How to add MCP servers to Cursor
How to add MCP servers to Cursor: project and global mcp.json files, remote and local servers, OAuth sign-in, secrets from env vars and tool approvals.
A coding agent is only as good as what it knows and how you work with it. The same model writes very different code depending on the instructions file in the repository, the tools it can call and how the task is framed.
These guides are for engineers who use Claude Code, Cursor, Codex, OpenCode, GitHub Copilot or Pi every day and want better results from them. Each one names the agent it covers and shows the commands, files and settings to copy from that agent's own docs: installing it, adding MCP servers, writing instructions it follows, and the workflows that hold up on a real codebase.
How Polylane handles this: Polylane for DevOps.
How to add MCP servers to Cursor: project and global mcp.json files, remote and local servers, OAuth sign-in, secrets from env vars and tool approvals.
How to add MCP servers to GitHub Copilot in VS Code: workspace and user mcp.json, HTTP and stdio servers, MCP: Add Server and confirming tool calls.
How to use Claude Code: install it, write a CLAUDE.md, pick a permission mode, steer it mid-task, script it with -p and connect it to your tools with MCP.
How to use Codex CLI: install it, sign in, write an AGENTS.md, set permissions, resume sessions, script it with codex exec and add MCP servers.
How to use OpenCode: install it, connect a provider, write an AGENTS.md with /init, switch between Plan and Build, undo changes and add MCP servers.
How to use the Pi coding agent: install it, sign in with /login, pick a model, branch sessions with /tree and /fork, compact context and script it with -p.