closure_drift
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| would_tagA | Use BEFORE creating a release tag: would the version that HEAD declares reuse a label that already names other code in the tags? Exit 1 means do not tag; bump the version first. Returns exit 0, 1 or 2 and the JSON report. Exit 2 is not a pass: nothing was decided, and output says why (no label found, a file not read, a tag not compared). Read-only: it runs git reads only, on the local repository, with no network. |
| check_versionsA | Use to audit the whole tag history: does each version label name exactly one code state? For a single release about to be tagged, use would_tag. With one release only, the answer is not decided (exit 2). Returns exit 0, 1 or 2 and the JSON report. Exit 2 is not a pass: nothing was decided, and output says why (no label found, a file not read, a tag not compared). Read-only: it runs git reads only, on the local repository, with no network. |
| explain_labelA | Use after check_versions reports drift: lists, for one label, the paths that differ between the first tag that used it and each other tag that did. For two references you choose, use compare. Returns exit 0, 1 or 2 and the JSON report. Exit 2 is not a pass: nothing was decided, and output says why (no label found, a file not read, a tag not compared). Read-only: it runs git reads only, on the local repository, with no network. |
| compareA | Use to compare any two tags or commits you name: their version labels, closures and the paths that differ. Publication points play no part. Exit 1 when both declare one label and the code differs. Returns exit 0, 1 or 2 and the JSON report. Exit 2 is not a pass: nothing was decided, and output says why (no label found, a file not read, a tag not compared). Read-only: it runs git reads only, on the local repository, with no network. |
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 4 tools
The four tools have largely distinct scopes: would_tag is for a forthcoming single release, check_versions audits all tag history, explain_label drills into one drifted label, and compare examines any two refs. The main possible confusion is between would_tag and check_versions, but their descriptions explicitly separate pre-tag single-release checks from full-history audits.
Three tools follow a verb_noun pattern (would_tag, check_versions, explain_label), while compare is a bare verb. This is a minor deviation and still readable, with no mixed casing styles.
Four tools are well-scoped for a focused read-only version/tag drift audit server. Each tool earns its place and covers a distinct step in the workflow.
The surface covers pre-tag checking, whole-history auditing, drift explanation, and arbitrary ref comparison. Minor gaps remain, such as listing tags or labels directly, but the core read-only lifecycle for this domain is covered.