Files
coder/docs/ai-coder/best-practices.md
Edward Angert 5c16079aff docs: add more specific steps and information about oidc refresh tokens (#18336)
closes https://github.com/coder/coder/issues/18307

relates to https://github.com/coder/coder/pull/18318

preview:
-
[refresh-tokens](https://coder.com/docs/@18307-refresh-tokens/admin/users/oidc-auth/refresh-tokens)
-
[configuring-okta](https://coder.com/docs/@18307-refresh-tokens/tutorials/configuring-okta)
~(not sure why @Emyrk 's photo is so huge there though)~ ✔️
- [x] removed from
[idp-sync](https://coder.com/docs/@18307-refresh-tokens/admin/users/idp-sync)

to do:
- move keycloak
- add ping federate and azure
- edit text (possibly placeholders for now - I want to see how it all
relates and edit it again. right now, there's a note about the same
thing in every section in way that's not super helpful/necessary)
- ~convert some paragraphs to OL~ calling this out of scope for now

---------

Co-authored-by: EdwardAngert <17991901+EdwardAngert@users.noreply.github.com>
2025-06-16 13:18:55 -04:00

2.7 KiB

Model Context Protocols (MCP) and adding AI tools

Note

This functionality is in beta and is evolving rapidly.

When using any AI tool for development, exercise a level of caution appropriate to your use case and environment. Always review AI-generated content before using it in critical systems.

Join our Discord channel or contact us to get help or share feedback.

Overview

Coder templates should be pre-equipped with the tools and dependencies needed for development. With AI Agents, this is no exception.

Prerequisites

Best Practices

  • Use the most capable ML models you have access to in order to evaluate Agent performance.

  • Set a system prompt with the AI_SYSTEM_PROMPT environment in your template

  • Within your repositories, write a .cursorrules, CLAUDE.md or similar file to guide the agent's behavior.

  • To read issue descriptions or pull request comments, install the proper CLI (e.g. gh) in your image/template.

  • Ensure your template is truly pre-configured for development without manual intervention (e.g. repos are cloned, dependencies are built, secrets are added/mocked, etc.).

    Note: External authentication can be helpful to authenticate with third-party services such as GitHub or JFrog.

  • Give your agent the proper tools via MCP to interact with your codebase and related services.

  • Read our recommendations on securing agents to avoid surprises.

Adding Tools via MCP

Model Context Protocol (MCP) is an emerging standard for adding tools to your agents.

Follow the documentation for your agent to learn how to configure MCP servers. See modelcontextprotocol/servers to browse open source MCP servers.

Our Favorite MCP Servers

In internal testing, we have seen significant improvements in agent performance when these tools are added via MCP.

  • Playwright: Instruct your agent to open a browser, and check its work by viewing output and taking screenshots.
  • desktop-commander: Instruct your agent to run long-running tasks (e.g. npm run dev) in the background instead of blocking the main thread.

Next Steps