repocritics-mcp-server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REPOCRITICS_API_BASE | No | Point at a local or staging deployment | https://repocritics.com/api/v1 |
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 | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_reposA | Full-text search across the RepoCritics seeded corpus. Returns matching repos with brief metadata. |
| get_repoA | Fetch metadata + scores for one repo (canonical_url, description, stars, forks, license, topics, critics_score, audience_score, final_score, category, staleness). |
| get_wikiA | Fetch the Tier-1 wiki content + tags for one repo. The wiki is RepoCritics' free, community-vetted summary. |
| list_reviewsB | Recent community reviews for one repo (newest first). |
| list_categoriesA | All RepoCritics categories with their tag filters. Useful for category-level navigation. |
| list_tagsC | Most-used tags across the wiki corpus. |
| get_ai_reportA | Tier-2 premium AI report content for a repo. Only returns a cached non-expired report; generation requires payment via the web app. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Global review feed | Atom feed of recent community reviews across every repo. Updates every ~5 minutes. |
TDQS
Scored across 7 tools
Each tool targets a distinct resource or action: search, repo metadata, wiki, reviews, categories, tags, and AI reports. There is no ambiguity between tools; even search_repos and get_repo are clearly differentiated by scope.
All tool names follow a consistent verb_noun pattern using snake_case (search_repos, get_repo, get_wiki, list_reviews, list_categories, list_tags, get_ai_report). The naming style is uniform and predictable.
With 7 tools, the server is well-scoped for a repository information service. Each tool earns its place, covering search, individual fetching, lists, and premium content without redundancy.
The tool set covers the main read-only operations for the RepoCritics corpus: searching repos, fetching metadata, wiki, reviews, categories, tags, and AI reports. Minor gaps exist, such as no way to fetch a single review or filter repos by category directly, but these are not critical for the core workflow.