Get the FREE Ultimate OpenClaw Setup Guide →

sdamgia

MCP (Model Context Protocol) server for interacting with the СДАМ ГИА educational platform. This server enables LLMs to search and retrieve exam problems, solutions, and answers across multiple subjects.

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio art22017-sdamgia-mcp-server npx -y sdamgia-mcp-server

How to use

The sdamgia MCP server provides programmatic access to the СДАМ ГИА dataset, enabling LLMs to search for problems, retrieve full problem details, and navigate catalogs across multiple subjects. Through the exposed MCP tools you can perform smart searches by text, fuzzy condition matching, fetch single or multiple problems, and explore problem catalogs and categories. Outputs can be returned in JSON for easy ingestion by a model or in Markdown for human-readable responses. This makes it suitable for building tutoring assistants, test prep workflows, or automated problem-solving demonstrations. To use, configure the MCP server in your environment, start it, and invoke the available tools from your MCP client (e.g., Claude, Gemini, Kilocode, or custom integrations).

How to install

Prerequisites:

  • Node.js 18+ or 20+
  • npm or yarn

Via npm (recommended):

npm install -g sdamgia-mcp-server

Or run without installation via npx:

npx sdamgia-mcp-server

From source:

git clone https://github.com/art22017/sdamgia-mcp-server.git
cd sdamgia-mcp-server
npm install
npm run build

Once installed or built, you can start the server and configure MCP clients as described in the README.

Additional notes

Tips and notes:

  • The server supports multiple subjects (math, mathb, rus, phys, chem, bio, geo, hist, soc, inf, en, de, fr, sp, lit). Use the subject code with each tool.
  • When using text-based search (sdamgia_search_problems) you can tune limit and response_format to tailor results for UI or automated processing.
  • For fuzzy matching (sdamgia_search_by_text), you can adjust threshold to control similarity sensitivity.
  • The tools support JSON or Markdown outputs; prefer JSON for downstream parsing in agents.
  • If you run into port or network issues, ensure your environment can reach the MCP server and that the npx package name is resolvable in your npm registry. For CLI-based usage, you can embed the command strings in your MCP client configurations exactly as shown in the examples (npx -y sdamgia-mcp-server).
  • The provided configuration snippets show common MCP client integrations (Claude, Cursor, Kilocode, Google Antigravity, Gemini CLI). Use the relevant snippet to create or update your mcp.json or equivalent config in your environment.
  • The MCP Inspector command helps validate wiring: npx @modelcontextprotocol/inspector npx -y sdamgia-mcp-server

Related MCP Servers

Sponsor this space

Reach thousands of developers