spec-gate
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| score_requestA | Scores a request against the repository profile and returns a proceed or block verdict with the questions that close the gap. Writes nothing. |
| write_recordB | Stores the decision as a committed record: what was missing, what was assumed, who authorised proceeding. The verdict is computed from the declared coverage, not accepted from the caller. |
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
The two tools have clearly distinct purposes: score_request evaluates and returns a verdict, while write_record persists the decision. No overlap in functionality or ambiguity in selection.
Both tools follow a consistent verb_noun pattern (score_request, write_record), making the naming predictable and easy to infer for an agent.
With only 2 tools, the server feels thin for a domain like spec gating, but the tools cover the core workflow (scoring and recording). It's borderline but not unreasonable for a narrow purpose.
The tool set covers scoring and storing decisions but lacks obvious operations like retrieving past records or updating profiles. These gaps are notable but can be worked around for the primary gating use case.