1. Conduid
  2. Developer Tools
  3. Openreview
MCP server · Developer Tools

Openreview

OpenReview MCP — ML conference submissions and reviews (API v2)

Unclaimed last commit 6 months ago devtools
44Fair

Scored 1 hours ago · breakdown

About Openreview

Openreview is an MCP server published by saba-ch in the Developer Tools category: openReview MCP — ML conference submissions and reviews (API v2). It has been installed 0 times through Conduid.

The repository has 4 stars and 0 forks, with the last commit 6 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues (0) before depending on it in production.

Install

Install
npx openreview

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about Openreview

Powered by Claude · Grounded in docs

I know everything about Openreview. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

OpenReview

A native git diff viewer with AI-powered code review via MCP. Open any repository, browse staged and unstaged changes, and let Claude (or any MCP-compatible AI) leave inline comments directly in the UI.

OpenReview screenshot


Features

  • Git diff viewer — staged and unstaged changes side by side, syntax highlighted, virtualised for large diffs
  • Inline comments — click any diff line to annotate it; comments survive refreshes until the line disappears
  • File tree sidebar — collapse/expand files, see addition/deletion counts at a glance
  • Copy review — export all comments as plain text (file path + line + text) for pasting into PRs or tickets
  • MCP server — full Model Context Protocol server running locally at http://127.0.0.1:27182/mcp; connect Claude Desktop, Cursor, or any MCP client and let the AI read the diff and post comments without leaving your editor

Getting started

npm install
npm run dev

Click open in the toolbar to pick a git repository. The MCP server starts automatically alongside the app.


MCP setup

The app exposes an MCP server on http://127.0.0.1:27182/mcp (Streamable HTTP transport). Click mcp url in the toolbar to copy the URL to your clipboard.

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "openreview": {
      "url": "http://127.0.0.1:27182/mcp"
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project (or globally in ~/.cursor/mcp.json):

{
  "mcpServers": {
    "openreview": {
      "url": "http://127.0.0.1:27182/mcp"
    }
  }
}

MCP capabilities

Tools

Tool Description
get_comments Returns all review comments. Optional filePath filter.
add_comment Adds an inline comment to a diff line by lineRef.
update_comment Edits the text of an existing comment by id.
delete_comment Removes a comment by id.

Resources

URI Description
comments://all Live snapshot of all current comments (subscribable).

Tech stack

Electron · React · Zustand · Tailwind CSS · Shiki · @modelcontextprotocol/sdk

README mirrored from the source repository 1 hours ago. The original is authoritative.

Questions

About Openreview

How do I install Openreview?

Run npx openreview, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is Openreview safe to use with an AI agent?

Its trust score is 44 out of 100 (fair). It passes 0 of 1 static security checks; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Openreview still maintained?

The last commit was 6 months ago, with 0 open issues. That's long enough that you should check whether the maintainer is responding to issues before depending on it.