GitHub
Code hostingIndependent review. Unpaid; no partnership with GitHub. Based on public documentation and research. Trademarks identify their owners’ products. Disclosure.
Hosts Git repositories with pull-request reviews, Issues, Projects and Actions for CI/CD. The official GitHub MCP server lets AI agents read repos, manage issues and PRs, and watch Actions.
The five-point review
Judgment, not a score. Documentation checked 2026-10-18.
- Value
- Hosts Git repositories with pull-request reviews, Issues, Projects and Actions for CI/CD. The official GitHub MCP server lets AI agents read repos, manage issues and PRs, and watch Actions.
- Differentiation
- Documented fit: Version control for every project; Deploy hooks into hosting. Uniqueness is not established.
- Replaceability and switching
- No substitute or migration assessment recorded. Check export and switching costs.
- Ease and technical aptitude
- Consider the fit limits: Teams wanting a document editor without Git's branching and review workflow. Setup effort has not been scored.
- Interoperability and portability
- See documented MCP, API and import routes below. Import does not prove export; API access does not prove a complete migration path. Check action scope, plans and portability.
Connections: MCP connections · APIs · Portability and vendor lock-in.
- Version control for every project
- Deploy hooks into hosting
- Teams wanting a document editor without Git's branching and review workflow
Top use cases
- Version control for code, sites and build-your-own projects source ↗
- Keep SOPs and docs as Markdown in a repo with history and review source ↗
- Automate builds, checks and scheduled jobs with GitHub Actions source ↗
- Track ops work with Issues and Projects source ↗
- Let AI agents read repos, manage issues and PRs and watch Actions via the GitHub MCP server source ↗
In depth
Actions minutes
Monthly standard-runner allowances are 2,000 minutes for Free accounts/organizations, 3,000 for Pro/Team and 50,000 for Enterprise Cloud. Standard runners are free for public repositories; larger runners are always charged. Additional private usage and storage can incur separate charges. Checked 2026-10-18. source ↗
Plans
Free includes unlimited public and private repositories. The current page advertises Team at $4 and Enterprise from $21 USD per user/month for the first 12 months. Confirm billing and renewal terms at checkout. Checked 2026-10-18. source ↗
Scoped agent access
GitHub offers hosted and local MCP servers. Its documentation names Claude, Codex, Cursor and Gemini CLI, with installation and authentication differing by host. Repository permissions, token scopes and organization policies still apply; start with read-only access and approve changes before writes. source ↗
How to use it with AI
How GitHub connects to each AI platform: native connector or MCP, API through code the agent writes, browser control, or file upload.
| Platform | MCP / connector | API (agent-written code) | Browser | Upload / export |
|---|---|---|---|---|
| Claude (incl. Claude Code) | Not documented Install guide for Claude Desktop and Claude Code. A named plugin, skill or CLI does not by itself establish an MCP/native connector pairing. Verify the route and client setup. GitHub named integration docs ↗Claude (incl. Claude Code) MCP docs ↗ | Not documented Claude (incl. Claude Code): Claude Code edits files and runs commands GitHub publishes an API, but this pairing still needs network, authentication and execution-scope checks. GitHub API ↗Claude (incl. Claude Code) docs ↗ | Inferred Claude Code with the Claude in Chrome extension (Chrome, Edge and other Chromium browsers). GitHub is a web app; the pairing itself is not documented. Claude (incl. Claude Code) browser docs ↗ | Not documented Verify which side exports and which imports, supported formats and permissions. GitHub's recorded upload/import status is yes; Claude (incl. Claude Code)'s file status is yes. These flags do not establish a file-transfer route. GitHub file docs ↗Claude (incl. Claude Code) file docs ↗ |
| OpenAI Codex | Not documented Install guide for OpenAI Codex. A named plugin, skill or CLI does not by itself establish an MCP/native connector pairing. Verify the route and client setup. GitHub named integration docs ↗OpenAI Codex MCP docs ↗ | Not documented OpenAI Codex: Edits files and runs commands locally; cloud tasks run in isolated workspaces GitHub publishes an API, but this pairing still needs network, authentication and execution-scope checks. GitHub API ↗OpenAI Codex docs ↗ | Inferred Only in the ChatGPT desktop app; not in the Codex CLI or IDE extension. GitHub is a web app; the pairing itself is not documented. OpenAI Codex browser docs ↗ | Not documented Verify which side exports and which imports, supported formats and permissions. GitHub's recorded upload/import status is yes; OpenAI Codex's file status is yes. These flags do not establish a file-transfer route. GitHub file docs ↗OpenAI Codex file docs ↗ |
| Google Antigravity | Not documented GitHub has an official MCP server and Google Antigravity supports MCP, but GitHub's docs don't name this pairing. Auth setup may differ. GitHub MCP docs ↗Google Antigravity MCP docs ↗ | Not documented Google Antigravity: Agents edit code and run tasks GitHub publishes an API, but this pairing still needs network, authentication and execution-scope checks. GitHub API ↗Google Antigravity docs ↗ | Inferred The /browser guide documents App and CLI support through Chrome DevTools MCP; the overview comparison conflicts on CLI availability. IDE browser features are separate. GitHub is a web app; the pairing itself is not documented. Google Antigravity browser docs ↗ | Not documented Verify which side exports and which imports, supported formats and permissions. GitHub's recorded upload/import status is yes; Google Antigravity's file status is yes. These flags do not establish a file-transfer route. GitHub file docs ↗Google Antigravity file docs ↗ |
GitHub's docs also name: Gemini.
Confirmed is reserved for evidence of the specific connection route. The current named integrations include plugins, skills and CLIs, so a named platform alone does not confirm MCP or a native connector. Inferred means each side documents a relevant capability, but no document describes the pairing. Code execution still needs network and credential access; file handling still needs a compatible format and transfer direction. Not documented means the records do not establish the route. IonBin has not tested these pairings. Recorded Oct 18, 2026.
Agent compatibility
| Level | Status | Detail / source |
|---|---|---|
| Native connector / MCP | Yes | Official docs ↗ |
| API / CLI | Yes | Official docs ↗ |
| Browser / manual | No | Browser access is recorded alongside a documented programmatic route. |
| File upload / import | Yes | Official docs ↗ |
Recorded Oct 18, 2026. Setup and plan limits vary; check the vendor's docs. How levels are assigned.
Appears in these proposed stacks
SOPs & process documentation Docs as code (optional)
Ops & admin automation Swap-in
Dev, web & IT Code
Document & knowledge preparation Version history
Local document questions Swap-in
An official MCP server is documented for this tool. These platforms separately document MCP client support: ChatGPT, Claude, Cursor, Gemini (Google), Google Antigravity, Grok, Grok Bot, Lindy, LM Studio, Mistral Vibe, OpenAI Codex. This inventory does not establish compatible transport, authentication or actions for a pairing. Check the connection matrix and linked sources.
Automation hubs to assess for a custom API connection: Gumloop, Make, n8n, Zapier. Verify credentials, supported requests, limits and error handling; no configured integration is implied.
Workflows using this tool
- Give every AI tool your brand context
- Fix site-audit issues as pull requests
- Hand coding tasks to an agent from your board
- Ship a small AI tool to production
- Turn sprint issues into booked time
- Package your best prompts as reusable agent skills
- Make your offer page readable by AI agents
- Get a weekly repo report from a scheduled agent
- Check your agent setups for the lethal trifecta
- Build an evaluation set from support tickets
- Re-run your evaluation set when a model changes
- Turn a PDF folder into checked, source-linked Markdown
Explained in the wiki
Related skills
Review
No long-form review yet. Verdict is based on research, not hands-on testing.