T

Test Dh MCP

This project demonstrates how to use FastMCP to implement a Multi - Channel Protocol (MCP) server, including tool registration, server/client usage examples, and integration with Claude Desktop and the MCP Inspector.
2 points
8

What is Model Context Protocol (MCP)?

MCP is a protocol for distributed computing and tool integration that allows clients to interact with the server through multiple transport methods (such as SSE or Stdio). It supports dynamic registration and invocation of tools and is widely used in fields such as data analysis and machine learning.

How to use the MCP server?

The MCP server can be quickly started through simple installation and configuration, supporting SSE mode and Stdio mode. You can use the Python client to test tool functions or integrate it into other tools (such as Claude Desktop).

Applicable scenarios

The MCP server is suitable for scenarios that require cross - platform tool collaboration, such as data analysis, model training, and real - time computing.

Main features

Tool registrationSupports dynamic registration of tool functions through decorators, facilitating the expansion of new functions.
SSE transport modeSupports real - time communication between browsers and web clients through HTTP/2 streaming.
Stdio transport modeCommunicates directly with tools through standard input/output, suitable for desktop application integration.
Deephaven integrationSupports seamless docking with the Deephaven toolchain, providing efficient data processing capabilities.

Advantages and limitations

Advantages
Easy to expand and integrate multiple tools
Supports multiple transport methods to meet different scenario requirements
Superior performance, suitable for large - scale distributed computing
Limitations
Requires a certain Python foundation to write tools
Some advanced functions may depend on specific environment configurations

How to use

Install dependencies
Ensure that the Python environment is installed and install project dependencies through pip or the uv tool.
Start the server
Select the SSE or Stdio mode to run the server according to your needs.
Test the tool
Use the Python client to test whether the tool works properly.

Usage examples

Example 1: Use the Echo toolCall the Echo tool and return the input message.
Example 2: Connect to Claude DesktopConfigure the MCP server as an external tool for Claude Desktop.

Frequently Asked Questions

How to install the MCP server?
Which transport modes does the MCP server support?
How to debug tools?

Related resources

MCP official documentation
Details the MCP protocol and its application scenarios
GitHub project address
Get the source code and the latest version
MCP Inspector
A tool for checking the status of the MCP server
Installation
Copy the following command to your Client for configuration
{
      "mcpServers": {
        "test-dh-mcp": {
          "command": "/Users/chip/dev/test-dh-mcp/.venv/bin/python3",
          "args": ["/Users/chip/dev/test-dh-mcp/src/mcp_server.py", "--transport", "stdio"],
          "env": {
            "DH_MCP_CONFIG_FILE": "/Users/chip/dev/test-dh-mcp/deephaven_workers.json"
          }
        }
      }
    }

{
      "mcpServers": {
        "test-dh-mcp": {
          "command": "uv",
          "args": [
            "--directory",
            "/Users/chip/dev/test-dh-mcp/src",
            "run",
            "mcp_server.py",
            "--transport",
            "stdio"
          ],
          "env": {
            "DH_MCP_CONFIG_FILE": "/Users/chip/dev/test-dh-mcp/deephaven_workers.json"
          }
        }
      }
    }
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.
659
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
342
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
829
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
228
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
322
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
110
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
615
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
555
5 points
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
85
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
140
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
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
829
4.3 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
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#
564
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
282
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
753
4.8 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIbase