glasz-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_REPO | No | Optional GitHub repository owner/name. When set, tools default to it if repo is omitted. | |
| GITHUB_TOKEN | No | GitHub token for private repositories. Optional. Can also be placed in ~/.glasz-mcp/auth.json. |
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 |
|---|---|
| get_indexA | Call this first for any cross-feature question about a project (what is blocked, what shipped, status overview). Returns the raw markdown of specs/INDEX.md for the chosen repository. specs/INDEX.md is a derived rollup, not authoritative on its own — for detail on a specific feature, follow up with get_feature. |
| get_featureA | Call this for any feature-specific question. Returns the trio of markdown files (product.md, tech.md, test-plan.md) for one feature folder under specs/features//. Each file body is preceded by a "file: …, ref: …" header so you can cite the source. If any file is missing it is reported as missing rather than failing the whole call. |
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 2 tools
get_index and get_feature have clearly distinct purposes: one provides a project-wide overview rollup, the other drills into a single feature's details. There is no overlap or ambiguity between them.
Both tools follow the same 'get_' verb + noun pattern (get_index, get_feature), making the naming scheme perfectly consistent and predictable.
With only two tools, the server feels minimal, but this is appropriate for its narrow scope of reading spec markdown files. It is borderline on the thin side but still reasonable.
The server covers the core needs for accessing spec documentation: an index for cross-feature questions and a feature-specific detail view. A minor gap is that there is no explicit listing of all feature slugs, though the index may indirectly provide that.