About Commentify
Commentify brings design feedback threads from Figma, Jira, and Notion into Claude, helping teams review decisions and open questions while working on code. Its plugin can also draft replies and close threads after confirmation; those actions require Pro.
Key features
- 01Search feedback across three services
- 02Cite relevant comment threads
- 03Surface feedback while coding
- 04Post confirmed replies
- 05Mark confirmed threads done
Use cases
- 01Check open feedback on a ticket
- 02Review design decisions before changing UI
- 03Draft a response to a comment
- 04Close threads after addressing feedback
MCP support
Commentify is listed in the MCP registry as `one.commentify/commentify`. Its Claude plugin connects through the Commentify connector; the README does not detail the server's exposed MCP tools.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://app.commentify.one/api/mcpclaude mcp add --transport http one-commentify-commentify https://app.commentify.one/api/mcp{"mcpServers":{"one-commentify-commentify":{"type":"http","url":"https://app.commentify.one/api/mcp"}}}Open in Cursor{"servers":{"one-commentify-commentify":{"type":"http","url":"https://app.commentify.one/api/mcp"}}}Open in VS Code{"mcpServers":{"one-commentify-commentify":{"type":"http","url":"https://app.commentify.one/api/mcp"}}}{"mcpServers":{"one-commentify-commentify":{"serverUrl":"https://app.commentify.one/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMECommentify
Your team's design feedback from Figma, Jira and Notion, in Claude.
Commentify brings the comment threads from your Figma files, Jira issues and Notion pages into one place. This plugin connects Claude to it, and teaches Claude how to use it well.
What it does
- Ask what the team said. "What did the team say about the Inbox page?" "Is there open feedback on PROJ-123?" Claude answers from the threads and cites them.
- Check feedback before changing code. When you work on a screen or a component, Claude looks up the threads about those files and brings the decisions and open questions into the work.
- Reply in your name. Claude drafts a reply, shows it to you, and posts it on Figma, Jira or Notion once you confirm. Pro plan.
- Close threads. Mark threads done in Commentify when they are handled, after you confirm the list. Pro plan.
Setup
-
Sign up at app.commentify.one and connect at least one of Figma, Jira or Notion under Settings → Connect.
-
Install this plugin. In Claude Code, one line does it:
/plugin install commentify --marketplace oneSlash-app/commentify-pluginOn claude.ai and in Cowork, add it from Customize → Plugins, then connect the Commentify connector from the plugin's Connectors tab and sign in. In Claude Code, run
/mcpand sign in when the browser opens. -
Ask Claude about your feedback.
Reading is on every Commentify plan, within a daily limit. Replying and marking threads done need the Pro plan. The full guide is at app.commentify.one/docs/agents.
Data
The plugin sends your questions, the file paths and ticket keys you mention, and the replies you confirm to Commentify at app.commentify.one, over the connector you sign in to. Commentify answers with your own team's comment threads. The plugin stores nothing itself. Commentify's privacy policy is at commentify.one/privacy-policy.
Skills
| Skill | When Claude uses it |
|---|---|
design-feedback-digest | A question about what the team said, or a digest of open threads |
feedback-for-code | Working on UI files, a component or a ticket that designers commented on |
reply-to-feedback | Answering a thread in your name (Pro) |
close-feedback-threads | Marking handled threads done (Pro) |
MCP registry
The server is listed in the MCP registry as one.commentify/commentify, so any client that reads the registry can find it under the same name. The listing is maintained from Commentify's own repository, not from here.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.