github-pr-review-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Set to 'true' to enable debug logging. | |
| GITHUB_TOKEN | Yes | Your GitHub Personal Access Token with repo and read:user scopes. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| logging | {} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_pr_reviewsA | Get all reviews for a GitHub pull request |
| get_pr_commentsB | Get all comments on a GitHub pull request |
| analyze_pr_codeC | Analyze code changes in a PR for issues and suggestions |
| get_pr_filesB | Get list of files changed in a pull request |
| submit_pr_reviewC | Submit a review to a pull request |
| add_pr_commentC | Add a comment to a PR (general or line-specific) |
| update_prB | Update PR title, description, or state |
| get_pr_detailsC | Get detailed information about a pull request |
| get_pr_diff_hunksA | Get diff hunks with line mapping for all changed files in a PR. Returns per-file hunks with oldStart/oldLines, newStart/newLines, and patch content for accurate inline comment placement. |
| validate_pr_comment_targetA | Validate if a comment target (path, line, side) is valid for the PR diff. Returns validation status, reason for invalidity, and nearest valid line suggestion if applicable. |
| ensure_pending_reviewA | Ensure a pending review exists for the PR. Creates a new pending review if none exists, or returns the existing one. Returns reviewId and commitId for adding inline comments. |
| get_pending_reviewA | Get the current pending review for the PR (if any). Returns null if no pending review exists. |
| list_pending_review_commentsA | List all draft comments in the pending review for the PR. Returns empty array if no pending review exists. Each comment includes path, line, side, body, and metadata. |
| review_pr_with_promptA | Get PR context and review prompt for AI-powered code review. Returns formatted PR data and review guidelines that can be used with an LLM to generate a comprehensive review. The LLM can then use submit_pr_review to submit the review. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Each tool has a clear primary target—PR metadata, files, diff hunks, comments, reviews, pending review state, or submission—and the specialized helpers like validate_pr_comment_target and ensure_pending_review are distinct. Minor ambiguity remains between get_pr_files and get_pr_diff_hunks, and between get_pr_comments and get_pr_reviews/list_pending_review_comments, but descriptions generally disambiguate granularity.
Tool names follow a consistent verb_noun pattern throughout: get_, add_, submit_, update_, ensure_, list_, analyze_, validate_, and review_. The naming style is uniform and the PR object is always clearly identified, making selection predictable.
14 tools is well within the ideal scope for a PR review server. Each tool covers a distinct step of the workflow—from reading PR data and diff hunks to managing pending reviews and submitting—without meaningful redundancy.
The tool surface covers the core PR review lifecycle: fetching PR details, files, diff hunks, reviews/comments, analyzing code, creating/managing pending reviews, adding comments, validating targets, and submitting reviews. Notable minor gaps are the absence of explicit editing/deleting for pending review comments and no dismissal or revision-handling tools, but these do not dead-end the primary workflow.