Strunk publishes a draft you wrote in Claude, ChatGPT, or Codex out to Google Docs, then brings your reviewers' comments back with the exact spans they anchored to. You triage and revise inside the AI tool that already holds your repo and data context, while your reviewers keep commenting in Google Docs. There is no copy and paste, no pull request, and nobody has to adopt a new tool to leave feedback. Existing comments and their anchors survive a re-publish. Revisions land a
Strunk publishes a draft you wrote in Claude, ChatGPT, or Codex out to Google Docs, then brings your reviewers' comments back with the exact spans they anchored to. You triage and revise inside the AI tool that already holds your repo and data context, while your reviewers keep commenting in Google Docs. There is no copy and paste, no pull request, and nobody has to adopt a new tool to leave feedback. Existing comments and their anchors survive a re-publish. Revisions land as targeted edits instead of a full replace, so a thread your reviewer opened last week still points at the text it was about. Google Docs stays the source of truth, and its version history is the revert path. The tools: publish_doc sends a draft out and re-publishes a revised version. pull_comments brings threads back with their quoted spans and the tab each one sits in. apply_revisions writes approved edits to specific spans. reply_comment and resolve_comment answer and close threads in place. inspect_doc reads t
| Type | MCP server |
| Section | MCP servers |
| Pricing | free |
| Platform | Command line |
| Systems | cli, api |
| Hosting | cloud |
| Install | mcp |
| Protocols | mcp |
| Site language | en |
| Vendor | strunk |