github-devhub-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | Yes | GitHub personal access token (classic with repo scope or fine-grained with read access to contents, pulls, issues) | |
| GROQ_API_KEY | Yes | Groq API key for free-tier LLM-powered tools |
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 |
|---|---|
| github.get_repoB | Get repository metadata: description, language, stars, default branch, archived status. |
| github.list_reposA | List repositories for an owner (user or org), sorted and paginated. |
| github.list_prsA | List pull requests in a repository, filtered by state. |
| github.get_prA | Get full detail on a pull request: title, state, author, stats, head/base refs. |
| github.ci_statusA | Get CI status (check runs + combined commit status) for a PR or a commit ref. |
| github.code_searchA | Search code across GitHub. Requires a token with scope for the repos you search. |
| github.list_issuesB | List issues in a repository, optionally filtered by state and labels. |
| github.get_issueB | Get an issue (not a PR) by number, with metadata. |
| github.create_issueA | Create an issue. Set dry_run=true to preview the request without writing anything. |
| github.add_issue_commentA | Post a comment on an issue or PR thread. Set dry_run=true to preview without writing. |
| ai.review_prB | Run an LLM code review on a pull request (fetches the diff, commits, and description). |
| ai.summarize_prA | Produce a concise summary of a pull request: what it does, how, and notable changes. |
| ai.summarize_issueA | Summarize an issue and its comment thread so a newcomer can jump in. |
| ai.triage_issueA | Classify an issue (type, priority, suggested labels) and explain why. |
| ai.gen_commit_messageA | Generate a conventional commit message from a pull request's commits and changed files. |
| ai.explain_repoA | Generate a newcomer's onboarding brief for a repository from its README and top-level file tree. |
| meta.healthA | Check connectivity: GitHub API rate limit and a live Groq LLM ping. |
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 17 tools
Each tool targets a distinct resource and action—PRs, issues, repos, code search, CI, and AI analysis are cleanly separated. Even overlapping AI tools (summary vs review vs triage) have clearly defined different outputs.
Most tools follow a verb_noun pattern (get_pr, create_issue, list_repos, summarize_pr) with domain prefixes. Minor exceptions like ci_status and health are noun phrases, but the overall pattern is consistent and predictable.
17 tools is slightly above the ideal range, but each tool serves a distinct purpose in the GitHub + AI workflow. No redundant tools; the count feels intentional even if a bit heavy.
The surface is strong for reading and analyzing (repos, issues, PRs, code, CI) and supports creating issues and comments. However, there are no update/delete/merge operations for issues or PRs, leaving common management workflows incomplete.