github-mcp-sketch
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CACHE_SIZE | No | Max number of cached responses kept in memory before LRU eviction. | 50 |
| GITHUB_PAT | Yes | Bearer token forwarded as the Authorization header on every upstream request. | |
| METRICS_CSV | No | If set to a file path, the proxy appends per-tool-call metrics to that CSV. Off by default. | |
| UPSTREAM_MCP_URL | No | Upstream MCP endpoint. Override for testing or self-hosted GitHub MCPs. | https://api.githubcopilot.com/mcp |
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 | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/markadelnawar/github-mcp-sketch'
If you have feedback or need assistance with the MCP directory API, please join our Discord server