Connect the MultitaskAI MCP server to Goose
Goose is an open source agent with a CLI and a desktop app. Add MultitaskAI as a remote Streamable HTTP extension with an Authorization header.
Endpoint
Text
https://mcp.multitaskai.com
Steps
- Create an API key in your MultitaskAI account.
- Run goose configure, choose Add Extension, then Remote Extension (Streamable HTTP).
- Name the extension multitaskai and enter the endpoint URL as the Streamable HTTP endpoint URI.
- When asked whether to add custom headers, choose Yes, enter Authorization as the header name and Bearer YOUR_API_KEY as the value.
- Start a session with goose session and ask which MultitaskAI tools it can use.
Text
Streamable HTTP endpoint URI: https://mcp.multitaskai.com
Header name: Authorization
Header value: Bearer YOUR_API_KEY
Authentication
Goose sends your MultitaskAI API key in the Authorization header. Create a key in your account and use it in place of YOUR_API_KEY. Keep the key out of files you share or commit.
Text
Authorization: Bearer YOUR_API_KEY
Good to know
- Goose now belongs to the Agentic AI Foundation, and its docs are at goose-docs.ai.
- goose configure also asks for a timeout and a description; the defaults are fine.
- In the desktop app, open Extensions in the sidebar, choose Add custom extension, pick Streamable HTTP and add the header as a custom request header.
- goose info -v prints the header value in plain text, so do not share its output.
Official documentation
The Agentic AI Foundation MCP documentation covers Goose's own settings in detail. See the overview for the endpoint and authentication, and pricing for the daily free requests.