Back to Home
Liquescent-Development icon

mcprobe

Verified Safe

by Liquescent-Development

Overview

A conversational testing framework for MCP (Model Context Protocol) servers, validating that LLM agents can correctly answer real-world questions using synthetic users and LLM judges.

Installation

Run Command
mcprobe run test-scenario.yaml --provider ollama --model llama3.2

Environment Variables

  • OPENAI_API_KEY
  • OLLAMA_BASE_URL
  • GOOGLE_API_KEY
  • MCP_URL
  • MCP_TOKEN
  • GEMINI_MODEL
  • AGENT_TEMPERATURE

Security Notes

The `mcprobe generate-scenarios` command executes arbitrary user-provided commands (e.g., `npx @example/weather-mcp`) via `subprocess.run` to connect to an MCP server. While intended for developers to launch their *own* trusted local servers for testing, this feature represents a significant security risk if the `server` argument were ever exposed to untrusted input. Otherwise, the project follows good security practices, such as using `SecretStr` for API keys in configurations and relying on environment variables.

Similar Servers

Stats

Interest Score0
Security Score6
Cost ClassHigh
Avg Tokens2000
Stars0
Forks0
Last Update2026-01-19

Tags

LLM TestingAgent EvaluationConversational AICI/CD IntegrationScenario Generation