moex
MCP server from prikotov/moex-mcp-server
claude mcp add --transport stdio prikotov-moex-mcp-server docker run -i --rm prikotov/moex-mcp-server:latest bin/server
How to use
This MCP server implements a console-based Symfony application that provides access to Moscow Exchange (MOEX) information through the MCP (Model Context Protocol) interface. It exposes tools for interacting with the MOEX ISS data, including retrieving security specifications, listing indices a security belongs to, generating aggregated trade totals for a given date, and fetching current trade data. The server is designed to run inside Docker (or locally if you install PHP and Composer) and can be accessed via the provided console commands or client utilities that exercise the MCP endpoints.
To use the tools, start the server in your preferred environment (Docker container or local PHP setup). Once running, you can invoke the available tools to query a specific security or instrument using the MCP client. The primary tools are: get_security_specification, get_security_indices, get_security_aggregates, and get_security_trade_data. Each tool returns structured data from MOEX ISS, such as a security’s metadata, its associated indices, daily aggregates for a period, and current trading information. Use these tools to script data retrieval for analysis, reporting, or integration with other systems that consume MCP-formatted responses.
How to install
Prerequisites:
- PHP 8.3 or higher (if running locally)
- Composer
- Docker (or Podman) if using containerized deployment
Install and run locally (non-Docker):
- Clone the repository: git clone <repo-url> cd moex-mcp-server
- Install PHP dependencies: composer install
- Run the server locally (via PHP CLI or Symfony console): php bin/console app:mcp-server or bin/server
Install and run with Docker:
- Build or pull the Docker image (if building locally from Dockerfile):
docker build -t moex-mcp-server .
or pull an existing image if available
- Run the server inside a container: docker run --rm -i moex-mcp-server bin/console app:mcp-server
- To test the client interface from the container, you can execute the MCP client command inside the container or use docker-compose/podman-compose as configured in the project: docker-compose run --rm moex-mcp-server bin/console app:mcp-client --via=console
Notes:
- The project includes a Makefile with targets like build, push, and test for convenient workflows.
- If you use Podman, you can replace docker commands with podman equivalents as shown in the repository documentation.
Additional notes
Tips and common issues:
- The Docker image prikotov/moex-mcp-server:latest is the recommended deployment approach; ensure you pull the latest image to access new tools and fixes.
- Environment variables are not strictly required for basic operations, but you may need to configure MOEX endpoints or credentials if your deployment customizes ISS data access.
- If you encounter permission errors running PHP CLI or Docker, ensure your user belongs to the docker group or runs commands with appropriate privileges.
- The Makefile provides shortcuts for common tasks (build, push, cache-clear, test). Use: make help to see available targets.
- Tests connect to the server and exercise the tools; ensure the server is running before executing tests or clients.
Related MCP Servers
drift
Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.
laravel
A Laravel package for implementing secure Model Context Protocol servers using Streamable HTTP and SSE transport, providing real-time communication and a scalable tool system for enterprise environments.
php
基于 PHP 实现的 MCP (Model Control Protocol) 服务器框架,通过注解优雅地定义 MCP 服务,支持 Tool、Prompt、Resource 三种处理器,支持Stdio、Sse 两种 transport。
mcp-profiler-bundle
The Symfony MCP Profiler Bundle mimics the WebProfiler Bundle. It bridges the gap between Profiler data and your favorite MCP-enabled AI-powered IDE.
elementor
Comprehensive Elementor MCP Server plugin.
mcp
Model Context Protocol for Hyperf