GitHub MCP
by abdul-34
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Bind address. '127.0.0.1' to expose only to a local proxy | 0.0.0.0 |
| PORT | No | Listen port | 8080 |
| TRUST_PROXY | No | Proxy hops to trust for client IPs. '1' behind a proxy | 0 |
| GITHUB_TOKEN | Yes | GitHub PAT the tools act with | |
| MAX_SESSIONS | No | Concurrent session cap (LRU eviction) | 50 |
| ALLOWED_REPOS | No | Comma-separated owner/repo allowlist for repo-scoped tools | (all) |
| MCP_READ_ONLY | No | Register read tools only; write tools are never exposed | false |
| MCP_AUTH_TOKEN | Yes | Shared secret clients must present (min 32 chars) | |
| ALLOWED_ORIGINS | No | Comma-separated browser origins allowed to call the server | (none) |
| SESSION_IDLE_MINUTES | No | Idle session timeout | 30 |
| MCP_ALLOW_QUERY_TOKEN | No | Also accept the token as ?key= | false |
| RATE_LIMIT_PER_MINUTE | No | Per-IP request ceiling | 240 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues