code-reviewer-mcp
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_branch_diffC | Get the git diff between the current branch and a base branch. Args: base_branch: The base branch to compare against (default: development). file_filter: File pattern to filter (default: *.py for Python files). working_directory: Working directory (defaults to current directory). Returns: The git diff output showing changes on the current branch. |
| get_changed_filesA | Get a list of changed files on the current branch. Args: base_branch: The base branch to compare against (default: development). file_filter: File pattern to filter (default: *.py for Python files). working_directory: Working directory (defaults to current directory). Returns: List of changed file paths with change statistics. |
| review_diffA | Review the git diff against the code review persona standards. This tool analyzes the diff between your current branch and the base branch, then provides structured feedback based on the team's code review standards. Args: base_branch: The base branch to compare against (default: development). working_directory: Working directory (defaults to current directory). focus_areas: Comma-separated focus areas: 'types', 'docs', 'style', 'errors', 'performance', 'architecture', or 'all'. persona_file: Path to a custom reviewer persona markdown file. Example: "notebooks/code_reviewer_persona.md" If not provided, uses the default persona. Returns: A structured code review with comments organized by file and category. |
| review_fileB | Review a specific file against the code review persona standards. Args: file_path: Path to the file to review (relative or absolute). working_directory: Working directory (defaults to current directory). persona_file: Path to a custom reviewer persona markdown file. Example: "notebooks/code_reviewer_persona.md" If not provided, uses the default persona. Returns: Code review feedback for the specified file. |
| get_personaA | Get the code reviewer persona that will be used for reviews. Use this to view or verify the persona before running a review. Args: persona_file: Path to a custom reviewer persona markdown file. Example: "notebooks/code_reviewer_persona.md" If not provided, uses the default persona. working_directory: Working directory (defaults to current directory). Returns: The full persona content that will be used for code reviews. |
| get_review_checklistB | Get the full code review checklist based on the persona. Returns: A comprehensive checklist for manual code review. |
| generate_review_reportB | Generate a comprehensive code review report as a markdown file. Args: base_branch: The base branch to compare against (default: development). output_file: Path to write the report (default: .code_review.md in repo root). working_directory: Working directory (defaults to current directory). persona_file: Path to a custom reviewer persona markdown file. Example: "notebooks/code_reviewer_persona.md" If not provided, uses the default persona. Returns: Path to the generated report file and a summary. |
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
Each tool targets a distinct artifact (diff, file list, checklist, persona, diff review, file review, report), and descriptions clarify boundaries. The only mild overlap is between review_diff and review_file, but they differ on scope (whole diff vs single file) so agents can still select correctly.
All names are snake_case and follow a predictable verb_noun pattern (get_*, review_*, generate_*). The convention is applied uniformly across all seven tools with no deviations.
Seven tools is well-scoped for a code review server, and each earns its place by covering a distinct step in the review workflow (gather, inspect, review, report). No redundancy or filler.
The surface covers the full local review lifecycle: diff retrieval, changed files, checklist, persona inspection, diff/file review, and report generation. Minor gaps exist around acting on results (e.g. posting comments to a PR or reviewing a commit range), but core workflows are complete.