M

MCP Autotest

A simple tool to test MCP servers by defining requests and responses in YAML files, supporting dynamic matching and multiple transport methods.
2.5 points
16

What is mcp-autotest?

mcp-autotest is a tool for testing Model Context Protocol (MCP) servers. It allows users to verify whether the requests and responses of MCP servers meet expectations by defining test cases in YAML format.

How to use mcp-autotest?

Run tests through a simple command-line interface, supporting multiple installation methods (including npm, pre-compiled binaries, and source code compilation). Test cases are defined in YAML files, containing input requests and expected output responses.

Applicable scenarios

Suitable for MCP server developers to conduct automated tests during the development process to ensure that the server functions comply with the MCP protocol specification.

Main features

YAML test casesDefine test cases using a simple YAML format, with each case containing an input request and an expected output response.
Multi-transport protocol supportSupport testing MCP servers using both stdio and HTTP transport protocols.
Dynamic matchingSupport using regular expressions to match dynamically changing response content.

Advantages and limitations

Advantages
Simple and easy-to-use YAML test case definition
Support for multiple installation methods and transport protocols
Provide detailed error output to assist debugging
Support dynamic content matching
Limitations
Currently only support JSON-RPC 2.0 format
HTTP transport only supports the POST method
Manual writing of test cases is required

How to use

Install mcp-autotest
Choose an installation method suitable for your environment
Create a test case file
Create a YAML file ending with _test.yaml in the test directory
Run tests
Execute the test command and specify the test directory and server startup command

Usage examples

Test the tool listVerify whether the server correctly returns the tool list
Dynamic content matchingUse regular expressions to match dynamically generated response content

Frequently Asked Questions

What naming rules must test files follow?
How to test an HTTP server?
How to match dynamically generated content?

Related resources

GitHub repository
Project source code and issue tracking
Release versions
Download pre-compiled binary versions
Postgres server example
A working example for testing a Postgres MCP server
Installation
Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.
Featured MCP Services
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
100
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
153
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
840
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
575
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
761
4.8 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIbase