> ## Documentation Index > Fetch the complete documentation index at: https://docs.credprotocol.com/llms.txt > Use this file to discover all available pages before exploring further. # Getting Started > Connect your AI agent or application to Cred Protocol MCP services # Getting Started with MCP Services This guide shows you how to connect to Cred Protocol's MCP services using different methods. ## Prerequisites All MCP endpoints require an API key. Generate one from the [Cred Protocol Dashboard](https://app.credprotocol.com/dashboard). ## Method 1: HTTP Endpoints (Simplest) The easiest way to use MCP services is through the HTTP endpoints. ### Base URL ``` https://api.credprotocol.com/mcp ``` ### Quick Test ```bash theme={null} # Get a credit score curl -H "Authorization: Bearer YOUR_API_KEY" \ "https://api.credprotocol.com/mcp/score/vitalik.eth" # List available tools curl -H "Authorization: Bearer YOUR_API_KEY" \ "https://api.credprotocol.com/mcp/tools" ``` ### Response ```json theme={null} { "address": "0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045", "score": 774, "decile": 5, "range": "good", "model_version": "andromeda_1.0", "timestamp": "2026-03-31T06:21:16.423948Z", "source": "live" } ``` ## Method 2: Cursor IDE Integration If you're using [Cursor](https://cursor.sh), you can integrate Cred Protocol as an MCP server. ### Step 1: Configure Cursor Add to your `.cursor/mcp.json` file: ```json theme={null} { "mcpServers": { "cred-protocol": { "url": "https://api.credprotocol.com/mcp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } } ``` ### Step 2: Use in Cursor Once configured, you can ask Cursor's AI: > "What's the credit score for vitalik.eth?" The AI will automatically call the MCP tool and respond with the result. ## Method 3: Claude Code For [Claude Code](https://claude.ai/code) (CLI, desktop app, or IDE extensions), add to your project's `.mcp.json`: ```json theme={null} { "mcpServers": { "cred-protocol": { "type": "url", "url": "https://api.credprotocol.com/mcp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } } ``` Once configured, you can ask Claude Code directly: > "What's the credit score for vitalik.eth?" ## Method 4: Claude Desktop For [Claude Desktop](https://claude.ai/download), add to your MCP configuration: ```json theme={null} { "mcpServers": { "cred-protocol": { "url": "https://api.credprotocol.com/mcp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } } ``` ## Method 5: Custom HTTP Client Build your own client using standard HTTP requests: ### Python ```python theme={null} import httpx API_KEY = "YOUR_API_KEY" BASE_URL = "https://api.credprotocol.com/mcp" HEADERS = {"Authorization": f"Bearer {API_KEY}"} async def get_credit_score(address: str) -> dict: """Get credit score via MCP HTTP endpoint.""" async with httpx.AsyncClient() as client: response = await client.get( f"{BASE_URL}/score/{address}", headers=HEADERS, ) return response.json() # Usage score = await get_credit_score("vitalik.eth") print(f"Score: {score['score']} ({score['range']})") ``` ### JavaScript/TypeScript ```typescript theme={null} const API_KEY = "YOUR_API_KEY"; const BASE_URL = "https://api.credprotocol.com/mcp"; async function getCreditScore(address: string): Promise { const response = await fetch(`${BASE_URL}/score/${address}`, { headers: { Authorization: `Bearer ${API_KEY}` }, }); return response.json(); } // Usage const score = await getCreditScore("vitalik.eth"); console.log(`Score: ${score.score} (${score.range})`); ``` ## Available Endpoints All endpoints require `Authorization: Bearer YOUR_API_KEY` header. **Score & Reports:** | Endpoint | Method | Description | | ------------------------------------------------ | ------ | --------------------------------------- | | `/mcp/score/{address}` | GET | Get credit score | | `/mcp/score/batch` | POST | Batch score multiple addresses | | `/mcp/score/aggregate?addresses=...` | GET | Aggregated score for multiple addresses | | `/mcp/summary/{address}` | GET | Get financial summary | | `/mcp/report/{address}` | GET | Comprehensive multi-chain credit report | | `/mcp/report/{address}/summary` | GET | Summary report (no per-chain details) | | `/mcp/report/{address}/chain/{chain_id}` | GET | Single-chain detailed report | | `/mcp/report/{address}/chain/{chain_id}/summary` | GET | Single-chain summary | **Portfolio:** | Endpoint | Method | Description | | ------------------------------------------- | ------ | --------------------------------- | | `/mcp/portfolio/{address}` | GET | Get total portfolio value | | `/mcp/portfolio/{address}/chain/{chain_id}` | GET | Get chain-specific portfolio | | `/mcp/portfolio/{address}/composition` | GET | Portfolio breakdown by asset type | **Identity & Graph:** | Endpoint | Method | Description | | --------------------------------- | ------ | ------------------------------- | | `/mcp/identity/{address}` | GET | Get identity attestations | | `/mcp/identity/{address}/sybil` | GET | Sybil detection score | | `/mcp/graph/{address}?chain_id=1` | GET | Transaction graph visualization | **Agents (ERC-8004):** | Endpoint | Method | Description | | ----------------------------------------------- | ------ | ---------------------------------- | | `/mcp/agents/count` | GET | Total registered agents | | `/mcp/agents` | GET | Paginated agent list | | `/mcp/agents/search?q={query}` | GET | Search agents by name/description | | `/mcp/agents/{agent_id}` | GET | Get agent info by ID | | `/mcp/agents/{agent_id}/reputation` | POST | Submit reputation feedback (10 CU) | | `/mcp/agents/{agent_id}/reputation` | GET | Read reputation summary (1 CU) | | `/mcp/agents/{agent_id}/reputation/status/{id}` | GET | Track submission status | | `/mcp/tools` | GET | List all available tools | ## Next Steps Learn about each available tool Practical usage examples