Best tools to use with Claude Code, Codex and Cursor
Add-ons that make coding agents more capable: current docs, GitHub access, a real browser, and apps built to work alongside Claude Code or Codex.
Ranked by score on our 100-point rubric (how we score). Scores are initial editorial estimates from public information, not hands-on tests. Pricing is labeled verified (checked on the vendor's official pricing page, with date) or unverified. Tools from more than one category appear here; each is scored within its own primary category.
Quick picks
| # | Tool | Tier | Score |
|---|---|---|---|
| 1 | GitHub MCP Server Official GitHub MCP server | S | 87 |
| 2 | Context7 Up-to-date library docs for coding agents | A | 84 |
| 3 | Playwright MCP MCP server for browser automation | A | 84 |
| 4 | HyperFrames Studio Video editor built for coding agents | A | 71 provisional |
| 5 | Rill Mac browser where Claude Code and Codex work beside you | B | 57 provisional |
The ranking
-
Lets agents read repos, manage issues and PRs, and inspect Actions through MCP; local or remote.
- Best for
- Your agent needs to work with GitHub issues, PRs and code.
- Skip it if
- You only use GitLab.
- Pricing
- Free and open source unverified editorial summary, not yet confirmed on an official pricing page
- Platforms
- MCP
-
MCP server and site from Upstash that feeds current, version-specific docs into your coding agent.
- Best for
- Your coding agent keeps hallucinating outdated APIs.
- Skip it if
- You work offline only.
- Pricing
- Free tier; paid plans for higher limits unverified editorial summary, not yet confirmed on an official pricing page
- Platforms
- MCP · API
-
Microsoft's MCP server that lets agents drive a real browser via Playwright accessibility snapshots.
- Best for
- You want Claude Code/Cursor to test and click through your web app.
- Skip it if
- You need a hosted, scalable browser fleet.
- Pricing
- Free and open source unverified editorial summary, not yet confirmed on an official pricing page
- Platforms
- MCP · CLI
-
HeyGen's HTML-based video editor for macOS and Linux where you and your agent (e.g. Claude Code, Codex) edit the same timeline; ships an open-source agent skill.
- Best for
- You make launch videos or explainers and live in a coding agent.
- Skip it if
- You want a traditional timeline editor.
- Pricing
- Free download; open-source skill unverified editorial summary, not yet confirmed on an official pricing page
- Platforms
- Mac · Linux · CLI
- 5
Rill🖱️ Browser agents provisional B57/100Mac browser where Claude Code and Codex work beside youFree beta WebKit browser for Apple-silicon Macs that runs on your existing Claude Code or Codex plan; send any page to an agent with ⌘E.
- Best for
- You vibe-code on a Mac and constantly copy pages into agent terminals.
- Skip it if
- You're on Windows/Linux or need a stable, mature browser.
- Pricing
- Free beta; uses your existing Claude Code/Codex plan unverified editorial summary, not yet confirmed on an official pricing page
- Platforms
- Mac
Head-to-head comparisons
FAQ
What is the best AI tool for extending Claude Code, Codex and other coding agents?
GitHub MCP Server ranks first with 87/100 (S-tier). Official GitHub MCP server. Use it when your agent needs to work with GitHub issues, PRs and code. Next in our ranking: Context7 (84/100, A-tier) and Playwright MCP (84/100, A-tier).
Which AI tools for extending Claude Code, Codex and other coding agents have a free tier?
In our pricing data, GitHub MCP Server (unverified), Context7 (unverified), Playwright MCP (unverified), HyperFrames Studio (unverified) and Rill (unverified) list a free tier. "Unverified" means it is an editorial summary we have not yet confirmed on the vendor's official pricing page, so check the vendor before relying on it.
Are there open-source options for extending Claude Code, Codex and other coding agents?
Yes. GitHub MCP Server, Context7, Playwright MCP and HyperFrames Studio are listed as open source or open weights. Check each project's license before commercial use.
How are these tools ranked?
Each tool is scored out of 100 on our public rubric: job fit (30), ease (15), value (15), momentum (15), openness and portability (10), trust and maturity (10) and a builder/gamer bonus (5). S-tier is 85+, A-tier 70–84, B-tier 55–69 and C-tier below 55. This guide mixes tools from more than one category, and scores are calibrated within each tool's primary category, so treat cross-category gaps as rough. Current scores are initial editorial estimates from public information, not hands-on tests, and sponsors can't buy points.