Schema | MCP QA Lab

MCP QA Lab

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.

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

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.

Interactive templates invoked by user choice

Name	Description
`audit_target_prompt`

Contextual data attached and managed by the client

Name	Description
`targets_resource`	Return the current secret-free target registry.

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/efficjump/mcp-qa-lab'

If you have feedback or need assistance with the MCP directory API, please join our Discord server