AI PR Reviewer
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PR_REVIEW_ARTIFACTS_DIR | No | Directory where review artifacts (review.json, review.md, and images) are written. Defaults to the system temp directory. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
pr-review opens a local review page for a repository and reads the review back. Use the tools directly: start_review, await_review, get_review, list_review_scope, close_review. To review a GitHub pull request: call list_pull_requests to see the open PRs, then start_review with mode="pr" and its number (pr=N); this reads the PR through the GitHub CLI, so gh must be installed and authenticated. Do not edit the OpenCode configuration, add wrapper scripts or change how this server is launched: the server finds git on its own and needs no environment setup. If a tool fails, report the error instead of rewriting the config.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_reviewB | Opens a GitHub-style review page in the browser for uncommitted changes, commits on a branch, specific commits, or a whole branch. Shows a syntax-highlighted diff with inline (multi-line) comments, pasted screenshots, go-to-definition links and a per-file viewer. Returns the URL and a reviewId. |
| await_reviewA | Blocks until the review page submits a review, then returns every inline comment plus paths to review.json and review.md. |
| get_reviewA | Reads a saved review (by reviewId or an explicit review.json path) and returns it as Markdown. |
| list_review_scopeA | Lists branches or commits so you can choose a scope for start_review. |
| list_pull_requestsA | Lists the pull requests of a repository through the GitHub CLI, newest first, so you can pick one to review with start_review(mode="pr", pr=NUMBER). Requires an authenticated gh. |
| resolve_commentsA | Marks review comments as resolved (fixed) or open again, in the saved review. Use it after fixing what a comment asked for, so the reviewer sees the state on the page and in review.md. |
| close_reviewC | Stops the local HTTP server for the given reviewId. |
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 7 tools
The tools mostly target distinct lifecycle stages: listing PRs/scopes, starting a review, awaiting submission, reading a saved review, resolving comments, and closing the server. The only mild overlap is between await_review and get_review, since both can return review content, but their blocking versus saved-read behavior is clearly described.
All tool names use a consistent snake_case verb_noun pattern: await_review, close_review, get_review, list_pull_requests, list_review_scope, resolve_comments, start_review. The convention is predictable and easy to follow.
Seven tools is well-scoped for an AI PR review workflow. Each tool maps to a necessary step without excessive surface area.
The set covers the full review lifecycle: discovering PRs and scopes, starting a review page, waiting for submitted feedback, retrieving saved reviews, resolving comments, and closing the server. No obvious workflow dead ends are present.