coderabbitai-mcpSAFE
MCP server for interacting with CodeRabbit AI reviews on GitHub pull requests
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server for interacting with CodeRabbit AI reviews on GitHub pull requests. This server enables Large Language Models (LLMs) to analyze, understand, and implement CodeRabbit suggestions programmatically.
Features
- Get CodeRabbit Reviews: Retrieve all CodeRabbit reviews for a specific pull request
- Review Details: Get detailed information about specific reviews including configuration and files reviewed
- Extract Comments: Get individual line comments with AI prompts and suggestions
- Comment Details: Deep dive into specific comments with context and fix examples
- Resolve Comments: Mark comments as addressed, won't fix, or not applicable
- Automated Workflow Prompt: Use
/coderabbit-reviewslash command for complete review processing
Quick Start
Installation (NPX - Recommended)
No installation required! Run directly with npx:
# Install the latest stable version explicitly npx coderabbitai-mcp@latest
Prerequisites
- GitHub Personal Access Token: Create at
- Required scopes:
repo(for private repos) orpublic_repo(for public only) - Node.js 18+: Required for running the server
Configuration
Claude Desktop Configuration
To use the CodeRabbit MCP server in Claude Desktop, add it to your configuration file:
Configuration file locations:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Step-by-step setup:
- Open your Claude Desktop configuration file (create it if it doesn't exist)
- Add the CodeRabbit MCP server configuration:
{
"mcpServers": {
"coderabbitai": {
"command": "npx",
"args": ["coderabbitai-mcp@latest"],
"env": {
"GITHUB_PAT": "ghp_your_token_here"
}
}
}
}- Repla
2c4165772b1fOBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add coderabbitai-mcp -- npx -y [email protected]
{
"mcpServers": {
"coderabbitai-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (10)
10 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
coderabbit-review | read | Automated CodeRabbit review processing and issue resolution for the current branch |
get_coderabbit_reviews | read | Get all CodeRabbit reviews for a specific GitHub pull request |
get_comment_details | read | Get detailed information about a specific CodeRabbit comment including AI prompts |
get_review_comments | read | Get all individual line comments from CodeRabbit reviews |
get_review_details | read | Get detailed information about a specific CodeRabbit review |
owner | read | Repository owner (username or organization) |
pullNumber | read | Pull request number to process |
repo | read | Repository name |
resolve_comment | read | Mark a CodeRabbit comment as resolved or addressed |
resolve_conversation | read | Resolve or unresolve a CodeRabbit review conversation in GitHub |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, zod, @types/node, typescript
Gates applied: no_behavioural_pass.
2c4165772b1ffull audit observations/trust-audit/mcp-server/bradthebeeble__coderabbitai-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 2c4165772b1f | SAFE | B | 89 | first audit |
Questions
What is the coderabbitai-mcp MCP server?
MCP server for interacting with CodeRabbit AI reviews on GitHub pull requests
What tools does coderabbitai-mcp expose?
10 in total: 10 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is coderabbitai-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does coderabbitai-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does coderabbitai-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as coderabbitai-mcp at 1.1.1.
How current is this page?
The grade is for one exact copy of the source (2c4165772b1f), read on 2026-10-12. The repository is watched and re-audited when it changes.