Toolchat
ToolChat is a tool for interacting with large language models (LLMs) via MCP servers, supporting the configuration of multiple tool servers and the invocation of specific functions, and can also handle multimodal input such as images and documents.
rating : 2 points
downloads : 18
What is ToolChat?
ToolChat is a tool that allows users to interact with various large language models (LLMs) through Model Context Protocol (MCP) servers. It supports text conversations, multimodal input (such as images and documents), and extended tool functions.How to use ToolChat?
Start via a simple command-line interface, configure the YAML file to define the MCP tool server, and select the tools to be enabled to start an interactive conversation.Applicable scenarios
Suitable for intelligent conversation scenarios that require the combination of professional tools (such as AWS documentation queries), supporting development debugging, technical documentation queries, multimodal content analysis, etc.Main features
MCP server integrationFlexibly connect to various MCP tool servers through the YAML configuration file
Multimodal supportSupports multiple input formats such as images and documents (depending on the model capabilities)
Tool chainingAutomatically combine multiple tools to complete complex tasks (such as searching first and then reading documents)
Advantages and limitations
Advantages
Flexible tool expansion capabilities
Supports the latest multimodal models
Automated tool invocation process
Limitations
Requires pre - configuration of the tool server
Some advanced features depend on the model version
The command-line interface is not user-friendly for non-technical users
How to use
Install the tool
Install the toolchat package via the uv tool
Prepare the configuration file
Create a tool server configuration file in YAML format (refer to sample-tools.yml)
Start the session
Specify the model and the tool servers to be enabled
Usage examples
AWS documentation queryFind the official documentation description of AWS services
Multimodal analysisUpload an image to get a description and analysis (requires model support)
Frequently Asked Questions
How to know which tools are available?
Why doesn't my image upload work?
How to develop my own MCP tool?
Related resources
MCP protocol documentation
Official technical documentation of the Model Context Protocol
Sample configuration file
Sample configuration file for the tool server
ToolChat source code
Open-source code repository for the tool
Featured MCP Services

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
141
4.5 points

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
86
4.3 points

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

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
830
4.3 points

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

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#
567
5 points

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
754
4.8 points

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
284
4.5 points