Get started Dashboard

Coding agents. How to get the most out of Claude Code, Cursor, Codex and the other coding agents: setup, MCP servers, rules files and day-to-day workflows.

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

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.

Boris Tane

More guides

How to use Claude Code: a practical guide

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.

Boris Tane

How to use the Pi coding agent

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.

Boris Tane

Nobody should be on-call. Polylane watches your infra, finds what broke, and writes the fix.

Get started for free