PR Review MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_review_threadsB | List review threads for a GitHub pull request |
| reply_to_review_threadC | Add a reply to a review thread |
| resolve_review_threadB | Mark a review thread as resolved |
| reply_and_resolveA | Reply to a review thread and immediately resolve it |
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 4 tools
Each tool targets a distinct action: listing threads, replying, resolving, and the combined reply-and-resolve. The combined tool is clearly a convenience wrapper with explicit behavior, so no ambiguity exists.
All tool names follow a consistent verb_noun snake_case pattern (list_review_threads, reply_to_review_thread, resolve_review_thread, reply_and_resolve). The combined tool uses 'and' but adheres to the same style, maintaining high predictability.
With 4 tools, the server is tightly scoped to the core review-thread workflow. Each tool is essential and the count is well-balanced for the stated purpose of managing PR review threads.
The surface covers the main lifecycle actions for review threads: list, reply, resolve, and a convenience composite. Missing operations like unresolving or fetching a single thread are minor and unlikely to cause agent failures given the typical workflow.