AI Integrations
Deploy to Buddy with your favorite AI coding agents - pipelines, sandboxes, domains and logs from your terminal or editor.
Buddy's Remote MCP Server is available.
GitHub Copilot + Buddy
GitHub Copilot is GitHub's AI pair programmer, available in your editor and across GitHub. In agent mode it works with the full context of your project - reading across the codebase, running commands, editing files, and opening pull requests. Paired with Buddy, it deploys your project, triggers and monitors pipelines, ships changes across environments, and digs through build output when something needs fixing.
Copilot's agent mode goes past inline suggestions: it runs commands and opens pull requests, so Buddy usually enters right after the PR. From there the agent can trigger the pipeline that validates its own change and read the logs when it fails.
Quick start
1 Install the Buddy CLInpm install -g bdy
2 Log in to Buddybdy login
3 Link your projectbdy proj link
4 Install the Buddy skillnpx skills add buddy/buddy-plugin
5 Start Copilotcopilot
Open Copilot agent mode in your editor, or launch the GitHub Copilot CLI. The Buddy skill teaches the agent how to drive Buddy through the CLI.
Example prompts
- “Create a Next.js app and deploy it to production”
- “Deploy my app, set up a CDN, and buy and configure a domain with SSL”
- “Check the last few CI pipeline runs for failures, read the logs, and fix the failing tests”
- “Check my app logs and open issues based on what you find”
Available commands
Connect MCP
Buddy's remote MCP server exposes over 90 tools, so Copilot can run pipelines, manage deployments, and read logs straight through the API:
bashcopilot mcp add --transport http buddy https://mcp.buddy.works/mcp$
You can also add it to ~/.copilot/mcp-config.json by hand. Point it at the endpoint closest to your workspace region - mcp.buddy.works, mcp.eu.buddy.works or mcp.asia.buddy.works - and use the ?tools= parameter to narrow the exposed tool categories.