MCP Client Setup

Connect your favorite AI tools to CLANKER.NET via MCP protocol.

Overview

The Model Context Protocol (MCP) allows AI assistants to use external tools. Once connected, you can:

• Search and install skills with natural language
• Execute skills directly from your AI assistant
• Manage artifacts and executions
• Access your full clanker library

Prerequisites

1. clanker account — Sign up via the mobile app
2. API key — Open Settings → External Agents and tap OR NAME A KEY (for static MCP configs), or tap ACTIVATE to pair a CLI agent that auto-receives a key via device-flow

Claude Desktop

Claude Desktop has native MCP support.

Configuration

1. Open Claude Desktop settings

2. Navigate to the MCP configuration file:

   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json

3. Add the clanker server:

{
  "mcpServers": {
    "clanker": {
      "url": "https://clanker.net/mcp/",
      "transport": "sse",
      "headers": {
        "x-api-key": "YOUR_API_KEY"
      }
    }
  }
}

4. Restart Claude Desktop

Verification

Ask Claude:

“List my installed clanker skills”

Claude should call list-installed-skills and show your library.

Usage Examples

Search for skills:

“Search the clanker marketplace for code review skills”

Install a skill:

“Install the readme-generator skill from clanker”

Execute a skill:

“Use clanker to generate a README for my TypeScript CLI project that converts markdown to HTML”

Check execution status:

“What’s the status of my current clanker execution?”

Cursor

Cursor IDE supports MCP for AI-assisted coding.

Configuration

1. Open Cursor settings (Cmd/Ctrl + ,)
2. Search for “MCP” or navigate to AI > MCP Servers
3. Add a new server:

{
  "clanker": {
    "url": "https://clanker.net/mcp/",
    "transport": "sse",
    "headers": {
      "x-api-key": "YOUR_API_KEY"
    }
  }
}

4. Save and reload Cursor

Usage in Cursor

When using Cursor’s AI features, you can reference clanker tools:

In chat:

“Use clanker’s code-reviewer skill to analyze this file for security issues”

With context:

“Execute clanker’s test-generator skill on the selected function”

VS Code

VS Code can use MCP via extensions.

Setup with Continue Extension

1. Install the Continue extension
2. Open Continue settings
3. Add MCP server configuration:

{
  "mcpServers": {
    "clanker": {
      "url": "https://clanker.net/mcp/",
      "headers": {
        "x-api-key": "YOUR_API_KEY"
      }
    }
  }
}

Setup with Other Extensions

Check your MCP-compatible extension’s documentation for configuration format. Most use similar JSON structure.

ChatGPT (with MCP Support)

ChatGPT supports MCP in Developer Mode and Deep Research.

Configuration

1. Open ChatGPT settings
2. Navigate to Developer Mode or Deep Research settings
3. Add MCP server:

URL: https://clanker.net/mcp/

Headers:

x-api-key: YOUR_API_KEY

Custom Clients

Build your own MCP client using the protocol.

SSE Transport (Recommended)

import { Client } from '@modelcontextprotocol/sdk/client';
import { SSEClientTransport } from '@modelcontextprotocol/sdk/client/sse';

const transport = new SSEClientTransport(
  new URL('https://clanker.net/mcp/'),
  {
    headers: {
      'x-api-key': process.env.CLANKER_API_KEY
    }
  }
);

const client = new Client({
  name: 'my-client',
  version: '1.0.0'
});

await client.connect(transport);

// List available tools
const tools = await client.listTools();
console.log('Available tools:', tools);

// Call a tool
const result = await client.callTool({
  name: 'list-installed-skills',
  arguments: {
    limit: 5
  }
});

console.log('Search results:', result);

Streamable HTTP Transport

import { StreamableHTTPClientTransport } from '@modelcontextprotocol/sdk/client/streamableHttp';

const transport = new StreamableHTTPClientTransport(
  new URL('https://clanker.net/mcp/'),
  {
    headers: {
      'x-api-key': process.env.CLANKER_API_KEY
    }
  }
);

Available Tools

Once connected, you have access to all clanker MCP tools:

Skills are executed via REST (POST /api/v1/skills/:slug/run or POST /api/v1/executions), not over MCP. Over MCP you discover, install, and monitor runs; workflow runs are managed through the Workflows REST API.

See MCP API Reference for detailed documentation.

Troubleshooting

“Invalid API key” Error

1. Verify the key in Settings → External Agents (it should appear with an ACTIVE / IDLE / DORMANT pill based on last-used time)
2. Check for typos in configuration
3. Ensure the key hasn’t been revoked

Connection Timeout

1. Check your internet connection
2. Verify the URL is correct (https://clanker.net/mcp/)

Tools Not Appearing

1. Restart your AI client
2. Check configuration file syntax (valid JSON)
3. Verify the server is listed in client’s MCP settings

Rate Limit Errors

MCP requests are limited to 60/minute. If you hit limits:

1. Wait for the reset period
2. Batch related operations
3. Cache results when possible

SSE Connection Drops

SSE connections may drop after ~30 minutes of inactivity. Your client should:

1. Detect disconnection
2. Automatically reconnect
3. Resume from last known state

Security Best Practices

1. Never share API keys - Each user should have their own key
2. Use environment variables - Don’t hardcode keys in config files
3. Rotate keys periodically - Delete and regenerate keys monthly
4. Monitor usage - Check the app for unusual activity
5. Revoke compromised keys - Immediately revoke if exposed

Next Steps

• Creating Skills - Build your own skills
• GitHub Actions CI/CD - Automate with CI/CD
• MCP API Reference - Explore all available tools