AIbase
EN
Explore
Ma3u MCP Dust Server
M

Ma3u MCP Dust Server

The MCP Dust Server is a server-side implementation of the Model Context Protocol (MCP) for interacting with Dust AI agents. The project consists of an MCP server and a test client, supporting real-time streaming responses, the complete JSON-RPC 2.0 protocol, session management, and other functions. It can be integrated into development environments such as Windsurf IDE and Claude Desktop.
Artificial intelligence chatbotsDeveloper tools#AI agent#Real-time interaction#Protocol service#Development tool.TypeScript
2 points
20

What is the MCP Dust Server?

The MCP Dust Server is a middleware server that implements the Model Context Protocol (MCP) standard and is specifically designed to interact with AI agents on the Dust.tt platform. It allows developers to access various AI capabilities on the Dust platform through a standardized protocol without having to directly handle the underlying API details.

How to use the MCP Dust Server?

You can interact with the server through simple HTTP requests or WebSocket connections. The server provides standard interfaces for initializing sessions, sending messages, and terminating sessions, and also supports advanced functions such as direct tool execution.

Applicable scenarios

Suitable for scenarios where Dust AI capabilities need to be integrated into existing systems, such as enterprise workflow automation, customer service robots, data analysis assistants, etc. Particularly suitable for multi-round dialogue applications that require long-term context maintenance.

Main features

Multi-protocol supportSupports both Server-Sent Events (SSE) and HTTP Stream Transport for real-time communication protocols
Complete MCP lifecycleImplements the complete session lifecycle management of initialize, message, and terminate
Direct tool executionTools can be directly executed through the 'run' method, simplifying client integration
Context maintenanceAutomatically maintains session status and context, supporting multi-round complex dialogues
Secure communicationAutomatically masks sensitive information such as API keys to ensure log security

Advantages and limitations

Advantages
Standardized protocol: Uses the MCP standard protocol, making it easy to integrate with other systems
Real-time interaction: Supports streaming responses, providing a more natural dialogue experience
Enterprise-level security: Built-in PII protection mechanism, meeting enterprise security requirements
Multi-platform support: Can be seamlessly integrated with tools such as Windsurf IDE and Claude Desktop
Limitations
Requires a Dust.tt platform account and API key
There is a certain learning curve for non-technical personnel to configure
Currently mainly targeted at developers, lacking a graphical configuration interface

How to use

Installation preparation
Ensure that the Node.js environment is installed. It is recommended to use nvm to manage the Node version.
Get the project code
Clone the GitHub repository to the local machine.
Configure the environment
Copy the .env.example file to .env and fill in your Dust API key and other information.
Start the service
Run the development mode server and the test client.
Test the connection
Access http://localhost:6001 to use the test client to verify the connection.

Usage examples

Integrate into an enterprise customer service systemUse the MCP server as middleware to connect the enterprise's existing customer service system and Dust AI agents, realizing intelligent Q&A functions
Data analysis assistantConnect to the data query agent through the MCP server, allowing business personnel to query enterprise data in natural language
Multi-agent workflowCoordinate multiple professional agents to complete complex tasks, such as generating a market analysis report

Frequently Asked Questions

How to obtain a Dust API key?
Which AI models does the server support?
How to expand custom functions?
What is the maximum session duration?
How to monitor the server status?

Related resources

GitHub repository
Project source code and the latest version
Dust.tt platform
Official platform website
MCP protocol specification
Official documentation of the Model Context Protocol
Node.js installation guide
Official download and installation instructions for Node.js
Installation
Copy the following command to your Client for configuration
{
  "mcpServers": {
    "dust-mcp": {
      "command": "npm",
      "args": [
        "run",
        "start:server"
      ],
      "env": {
        "DUST_API_KEY": "${YOUR_API_KEY}",
        "DUST_WORKSPACE_ID": "${YOUR_WORKSPACE_ID}",
        "DUST_AGENT_ID": "${YOUR_AGENT_ID}"
      },
      "host": "127.0.0.1",
      "port": 5001,
      "timeout": 30000
    }
  }
}

{
  "mcpServers": {
    "dust-agent": {
      "command": "npm",
      "args": [
        "run",
        "start:server"
      ],
      "cwd": "path/to/mcp-dust-server",
      "host": "127.0.0.1",
      "port": 5001,
      "timeout": 30000,
      "env": {
        "DUST_API_KEY": "${YOUR_API_KEY}",
        "DUST_WORKSPACE_ID": "${YOUR_WORKSPACE_ID}",
        "DUST_AGENT_ID": "${YOUR_AGENT_ID}"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
N
Notte Browser
Certified
Notte is an open-source full-stack network AI agent framework that provides browser sessions, automated LLM-driven agents, web page observation and operation, credential management, etc. It aims to transform the Internet into an agent-friendly environment and reduce the cognitive burden of LLMs by describing website structures in natural language.
651
4.5 points
S
Search1api
The Search1API MCP Server is a server based on the Model Context Protocol (MCP), providing search and crawling functions, and supporting multiple search services and tools.
TypeScript
336
4 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
823
4.3 points
B
Bing Search MCP
An MCP server for integrating Microsoft Bing Search API, supporting web page, news, and image search functions, providing network search capabilities for AI assistants.
Python
221
4 points
M
MCP Alchemy
Certified
MCP Alchemy is a tool that connects Claude Desktop to multiple databases, supporting SQL queries, database structure analysis, and data report generation.
Python
317
4.2 points
P
Postgresql MCP
A PostgreSQL database MCP service based on the FastMCP library, providing CRUD operations, schema inspection, and custom SQL query functions for specified tables.
Python
105
4 points
M
MCP Scan
MCP-Scan is a security scanning tool for MCP servers, used to detect common security vulnerabilities such as prompt injection, tool poisoning, and cross-domain escalation.
Python
609
5 points
A
Agentic Radar
Agentic Radar is a security scanning tool for analyzing and assessing agentic systems, helping developers, researchers, and security experts understand the workflows of agentic systems and identify potential vulnerabilities.
Python
548
5 points
Featured MCP Services
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
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
823
4.3 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
79
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
130
4.5 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#
554
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
6.6K
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
745
4.8 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2025AIbase