MCP server · Chat
Outsource MCP server
by gwbischof
Let your AI ask other AI models to write text or make images for you.
This is a small helper that lets your AI hand a job to a different AI model. You can ask for text from OpenAI, Anthropic, Google and many others, or ask OpenAI to draw an image. It is handy if you want to compare answers from different models or get a picture made without leaving your chat.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you using the brain it already has. An MCP server is a small helper program that gives your AI a new skill or a connection to another service. This one connects your AI to other AI providers, so when you ask for something, your AI can pass the request along and bring the answer back. You stay in your normal chat the whole time.
What this MCP server does
You type a request in your chat, like asking for a poem or a picture. Your AI notices this helper can do that, and it sends the job over with three simple details: which company, which model, and what you want. The helper talks to that company's service using your key, waits for the result, and hands it back. Your AI then shows you the text or the image link right in the conversation.
Click to zoomWhat you can do with it
- Get text written by a model from OpenAI, Anthropic, Google, or others
- Compare answers by asking two different models the same question
- Generate an image with DALL-E 3 or DALL-E 2 and get a link to it
- Pick a specific model by name, like gpt-4o-mini or claude-3-5-sonnet
- Use a local model through Ollama if you run one on your computer
- Try smaller or cheaper models for quick drafts
Try asking your AI
- “Ask OpenAI's gpt-4o-mini to write a haiku about coding”
- “Ask Anthropic's claude-3-5-sonnet to explain quantum computing in simple terms”
- “Ask Google's gemini-2.0-flash-exp for a chocolate chip cookie recipe”
- “Use DALL-E 3 to make an image of a serene Japanese garden with cherry blossoms”
What it gives back to you
For text requests, you get the model's answer as normal chat text. For image requests, you get a web link to the generated picture, which you can open or share. If something goes wrong, like a missing key or an unknown model name, you get a short error message explaining it.
Before you start
What you need
- An MCP client that supports adding servers, like Claude Desktop or Cline
- The uv tool installed on your computer (it runs the helper)
- At least one API key from a provider you want to use, like OpenAI or Anthropic (an API key is a kind of password for apps; the provider's website gives you one)
- Internet access, unless you only use a local Ollama model
Good to know
Each request uses your provider API keys and may cost money on those accounts, so keep an eye on your usage and credits.
Install it with your AI
Add Outsource MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Outsource MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
People who want to try different AI models or make images without leaving their chat, and who do not mind pasting in an API key.
