Cross-LLM MCP Server

A Model Context Protocol (MCP) server that provides access to multiple Large Language Model (LLM) APIs including ChatGPT, Claude, and DeepSeek. This allows you to call different LLMs from within any MCP-compatible client and combine their responses.

Features

This MCP server offers five specialized tools for interacting with different LLM providers:

🤖 Individual LLM Tools

`call-chatgpt`

Call OpenAI's ChatGPT API with a prompt.

Input:

prompt (string): The prompt to send to ChatGPT
model (optional, string): ChatGPT model to use (default: gpt-4)
temperature (optional, number): Temperature for response randomness (0-2, default: 0.7)
max_tokens (optional, number): Maximum tokens in response (default: 1000)

Output:

ChatGPT response with model information and token usage statistics

Example:

ChatGPT Response
Model: gpt-4

Here's a comprehensive explanation of quantum computing...

---
Usage:
- Prompt tokens: 15
- Completion tokens: 245
- Total tokens: 260

`call-claude`

Call Anthropic's Claude API with a prompt.

Input:

prompt (string): The prompt to send to Claude
model (optional, string): Claude model to use (default: claude-3-sonnet-20240229)
temperature (optional, number): Temperature for response randomness (0-1, default: 0.7)
max_tokens (optional, number): Maximum tokens in response (default: 1000)

Output:

Claude response with model information and token usage statistics

`call-deepseek`

Call DeepSeek API with a prompt.

Input:

prompt (string): The prompt to send to DeepSeek
model (optional, string): DeepSeek model to use (default: deepseek-chat)
temperature (optional, number): Temperature for response randomness (0-2, default: 0.7)
max_tokens (optional, number): Maximum tokens in response (default: 1000)

Output:

DeepSeek response with model information and token usage statistics

🔄 Combined Tools

`call-all-llms`

Call all available LLM APIs (ChatGPT, Claude, DeepSeek) with the same prompt and get combined responses.

Input:

prompt (string): The prompt to send to all LLMs
temperature (optional, number): Temperature for response randomness (0-2, default: 0.7)
max_tokens (optional, number): Maximum tokens in response (default: 1000)

Output:

Combined responses from all LLMs with individual model information and usage statistics
Summary of successful responses and total tokens used

Example:

Multi-LLM Response

Prompt: Explain quantum computing in simple terms

---

## CHATGPT

Model: gpt-4

Quantum computing is like having a super-powered computer...

---

## CLAUDE

Model: claude-3-sonnet-20240229

Quantum computing represents a fundamental shift...

---

## DEEPSEEK

Model: deepseek-chat

Quantum computing harnesses the principles of quantum mechanics...

---

Summary:
- Successful responses: 3/3
- Total tokens used: 1250

`call-llm`

Call a specific LLM provider by name.

Input:

provider (string): The LLM provider to call ("chatgpt", "claude", or "deepseek")
prompt (string): The prompt to send to the LLM
model (optional, string): Model to use (uses provider default if not specified)
temperature (optional, number): Temperature for response randomness (0-2, default: 0.7)
max_tokens (optional, number): Maximum tokens in response (default: 1000)

Output:

Response from the specified LLM with model information and usage statistics

Installation

Clone this repository:

git clone <repository-url>
cd cross-llm-mcp

Install dependencies:

npm install

Set up environment variables:

cp env.example .env

Edit the .env file with your API keys:

# OpenAI/ChatGPT API Key
OPENAI_API_KEY=your_openai_api_key_here

# Anthropic/Claude API Key
ANTHROPIC_API_KEY=your_anthropic_api_key_here

# DeepSeek API Key
DEEPSEEK_API_KEY=your_deepseek_api_key_here

# Default models for each provider
DEFAULT_CHATGPT_MODEL=gpt-4
DEFAULT_CLAUDE_MODEL=claude-3-sonnet-20240229
DEFAULT_DEEPSEEK_MODEL=deepseek-chat

Build the project:

npm run build

Getting API Keys

OpenAI/ChatGPT

Visit OpenAI Platform
Sign up or log in to your account
Create a new API key
Add it to your .env file as OPENAI_API_KEY

Anthropic/Claude

Visit Anthropic Console
Sign up or log in to your account
Create a new API key
Add it to your .env file as ANTHROPIC_API_KEY

DeepSeek

Visit DeepSeek Platform
Sign up or log in to your account
Create a new API key
Add it to your .env file as DEEPSEEK_API_KEY

Usage

Running the Server

Start the MCP server:

npm start

The server runs on stdio and can be connected to any MCP-compatible client.

Example Queries

Here are some example queries you can make with this MCP server:

Call ChatGPT

{
  "tool": "call-chatgpt",
  "arguments": {
    "prompt": "Explain quantum computing in simple terms",
    "temperature": 0.7,
    "max_tokens": 500
  }
}

Call Claude

{
  "tool": "call-claude",
  "arguments": {
    "prompt": "What are the benefits of renewable energy?",
    "model": "claude-3-sonnet-20240229"
  }
}

Call All LLMs

{
  "tool": "call-all-llms",
  "arguments": {
    "prompt": "Write a short poem about artificial intelligence",
    "temperature": 0.8
  }
}

Call Specific LLM

{
  "tool": "call-llm",
  "arguments": {
    "provider": "deepseek",
    "prompt": "Explain machine learning algorithms",
    "max_tokens": 800
  }
}

Use Cases

1. Multi-Perspective Analysis

Use call-all-llms to get different perspectives on the same topic from multiple AI models.

2. Model Comparison

Compare responses from different LLMs to understand their strengths and weaknesses.

3. Redundancy and Reliability

If one LLM is unavailable, you can still get responses from other providers.

4. Cost Optimization

Choose the most cost-effective LLM for your specific use case.

5. Quality Assurance

Cross-reference responses from multiple models to validate information.

API Endpoints

This MCP server uses the following API endpoints:

OpenAI: https://api.openai.com/v1/chat/completions
Anthropic: https://api.anthropic.com/v1/messages
DeepSeek: https://api.deepseek.com/v1/chat/completions

Error Handling

The server includes comprehensive error handling with detailed messages:

Missing API Key

**ChatGPT Error:** OpenAI API key not configured

Invalid API Key

**Claude Error:** Claude API error: Invalid API key - please check your Anthropic API key

Rate Limiting

**DeepSeek Error:** DeepSeek API error: Rate limit exceeded - please try again later

Payment Issues

**ChatGPT Error:** ChatGPT API error: Payment required - please check your OpenAI billing

Network Issues

**Claude Error:** Claude API error: Network timeout

Configuration

Environment Variables

OPENAI_API_KEY: Your OpenAI API key
ANTHROPIC_API_KEY: Your Anthropic API key
DEEPSEEK_API_KEY: Your DeepSeek API key
DEFAULT_CHATGPT_MODEL: Default ChatGPT model (default: gpt-4)
DEFAULT_CLAUDE_MODEL: Default Claude model (default: claude-3-sonnet-20240229)
DEFAULT_DEEPSEEK_MODEL: Default DeepSeek model (default: deepseek-chat)

Supported Models

ChatGPT Models

gpt-4
gpt-4-turbo
gpt-3.5-turbo
And other OpenAI models

Claude Models

claude-3-sonnet-20240229
claude-3-opus-20240229
claude-3-haiku-20240307
And other Anthropic models

DeepSeek Models

deepseek-chat
deepseek-coder
And other DeepSeek models

Project Structure

cross-llm-mcp/
├── src/
│   ├── index.ts          # Main MCP server with all 5 tools
│   ├── types.ts          # TypeScript type definitions
│   └── llm-clients.ts    # LLM API client implementations
├── build/                # Compiled JavaScript output
├── env.example           # Environment variables template
├── example-usage.md      # Detailed usage examples
├── package.json          # Project dependencies and scripts
└── README.md            # This file

Dependencies

@modelcontextprotocol/sdk - MCP SDK for server implementation
superagent - HTTP client for API requests
zod - Schema validation for tool parameters
dotenv - Environment variable management

Development

Building the Project

npm run build

Adding New LLM Providers

To add a new LLM provider:

Add the provider type to src/types.ts
Implement the client in src/llm-clients.ts
Add the tool to src/index.ts
Update the callAllLLMs method to include the new provider

Troubleshooting

Common Issues

Server won't start

Check that all dependencies are installed: npm install
Verify the build was successful: npm run build
Ensure the .env file exists and has valid API keys

API errors

Verify your API keys are correct and active
Check your API usage limits and billing status
Ensure you're using supported model names

No responses

Check that at least one API key is configured
Verify network connectivity
Look for error messages in the response

Debug Mode

For debugging, you can run the server directly:

node build/index.js

License

This project is licensed under the MIT License - see the LICENSE.md file for details.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Support

If you encounter any issues or have questions, please:

Check the troubleshooting section above
Review the error messages for specific guidance
Ensure your API keys are properly configured
Verify your network connectivity

This server cannot be installed

security - not tested

license - permissive license

quality - not tested

How are these scores calculated?

A Model Context Protocol server that provides unified access to multiple LLM APIs including ChatGPT, Claude, and DeepSeek, allowing users to call different LLMs from MCP-compatible clients and combine their responses.

Related MCP Servers

mcp-lancedb
adiom-data
-
security
A
license
-
quality
A Model Context Protocol (MCP) server that enables LLMs to interact directly the documents that they have on-disk through agentic RAG and hybrid search in LanceDB. Ask LLMs questions about the dataset as a whole or about specific documents.
Last updated -
4
63
TypeScript
MIT License
microCMS MCP Server
SpringMT
-
security
A
license
-
quality
A Model Context Protocol (MCP) compliant server that allows Large Language Models (LLMs) to search and retrieve content from microCMS APIs.
Last updated -
TypeScript
MIT License
URL Fetch MCP
aelaguiz
A
security
A
license
A
quality
A Model Context Protocol (MCP) server that enables Claude or other LLMs to fetch content from URLs, supporting HTML, JSON, text, and images with configurable request parameters.
Last updated -
3
1
Python
MIT License
OpenAPI MCP Server
rahgadda
-
security
A
license
-
quality
A Model Context Protocol Server that enables LLMs to interact with and execute REST API calls through natural language prompts, supporting GET/PUT/POST/PATCH operations on configured APIs.
Last updated -
6
Python
Apache 2.0

View all related MCP servers