MOMO AI MCP User Guide - MOMO AI Docs

Overview

MOMO AI provides MCP (Model Context Protocol) protocol support. You can integrate MOMO AI agents into any MCP-compatible application through the MCP interface. MCP is a standardized protocol that allows AI models to interact with external tools and services.

MOMO AI's MCP service provides the following capabilities:

Discover Agents: Browse and search your purchased MOMO AI agents
Call Agents: Directly use agents through tool calling interface
Search Market: Search for more agents in MOMO AI marketplace
Purchase Credits: Purchase usage credits for specific agents

MCP Endpoints

MOMO AI provides two MCP endpoints:

Endpoint	Method	Purpose
`/api/mcp/messages`	POST	Handle MCP JSON-RPC requests
`/api/mcp/sse`	GET	Establish SSE long connection (for remote transport)

Authentication

All MCP requests require authentication via API key.

Authentication Header

x-momoai-key: YOUR_API_KEY

Or use standard Authorization header:

Authorization: Bearer YOUR_API_KEY

JSON-RPC Interface

Initialize Connection

Before using tools, you need to initialize the connection.

Request:

json

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "initialize",
  "params": {}
}

Response:

json

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "protocolVersion": "2024-11-05",
    "capabilities": {
      "tools": {}
    },
    "serverInfo": {
      "name": "momoai-hub",
      "version": "1.0.0"
    }
  }
}

Health Check

Request:

json

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "ping",
  "params": {}
}

Response:

json

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "status": "pong"
  }
}

Tool List

Call tools/list method to get available tools list.

Request:

json

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/list",
  "params": {}
}

Response:

json

{
  "jsonrpc": "2.0",
  "id": 2,
  "result": {
    "tools": [
      {
        "name": "search_momo_agents",
        "description": "Search for agents in MomoAI marketplace...",
        "inputSchema": {
          "type": "object",
          "properties": {
            "query": { "type": "string", "description": "Search query" }
          },
          "required": ["query"]
        }
      },
      {
        "name": "buy_agent_tokens",
        "description": "Purchase tokens for specified agent...",
        "inputSchema": {
          "type": "object",
          "properties": {
            "agent_id": { "type": "number", "description": "Agent ID" },
            "token_amount": { "type": "number", "description": "Purchase amount" }
          },
          "required": ["agent_id", "token_amount"]
        }
      },
      {
        "name": "momo_agent_58",
        "description": "Translation Assistant (deepseek-chat) | Balance: 10000 tokens | Price: 1 credits / 1000 tokens | Professional translation agent...",
        "inputSchema": {
          "type": "object",
          "properties": {
            "prompt": { "type": "string", "description": "Instruction or question for the agent" }
          },
          "required": ["prompt"]
        }
      }
    ]
  }
}

Available Tools Description

Tool Name	Function
`search_momo_agents`	Search for agents in MOMO AI marketplace
`buy_agent_tokens`	Purchase token credits for specified agent
`momo_agent_{id}`	Call specific agent (displayed as list of purchased agents)

Tool Calls

Search Agents

Request:

json

{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "tools/call",
  "params": {
    "name": "search_momo_agents",
    "arguments": {
      "query": "translation"
    }
  }
}

Response:

json

{
  "jsonrpc": "2.0",
  "id": 3,
  "result": {
    "content": [
      {
        "type": "text",
        "text": "{\n  \"query\": \"translation\",\n  \"count\": 5,\n  \"agents\": [\n    {\n      \"id\": 58,\n      \"name\": \"Translation Assistant\",\n      \"description\": \"Professional translation agent, supports multilingual translation...\",\n      \"price\": 1,\n      \"priceUnit\": \"1000\",\n      \"baseModel\": \"deepseek-chat\",\n      \"tags\": [\"translation\", \"language\"],\n      \"hasPurchased\": true,\n      \"availableTokens\": 10000\n    }\n  ],\n  \"tip\": \"Use buy_agent_tokens tool to purchase tokens before using the agent\"\n}"
      }
    ]
  }
}

Purchase Token Credits

Request:

json

{
  "jsonrpc": "2.0",
  "id": 4,
  "method": "tools/call",
  "params": {
    "name": "buy_agent_tokens",
    "arguments": {
      "agent_id": 58,
      "token_amount": 10000
    }
  }
}

Response:

json

{
  "jsonrpc": "2.0",
  "id": 4,
  "result": {
    "content": [
      {
        "type": "text",
        "text": "Successfully purchased 10000 tokens for Agent 58"
      }
    ]
  }
}

Call Agent

Request:

json

{
  "jsonrpc": "2.0",
  "id": 5,
  "method": "tools/call",
  "params": {
    "name": "momo_agent_58",
    "arguments": {
      "prompt": "Translate the following Chinese to English: Hello, World!"
    }
  }
}

Response:

json

{
  "jsonrpc": "2.0",
  "id": 5,
  "result": {
    "content": [
      {
        "type": "text",
        "text": "Hello, World!"
      }
    ]
  }
}

Error Response Example

Tool call failed:

json

{
  "jsonrpc": "2.0",
  "id": 6,
  "result": {
    "content": [
      {
        "type": "text",
        "text": "Error: Insufficient token balance, please purchase credits first"
      }
    ],
    "isError": true
  }
}

Complete Usage Examples

Python Example

python

import requests
import json

API_KEY = "YOUR_API_KEY"
BASE_URL = "https://hub.momoai.pro/api/mcp"

headers = {
    "Content-Type": "application/json",
    "x-momoai-key": API_KEY
}

def mcp_request(method, params=None):
    payload = {
        "jsonrpc": "2.0",
        "id": 1,
        "method": method,
        "params": params or {}
    }
    response = requests.post(
        f"{BASE_URL}/messages",
        headers=headers,
        json=payload
    )
    return response.json()

# 1. Initialize
print("=== Initialize ===")
result = mcp_request("initialize")
print(json.dumps(result, indent=2, ensure_ascii=False))

# 2. Get tool list
print("\n=== Tool List ===")
result = mcp_request("tools/list")
for tool in result["result"]["tools"]:
    print(f"- {tool['name']}")

# 3. Search agents
print("\n=== Search Agents ===")
result = mcp_request("tools/call", {
    "name": "search_momo_agents",
    "arguments": {"query": "programming"}
})
print(json.dumps(result, indent=2, ensure_ascii=False))

# 4. Call agent
print("\n=== Call Agent ===")
result = mcp_request("tools/call", {
    "name": "momo_agent_58",
    "arguments": {"prompt": "Hello, please introduce yourself"}
})
print(result["result"]["content"][0]["text"])

Node.js Example

javascript

const fetch = require('node-fetch');

const API_KEY = "YOUR_API_KEY";
const BASE_URL = "https://hub.momoai.pro/api/mcp";

async function mcpRequest(method, params = {}) {
  const response = await fetch(`${BASE_URL}/messages`, {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'x-momoai-key': API_KEY
    },
    body: JSON.stringify({
      jsonrpc: '2.0',
      id: 1,
      method,
      params
    })
  });
  return response.json();
}

async function main() {
  // 1. Initialize
  console.log('=== Initialize ===');
  const init = await mcpRequest('initialize');
  console.log(JSON.stringify(init, null, 2));

  // 2. Get tool list
  console.log('\n=== Tool List ===');
  const tools = await mcpRequest('tools/list');
  tools.result.tools.forEach(tool => {
    console.log(`- ${tool.name}`);
  });

  // 3. Search agents
  console.log('\n=== Search Agents ===');
  const search = await mcpRequest('tools/call', {
    name: 'search_momo_agents',
    arguments: { query: 'data analysis' }
  });
  console.log(search.result.content[0].text);

  // 4. Call agent
  console.log('\n=== Call Agent ===');
  const result = await mcpRequest('tools/call', {
    name: 'momo_agent_58',
    arguments: { prompt: 'Introduce yourself in one sentence' }
  });
  console.log(result.result.content[0].text);
}

main().catch(console.error);

cURL Example

bash

# 1. Initialize
curl -X POST "https://hub.momoai.pro/api/mcp/messages" \
  -H "Content-Type: application/json" \
  -H "x-momoai-key: YOUR_API_KEY" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "initialize",
    "params": {}
  }'

# 2. Get tool list
curl -X POST "https://hub.momoai.pro/api/mcp/messages" \
  -H "Content-Type: application/json" \
  -H "x-momoai-key: YOUR_API_KEY" \
  -d '{
    "jsonrpc": "2.0",
    "id": 2,
    "method": "tools/list",
    "params": {}
  }'

# 3. Search agents
curl -X POST "https://hub.momoai.pro/api/mcp/messages" \
  -H "Content-Type: application/json" \
  -H "x-momoai-key: YOUR_API_KEY" \
  -d '{
    "jsonrpc": "2.0",
    "id": 3,
    "method": "tools/call",
    "params": {
      "name": "search_momo_agents",
      "arguments": {
        "query": "Python"
      }
    }
  }'

# 4. Call agent
curl -X POST "https://hub.momoai.pro/api/mcp/messages" \
  -H "Content-Type: application/json" \
  -H "x-momoai-key: YOUR_API_KEY" \
  -d '{
    "jsonrpc": "2.0",
    "id": 4,
    "method": "tools/call",
    "params": {
      "name": "momo_agent_58",
      "arguments": {
        "prompt": "Explain what a REST API is"
      }
    }
  }'

SSE Remote Transport

For scenarios requiring long connections, you can use the SSE (Server-Sent Events) endpoint.

Establish Connection

GET /api/mcp/sse?key=YOUR_API_KEY

Request Headers:

x-momoai-key: YOUR_API_KEY

Response:

Content-Type: text/event-stream

data: {"jsonrpc":"2.0","method":"connection/established","params":{"connectionId":"user123_1700000000000","serverInfo":{"name":"momoai-hub","version":"1.0.0"}}}

: heartbeat

Connection Description

Connection Establishment: Server returns connection/established event with connection ID
Heartbeat Detection: Sends heartbeat every 30 seconds (: heartbeat) to keep connection alive
Connection Closure: Server automatically cleans up resources when client disconnects

Error Handling

Error Codes

Error Code	Description
-32600	Invalid request (missing or invalid API key)
-32601	Method not found
-32603	Server internal error

Error Response Format

json

{
  "jsonrpc": "2.0",
  "id": 1,
  "error": {
    "code": -32600,
    "message": "Missing API key"
  }
}

Common Errors

Authentication failed:

json

{
  "jsonrpc": "2.0",
  "error": {
    "code": -32600,
    "message": "Invalid API key"
  }
}

Insufficient token balance:

json

{
  "jsonrpc": "2.0",
  "result": {
    "content": [
      {
        "type": "text",
        "text": "Error: You don't have usage credits for Agent 58. Please purchase tokens at https://hub.momoai.pro first."
      }
    ],
    "isError": true
  }
}

Tool Description

search_momo_agents

Search for agents in MOMO AI marketplace.

Parameters:

Parameter	Type	Required	Description
`query`	string	Yes	Search keyword

Returns: JSON result containing agent ID, name, description, price, tags, etc.

buy_agent_tokens

Purchase usage credits for specified agent.

Parameters:

Parameter	Type	Required	Description
`agent_id`	number	Yes	Agent ID
`token_amount`	number	Yes	Number of tokens to purchase

Returns: Purchase result message.

momo_agent_{id}

Call purchased MOMO AI agent.

Parameters:

Parameter	Type	Required	Description
`prompt`	string	Yes	Instruction or question for the agent

Note: This tool only displays agents you have purchased (maximum 10). Agents not purchased must have credits purchased before use.

Usage Limits

Tool List Limit: Maximum 10 purchased agents displayed
Search Result Limit: Maximum 10 results per search
Authentication Requirement: All requests must include valid API key

Using in AI Applications

MCP protocol is widely used in AI assistant applications such as Claude Desktop, Cursor, etc. You can add MOMO AI as an MCP server in these applications' configurations.

Claude Desktop Configuration Example

Add to claude_desktop_config.json:

json

{
  "mcpServers": {
    "momoai": {
      "command": "python",
      "args": ["-m", "mcp_client.py", "https://hub.momoai.pro"],
      "env": {
        "MOMOAI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Cursor Configuration Example

Add MCP server configuration in Cursor settings, pointing to https://hub.momoai.pro.

FAQ

Q: Why is my tool list empty? A: You need to purchase agent credits on the MOMO AI platform first. After purchase, agents will automatically appear in the tool list.

Q: How to view agents I have purchased? A: Log in to MOMO AI platform, go to Account → Token Management page to view.

Q: What to do when prompted about insufficient balance when calling agent? A: Use buy_agent_tokens tool to purchase credits for that agent, or purchase on MOMO AI platform.

Q: Does it support streaming response? A: Current version does not support streaming response; tool calls return complete results.

Q: Can I call multiple agents simultaneously? A: Yes, MCP supports concurrent calls to multiple different tools.

Technical Support

If you have any questions, please contact MOMO AI official:

Email: partnership@momoai.wecom.work
Business: 13716105018
Technical Support: 13815831618