Documentation
Start with Getting Started, then follow the CLI track for terminal-based workflows or the App track for the web UI.
What MCPLab Does
MCPLab is a testing and evaluation framework for MCP servers. Write scenarios that describe tasks an LLM agent should complete using your MCP tools, run them against one or more models, and assert on the results — which tools were called, in what order, and what the response contained.
Getting Started
Overview
What MCPLab does and when to use it.
Installation
Install MCPLab and configure your API keys.
Quick Start
Write your first eval and see results in under 5 minutes.
Setting Up Evaluations
Set up a robust evaluation workflow before running your first full test suite.
Scenario Configuration
Detailed guide for writing MCPLab scenarios and assertions.
Libraries & Refs
Reuse shared servers, agents, and scenarios across evaluation configs.
CLI
App
Starting the App
Launch the MCPLab web UI and find your way around.
Configurations
Browse, filter, and run eval configs from the Configurations page.
Running Evaluations
Launch and monitor evaluations from the web UI.
Analysing Results
Understand run output, compare agents, and browse markdown reports.
AI Assistants
Use the Scenario and Result AI assistants to work faster.
MCPLab Assistant Skill
Install and use the mcplab-assistant skill from skills.sh in Codex/Claude-style agent workflows.
OAuth Debugger
Debug OAuth 2.0 authorization flows for MCP servers step by step.
Scenario Setup in the App
Create and manage evaluation scenarios directly in the MCPLab app UI.
MCP Tool Analysis
Review MCP tool definitions for quality and LLM-readiness.
Library
Manage reusable agents and servers shared across eval configs.