This repository contains MCP (Model Context Protocol) servers designed for various use cases, integrated with CAMEL-AI. These servers enable different functionalities like filesystem access, SQL operations, and markdown processing to enhance AI interactions with different data sources.
The Filesystem Server allows AI models to interact with the local filesystem, providing capabilities to read, write, and manipulate files and directories.
The SQL Server provides an interface for AI models to interact with SQL databases, enabling database queries and operations.
Two markdown-focused servers are available:
Clone the repository:
git clone https://github.com/parthshr370/MCP-Servers.git
cd MCP-Servers
Create and activate a virtual environment (recommended):
python -m venv venv
# On Windows
venv\Scripts\activate
# On macOS/Linux
source venv/bin/activate
Install dependencies:
pip install -r requirements.txt
Navigate to the filesystem server directory:
cd filesystem_server
Start the server:
python server.py
The server will be available for connection from CAMEL-AI or other compatible clients.
Navigate to the SQL server directory:
cd sql_server
Configure your database connection in the config file.
Start the server:
python sql_server.py
Connect to the server using a compatible client to perform SQL operations.
Navigate to the markdown conversion directory:
cd markitdown_camel
Run the server:
python markdown_server.py
Use the API endpoints to convert documents to markdown format.
The Note-taking markdown server is in a separate repository:
Clone the repository:
git clone https://github.com/parthshr370/Md-Notes-Buddy.git
cd Md-Notes-Buddy
Follow the installation and usage instructions in that repository.
For each server, you can connect with CAMEL-AI by:
The connection details and specific parameters will depend on which server you're using and your CAMEL-AI configuration.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.