MCP Chat
mcp-chat is an open-source and general-purpose MCP client tool for testing and evaluating MCP servers and proxies. It supports command-line interaction and web mode, can connect to various MCP servers (JS/Python/Docker), and provides functions such as chat history recording, model selection, and system prompt customization to help developers debug MCP services.
2.5 points
8.4K

What is mcp-chat?

mcp-chat is an open-source tool that allows developers or users to interact with various MCP servers through the command line or web interface. It supports connecting to different types of MCP servers (implemented in JavaScript, Python, or Docker) and can test server functions by having conversations with AI models in natural language.

How to use mcp-chat?

You can start mcp-chat with a simple npx command, specify the MCP server to connect to, and then interact with the AI model in a conversational form. It supports two modes: command-line interaction mode and web interface mode.

Applicable scenarios

It is suitable for scenarios such as MCP server developers testing functions, AI application developers integrating the MCP protocol, and technology enthusiasts exploring the integration of AI and tools.

Main features

Command-line interaction mode
Have conversations with the AI model directly in the terminal, suitable for quick testing and automation scripts.
Web interface mode
A user-friendly interface accessible via a browser, supporting dynamic configuration of MCP servers.
Multi-server support
Can connect to MCP servers implemented in JavaScript, Python, or Docker.
Model selection
Supports selecting different AI models for conversations (currently supports Anthropic models).
Conversation history saving
Automatically saves all chat records and settings for subsequent viewing and continued conversations.
Advantages
A simple and easy-to-use interaction interface that lowers the threshold for using the MCP protocol.
Supports multiple operating environments and server types.
A complete conversation history recording function.
Developer-friendly debugging tools that allow direct viewing of tool call details.
Limitations
Currently only supports Anthropic's AI models.
Requires some command-line knowledge for initial configuration.
The web interface functions are relatively basic.

How to use

Installation preparation
Ensure that the Node.js environment is installed and the ANTHROPIC_API_KEY environment variable is set.
Start in command-line mode
Start with the npx command and specify the MCP server to connect to.
Start in web mode
Add the --web parameter to start the web server, and then access it in the browser.
Interact with the AI
Enter your questions or instructions in the command line or web interface, and the AI will perform operations through the MCP server and return the results.

Usage examples

Test file system operations
Use the file system MCP server to query desktop files.
Kubernetes cluster management
Use the Kubernetes MCP server to manage the cluster.
Weather query
Use the weather MCP server to obtain weather information.

Frequently Asked Questions

How to obtain the ANTHROPIC_API_KEY?
Which AI models are supported?
How to develop your own MCP server?
Where are the chat records saved?
What functions does the web interface support?

Related resources

GitHub repository
Project source code and latest documentation
Anthropic console
Obtain the API key
MCP protocol documentation
Official documentation of the Model Context Protocol
npm package page
Package information on npm

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
10.5K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
10.1K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
15.8K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
6.7K
4 points
P
Paperbanana
Python
8.9K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
9.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
10.0K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
9.7K
5 points
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
28.3K
4.3 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
23.8K
4.5 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
39.1K
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
81.4K
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#
38.4K
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
69.4K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
24.9K
4.5 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
55.2K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase