Outsource MCP server for AI agents

Outsource MCP is a server that enables AI applications to access multiple AI model providers through a unified interface using the Model Context Protocol (MCP). It supports 20+ providers, including OpenAI, Anthropic, Google, and many others, allowing you to generate text and images with a consistent API structure.

Installation and Configuration

To use Outsource MCP, you need to add its configuration to your MCP client. The setup uses uvx to run the server directly from GitHub:

{
  "mcpServers": {
    "outsource-mcp": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/gwbischof/outsource-mcp.git", "outsource-mcp"],
      "env": {
        "OPENAI_API_KEY": "your-openai-key",
        "ANTHROPIC_API_KEY": "your-anthropic-key",
        "GOOGLE_API_KEY": "your-google-key"
        // Add only the API keys you need
      }
    }
  }
}

You only need to include API keys for providers you intend to use. For example, if you only plan to use OpenAI's models, you can include just the OPENAI_API_KEY.

Using Outsource MCP

Once configured, you can use two main tools with your MCP client:

Text Generation

The outsource_text tool generates text responses using various AI models:

# Example with OpenAI
provider: openai
model: gpt-4o-mini
prompt: Write a haiku about coding

# Example with Anthropic
provider: anthropic
model: claude-3-5-sonnet-20241022
prompt: Explain quantum computing in simple terms

Image Generation

The outsource_image tool creates images (currently only supported with OpenAI's DALL-E models):

# Using DALL-E 3
provider: openai
model: dall-e-3
prompt: A serene Japanese garden with cherry blossoms

# Using DALL-E 2
provider: openai
model: dall-e-2
prompt: A futuristic cityscape at sunset

Supported Providers and Models

Core Providers

OpenAI (openai) - GPT-4, GPT-3.5, DALL-E, etc.
Anthropic (anthropic) - Claude 3.5, Claude 3, etc.
Google (google) - Gemini Pro, Gemini Flash, etc.
Groq (groq) - Llama 3, Mixtral, etc.
DeepSeek (deepseek) - DeepSeek Chat & Coder
xAI (xai) - Grok models
Perplexity (perplexity) - Sonar models

Additional Providers

Cohere (cohere), Mistral AI (mistral), NVIDIA (nvidia)
HuggingFace (huggingface), Ollama (ollama), Fireworks AI (fireworks)
OpenRouter (openrouter), Together AI (together), Cerebras (cerebras)
DeepInfra (deepinfra), SambaNova (sambanova)

Enterprise Providers

AWS Bedrock (aws or bedrock), Azure AI (azure), IBM WatsonX (ibm or watsonx)
LiteLLM (litellm), Vercel v0 (vercel or v0), Meta Llama (meta)

Environment Variables

Each provider requires its own API key environment variable:

Provider	Environment Variable	Example
OpenAI	`OPENAI_API_KEY`	sk-...
Anthropic	`ANTHROPIC_API_KEY`	sk-ant-...
Google	`GOOGLE_API_KEY`	AIza...
Groq	`GROQ_API_KEY`	gsk_...
Ollama	`OLLAMA_HOST`	http://localhost:11434

Troubleshooting

If you encounter issues:

"Error: Unknown provider" - Verify you're using a supported provider name
API errors - Check that your API key is correct and has access to the requested model
"No image was generated" - Try a simpler prompt or different model
Environment variables not working - Restart your MCP client and verify configuration

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "outsource-mcp" '{"command":"uvx","args":["--from","git+https://github.com/gwbischof/outsource-mcp.git","outsource-mcp"],"env":{"OPENAI_API_KEY":"your-openai-key","ANTHROPIC_API_KEY":"your-anthropic-key","GOOGLE_API_KEY":"your-google-key","GROQ_API_KEY":"your-groq-key","DEEPSEEK_API_KEY":"your-deepseek-key","XAI_API_KEY":"your-xai-key","PERPLEXITY_API_KEY":"your-perplexity-key","COHERE_API_KEY":"your-cohere-key","FIREWORKS_API_KEY":"your-fireworks-key","HUGGINGFACE_API_KEY":"your-huggingface-key","MISTRAL_API_KEY":"your-mistral-key","NVIDIA_API_KEY":"your-nvidia-key","OLLAMA_HOST":"http://localhost:11434","OPENROUTER_API_KEY":"your-openrouter-key","TOGETHER_API_KEY":"your-together-key","CEREBRAS_API_KEY":"your-cerebras-key","DEEPINFRA_API_KEY":"your-deepinfra-key","SAMBANOVA_API_KEY":"your-sambanova-key"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "outsource-mcp": {
            "command": "uvx",
            "args": [
                "--from",
                "git+https://github.com/gwbischof/outsource-mcp.git",
                "outsource-mcp"
            ],
            "env": {
                "OPENAI_API_KEY": "your-openai-key",
                "ANTHROPIC_API_KEY": "your-anthropic-key",
                "GOOGLE_API_KEY": "your-google-key",
                "GROQ_API_KEY": "your-groq-key",
                "DEEPSEEK_API_KEY": "your-deepseek-key",
                "XAI_API_KEY": "your-xai-key",
                "PERPLEXITY_API_KEY": "your-perplexity-key",
                "COHERE_API_KEY": "your-cohere-key",
                "FIREWORKS_API_KEY": "your-fireworks-key",
                "HUGGINGFACE_API_KEY": "your-huggingface-key",
                "MISTRAL_API_KEY": "your-mistral-key",
                "NVIDIA_API_KEY": "your-nvidia-key",
                "OLLAMA_HOST": "http://localhost:11434",
                "OPENROUTER_API_KEY": "your-openrouter-key",
                "TOGETHER_API_KEY": "your-together-key",
                "CEREBRAS_API_KEY": "your-cerebras-key",
                "DEEPINFRA_API_KEY": "your-deepinfra-key",
                "SAMBANOVA_API_KEY": "your-sambanova-key"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

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

2. Add this to your configuration file:

{
    "mcpServers": {
        "outsource-mcp": {
            "command": "uvx",
            "args": [
                "--from",
                "git+https://github.com/gwbischof/outsource-mcp.git",
                "outsource-mcp"
            ],
            "env": {
                "OPENAI_API_KEY": "your-openai-key",
                "ANTHROPIC_API_KEY": "your-anthropic-key",
                "GOOGLE_API_KEY": "your-google-key",
                "GROQ_API_KEY": "your-groq-key",
                "DEEPSEEK_API_KEY": "your-deepseek-key",
                "XAI_API_KEY": "your-xai-key",
                "PERPLEXITY_API_KEY": "your-perplexity-key",
                "COHERE_API_KEY": "your-cohere-key",
                "FIREWORKS_API_KEY": "your-fireworks-key",
                "HUGGINGFACE_API_KEY": "your-huggingface-key",
                "MISTRAL_API_KEY": "your-mistral-key",
                "NVIDIA_API_KEY": "your-nvidia-key",
                "OLLAMA_HOST": "http://localhost:11434",
                "OPENROUTER_API_KEY": "your-openrouter-key",
                "TOGETHER_API_KEY": "your-together-key",
                "CEREBRAS_API_KEY": "your-cerebras-key",
                "DEEPINFRA_API_KEY": "your-deepinfra-key",
                "SAMBANOVA_API_KEY": "your-sambanova-key"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect