Skip to main content
Glama

MCP QA Lab

CI Python 3.11+ License: MIT

Evidence-driven quality testing for Model Context Protocol servers. MCP QA Lab connects as a real client, captures the complete model-facing contract, finds agent-usability risks, measures context cost, and runs only explicitly approved target calls.

Why use it?

A server can have perfect handler-level tests and still be difficult for an agent to use. Tool names may be ambiguous, input fields may be undocumented, pagination may be incomplete, and safety intent may be missing. MCP QA Lab tests that public protocol surface separately from implementation code.

flowchart LR
    A[Register target] --> B[Live protocol inspection]
    B --> C[Static contract checks]
    B --> D[Context-cost measurement]
    C --> E[Scenario generation]
    E --> F[Approved calls only]
    D --> G[Evidence report]
    F --> G

Related MCP server: iris-eval/mcp-server

Highlights

  • Complete paginated discovery of tools, prompts, resources, and resource templates

  • Deterministic checks for schema quality, naming, descriptions, and safety annotations

  • Model-facing contract size and approximate context-cost measurement

  • Host-model sampling for task-oriented scenario proposals

  • Explicit approval boundary for target tool calls with possible side effects

  • Secret-free target registration using environment variable names, never values

  • Redacted Markdown reports with reproducible evidence

  • Stdio and Streamable HTTP target support

Install

Install directly from the public repository:

uv tool install "git+https://github.com/efficjump/mcp-qa-lab.git"
mcp-qa-lab --transport stdio

For source development:

git clone https://github.com/efficjump/mcp-qa-lab.git
cd mcp-qa-lab
uv sync --all-extras --locked
uv run mcp-qa-lab --transport stdio

Generic MCP client configuration

{
  "mcpServers": {
    "mcp-qa-lab": {
      "command": "mcp-qa-lab",
      "args": ["--transport", "stdio"]
    }
  }
}

Client configuration formats vary; the command and arguments above do not require a local repository path after tool installation.

Tool workflow

Tool

Purpose

register_target

Persist a secret-free stdio or Streamable HTTP target definition

list_targets

List registered targets

inspect_target

Capture the live, paginated MCP contract

run_static_checks

Find deterministic contract and usability issues

measure_context_cost

Measure serialized contract size and approximate token cost

generate_scenarios

Ask the host model for evidence-oriented test journeys

run_target_tool

Invoke one reviewed target tool with safety approval

build_report

Write a redacted Markdown QA report

Safety defaults

  • Remote targets are denied unless MCP_QA_ALLOW_REMOTE=1.

  • Local target working directories must stay inside MCP_QA_ALLOWED_ROOTS when configured.

  • Registrations reference inherited environment variable names; values are never persisted.

  • Inspection and static checks never invoke target tools.

  • Tools without readOnlyHint: true require explicit side-effect approval.

  • Reports redact credentials, authorization headers, tokens, and URL user information.

The process boundary is not an operating-system sandbox. Run untrusted targets in an isolated environment.

Streamable HTTP

mcp-qa-lab --transport streamable-http --host 127.0.0.1 --port 8765

The default endpoint is http://127.0.0.1:8765/mcp. Keep the listener on loopback unless a separate authentication and network boundary is in place.

Development

uv sync --all-extras --locked
uv run ruff format --check .
uv run ruff check .
uv run mypy src
uv run pytest --cov --cov-report=term-missing
uv build

The coverage gate is 85%. See architecture, security policy, and contribution guide.

License

MIT

A
license - permissive license
-
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    A
    quality
    A
    maintenance
    MCP server that lets coding agents test AI agents. Create YAML test cases, snapshot golden baselines, check for regressions, and generate visual reports all from inside Claude Code or any MCP-compatible tool. Works with LangGraph, CrewAI, OpenAI, Claude, Mistral, and any HTTP API.
    Last updated
    10
    33
    124
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    MCP-native agent evaluation and observability server. Log traces, evaluate output quality with 12 built-in rules (PII detection, prompt injection, cost thresholds), and track agent costs. Real-time dashboard, OTel-compatible spans. Self-hosted, MIT licensed.
    Last updated
    9
    41
    7
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    A stdio MCP server that audits other MCP servers over the live protocol. It connects to any MCP target (stdio or HTTP), lints every tool's schema for agent-usability, then actually calls the tools with deliberately broken inputs to see how the server handles them, and returns a 0–100 conformance score with a per-dimension breakdown rendered as Markdown.
    Last updated
    6
    6
    MIT
  • A
    license
    -
    quality
    B
    maintenance
    A universal AI-powered testing server built on the Model Context Protocol (MCP). Allows AI agents to inspect, execute, test, monitor, debug, and report on software projects.
    Last updated
    3
    GNU Lesser General Public v2.1 only

View all related MCP servers

Related MCP Connectors

  • Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.

  • Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.

  • MCP Spec Compliance MCP — audits any MCP server.json against the official Model Context Protocol

View all MCP Connectors

Latest Blog Posts

MCP directory API

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