@shareworker/code-review-mcp
OfficialServer 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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_review_targetsA | Determine which files need review from a git diff. Applies file filtering and returns a diff_ref to pass to downstream tools. |
| get_file_bundleA | Group related files into review bundles (test/source pairs, i18n variants) with a 20000 char cap. Pass the diff_ref from get_review_targets. |
| match_rulesB | Return applicable review rules for a file path, merged into a prompt_section for the host LLM. |
| position_commentB | Locate a comment to precise line numbers. Text matching primary (hunk new-side → old-side → full file), hunk alignment fallback. Pass diff_ref from get_review_targets. |
| reflect_commentA | Deterministic validation of a positioned comment. Returns keep or drop. Does not call LLM. Three checks: line_in_hunk, existing_code_found, existing_code_in_diff. |
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 5 tools
Each tool has a clearly distinct purpose: identifying files to review, grouping related files, matching rules, positioning comments, and validating them. No two tools overlap in functionality.
All tools follow a consistent verb_noun pattern in snake_case (e.g., get_review_targets, position_comment), making them predictable and easy to understand.
Five tools is an ideal size for this domain, covering the essential steps of a code review process without unnecessary bloat or gaps.
The set covers core review workflow steps (targeting, file bundling, rule matching, comment positioning, validation) but lacks a tool for finalizing or submitting a review, which is a minor gap.