MCP Servers Collection logo

MCP Servers Collection

by syedair

This repository provides a collection of Model Context Protocol (MCP) servers designed for use with LLMs like Amazon Q and Claude Desktop. These servers extend LLM capabilities by providing additional tools and resources.

View on GitHub

Last updated: N/A

What is MCP Servers Collection?

This is a collection of Model Context Protocol (MCP) servers. MCP is an open protocol that standardizes how applications provide context to LLMs, enabling communication between the system and locally running servers that offer additional tools and resources.

How to use MCP Servers Collection?

To use these MCP servers, you need to configure your LLM (e.g., Amazon Q or Claude Desktop) to recognize and communicate with the server. This typically involves creating a configuration file (e.g., mcp.json) that specifies the server's command, arguments, and environment variables. Refer to the README for specific instructions for each LLM.

Key features of MCP Servers Collection

  • Exposes trading operations via Capital.com API

  • Allows searching for markets (e.g., EURUSD, AAPL)

  • Enables getting account information and positions

  • Supports creating and managing trading positions

  • Provides access to watchlists

  • Supports automated building and publishing via GitHub Actions

Use cases of MCP Servers Collection

  • Integrating trading capabilities into LLM workflows

  • Providing real-time market data to LLMs

  • Automating trading tasks through LLM interactions

  • Extending LLM functionality with custom tools and resources

FAQ from MCP Servers Collection

What is MCP?

Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to LLMs.

What LLMs are supported?

Currently, the servers are designed for use with Amazon Q and Claude Desktop, but any LLM supporting the MCP protocol should be compatible.

How do I install the MCP servers?

Each MCP server is a separate Python package. You can install them using uv pip install from within the server's directory.

How do I configure my LLM to use the MCP servers?

You need to create a configuration file (e.g., mcp.json) in your LLM's configuration directory, specifying the server's command, arguments, and environment variables. Refer to the README for specific instructions for each LLM.

How do I add a new MCP server to this collection?

Create a new directory under src/ with your server name, add the necessary files for your MCP server implementation, include a pyproject.toml and setup.py in the server directory, and add a README.md with usage instructions.