qa-toolkit-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PROJECT | Yes | Absolute path to the project root passed via the --project flag. All paths are restricted to this directory. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| qa_capabilitiesB | Describe available operations and evidence status. |
| qa_discover_api_surfaceB | Read a local OpenAPI JSON file and return an endpoint-by-endpoint QA questionnaire. |
| qa_compile_indexed_casesC | Compile reviewed questionnaire answers into stable, unverified test cases. |
| qa_audit_case_referencesC | Locate candidate references to indexed case IDs; never claim tests pass. |
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
Each tool has a distinct role in the QA workflow: capabilities reporting, API surface discovery, case compilation, and reference auditing. There is no meaningful overlap that would cause misselection.
Three tools follow a clear qa_verb_noun pattern (qa_discover_api_surface, qa_compile_indexed_cases, qa_audit_case_references). qa_capabilities is a minor deviation as a noun-only tool, but it remains readable and consistent enough.
Four tools is well-scoped for a narrow QA toolkit focused on OpenAPI questionnaire discovery, compilation, and auditing. Each tool appears to earn its place without excess.
The set covers a discovery-to-compilation-to-audit flow, but it lacks obvious lifecycle operations such as listing or retrieving compiled cases and updating/deleting indexed cases. These gaps may force agents to work around the surface when managing cases.