MCP Server

Server Name: repo-cat-mcp
Version: 1.0.0
Transport: Streamable HTTP (Stateless)

Authentication Methods

• Header: Authorization: Bearer <api-key> (recommended for MCP clients)
• Legacy Header: x-api-key: <api-key> (backward compatibility)
• Query Parameter: ?apiKey=<api-key>

Stateless Mode

The MCP server operates in stateless mode. Each request creates a new transport instance with no session persistence. The user context (userId) is extracted from the API key and passed to tools via the request context.

https://repocat.cloud/mcp

Example: Accessing a Scan Resource

// Access scan resource via MCP
const result = await client.readResource({
  uri: 'scan://123',
});

console.log(result.contents[0].text);

analyze-repo

Guided prompt template that helps AI tools analyze a GitHub repository by triggering a scan and polling for results.

When an AI tool uses this prompt, it guides the assistant through:

• Calling the trigger_scan tool to start a scan
• Polling the get_scan tool to check progress
• Providing a comprehensive summary once complete

Configuration

Add the following entry to your Opencode config file (located at ~/.config/opencode/opencode.jsonc for global availability, or a project-level opencode.jsonc):

{
  "mcp": {
    "repo-cat": {
      "type": "remote",
      "url": "https://repocat.cloud/mcp",
      "headers": { "Authorization": "Bearer <your-api-key>" }
    }
  }
}

Getting an API Key

Generate an API key from the Dashboard > API Key Management section. Use it in place of <your-api-key> in the config above.

Restart Required

Opencode loads its configuration once at startup and does not hot-reload. After saving the config change, quit and restart Opencode for the MCP server to be picked up.

Available Capabilities

Once connected, Opencode automatically discovers all tools, resources, and prompts exposed by the server. You can use them in chat like any other Opencode tool:

• trigger_scan — Start a new repository scan
• get_scan — Check scan status by ID
• get_scan_pdf — Download a PDF report
• list_scans — List your recent scans
• cancel_scan — Cancel an in-progress scan
• delete_scan — Delete a completed or failed scan
• get_user_info — View account and subscription details
• get_settings / update_settings — Manage preferences

For the full list of available tools and their parameters, see the Tools section above.

JavaScript: Connecting with MCP SDK

import { Client } from '@modelcontextprotocol/sdk/client/index.js';
import { StreamableHTTPClientTransport } from '@modelcontextprotocol/sdk/client/streamableHttp.js';

const transport = new StreamableHTTPClientTransport(
  new URL('https://repocat.cloud/mcp'),
  { headers: { Authorization: 'Bearer <your-api-key>' } }
);

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

await client.connect(transport);

// Call a tool
const result = await client.callTool({
  name: 'trigger_scan',
  arguments: {
    repo: 'facebook/react',
    level: 'standard',
  },
});

console.log(result);

cURL: Calling a Tool Directly

You can also call MCP tools directly using cURL with JSON-RPC:

curl -X POST "https://repocat.cloud/mcp" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-here" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "trigger_scan",
      "arguments": {
        "repo": "facebook/react",
        "level": "standard"
      }
    }
  }'

Use Case: AI Repository Analysis

An AI tool can use the analyze-repo prompt to analyze a repository:

1. AI loads the analyze-repo prompt
2. Prompt guides AI to call trigger_scan with repo details
3. AI polls get_scan to check scan status
4. Once complete, AI reads the scan://{scanId} resource
5. AI provides a comprehensive analysis to the user