github-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | Yes | GitHub Personal Access Token with at least the public_repo (or repo for private repos) scope |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_repositoriesB | Search GitHub repositories by keyword. Returns repo name, description, URL, stars, forks, and primary language. |
| list_issuesA | List issues for a GitHub repository. Returns issue number, title, state, labels, author, and URL. |
| read_file_contentsA | Read the raw text contents of a file from a GitHub repository. Returns the decoded file content. |
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 3 tools
Each tool targets a clearly different resource and action: searching repositories, listing issues, and reading file contents. There is no meaningful overlap between them.
All tool names follow the same lowercase snake_case verb_noun pattern: search_repositories, list_issues, read_file_contents. The convention is consistent and predictable.
Three tools is on the low end for a server named github-mcp-server. While the set is focused and each tool earns its place, the name implies a broader GitHub surface than three read-only operations.
The server lacks many core GitHub operations such as getting a single repository, creating or updating issues, listing pull requests, or exploring file paths before reading them. Agents would frequently hit dead ends, especially after searching for a repo or listing issues.