MCP QA Lab
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_QA_ALLOW_REMOTE | No | Set to 1 to allow remote targets. Defaults to deny. | 0 |
| MCP_QA_ALLOWED_ROOTS | No | Comma-separated list of allowed root directories for local target working directories. |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| register_targetA | Register a secret-free stdio or Streamable HTTP target after boundary validation. |
| list_targetsA | List registered targets without resolving or exposing environment values. |
| inspect_targetA | Connect to a target and capture its complete paginated model-facing MCP contract. |
| run_static_checksA | Analyze live schemas, descriptions, annotations, and size without tool calls. |
| measure_context_costA | Measure serialized model-facing tool metadata and exact duplicate descriptions. |
| generate_scenariosA | Generate task-oriented multi-tool journeys using sampling, with an explicit fallback. |
| run_target_toolA | Execute one call; non-read-only tools require explicit side-effect approval. |
| build_reportA | Create a redacted Markdown report from a new live inspection and deterministic checks. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| audit_target_prompt |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| targets_resource | Return the current secret-free target registry. |
TDQS
Scored across 8 tools
Most tools have clearly distinct purposes (listing, registering, inspecting, checking, measuring, generating, executing, reporting). The only potential confusion is between run_static_checks and measure_context_cost, but their descriptions clarify that one focuses on quality/size analysis and the other on serialized metadata cost and duplicate descriptions.
All tool names follow a consistent verb_noun pattern (list_targets, register_target, inspect_target, run_static_checks, measure_context_cost, generate_scenarios, run_target_tool, build_report). The naming is uniform and predictable.
Eight tools is an appropriate scope for a QA lab. The set covers the main workflow areas without being bloated or sparse, aligning well with the typical 3-15 tool sweet spot.
The toolset covers the core workflow: register, inspect, run checks, measure cost, generate scenarios, execute a tool, and build a report. A minor gap is the absence of a delete/unregister target operation, which could make target lifecycle management incomplete.