:

await mcp.callTool('add_agent_reply', {
  annotationId: 'ann_abc123',
  body: 'Is this button in the main navigation or sidebar?'
});

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.

Parameters:

• annotationId (string, required) — Annotation ID
• fixDescription (string, required) — Description of the fix
• filePath (string, optional) — File where fix was applied
• lineNumber (number, optional) — Line number of the fix
• commitSha (string, optional) — Commit SHA that landed the change
• branchName (string, optional) — Branch the commit was made on
• prUrl (string, optional) — Pull request URL (GitHub/GitLab/Bitbucket; shape-validated)

Example:

await mcp.callTool('fix_and_resolve', {
  annotationId: 'ann_abc123',
  fixDescription: 'Updated button label to match design spec',
  filePath: 'src/components/wmlHomePage.js',
  lineNumber: 42,
  commitSha: 'abc123def456',
  branchName: 'pincushion/checkout-fix',
  prUrl: 'https://github.com/acme/app/pull/142'
});

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.

await mcp.callTool('get_implementation_packet', { pageUrl: '/checkout' });

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 shells out to Cursor / Claude Code / Codex.

await mcp.callTool('assign_pin_to_agent', { annotationId: 'ann_abc123' });

link_pin_deploy