home / mcp / sdamgia mcp server
Provides an MCP server to query and fetch СДАМ ГИА problems, solutions, and answers across multiple subjects via flexible tools.
Configuration
View docs{
"mcpServers": {
"art22017-sdamgia-mcp-server": {
"command": "npx",
"args": [
"-y",
"sdamgia-mcp-server"
]
}
}
}You can use the Sdamgia MCP Server to enable large language models to search, retrieve, and format problems, solutions, and answers from the СДАМ ГИА platform. This server exposes a robust set of search and retrieval capabilities, supports multiple subjects, and outputs data in convenient formats for downstream processing or human-friendly display.
After you configure a client to connect to the MCP server, you can perform structured queries to locate and fetch СДАМ ГИА problems. Use the search tools to find problems by keywords or by text similarity, retrieve single or multiple problems with their conditions, solutions, and answers, and browse catalogs and categories to explore related items. Outputs can be consumed as JSON for programmatic workflows or as Markdown for quick review.
Prerequisites: ensure you have Node.js 18 or newer and a package manager such as npm or yarn installed.
Install the MCP server globally and prepare it for use by your MCP clients.
npm install -g sdamgia-mcp-server
npx sdamgia-mcp-server
# Or clone from source and build
# git clone https://github.com/art22017/sdamgia-mcp-server.git
# cd sdamgia-mcp-server
# npm install
# npm run build
# npm run startThe server supports multiple client configurations through MCP-compatible profiles. The following is a representative local/runtime configuration that enables a stdio-based connection using a common runtime command.
{
"mcpServers": {
"sdamgia": {
"type": "stdio",
"command": "npx",
"args": ["-y", "sdamgia-mcp-server"]
}
}
}Retrieve a specific problem by subject and ID, returning the full problem details including condition, solution, and answer.
Search for problems by text query within a subject, with optional limit and output format.
Find problems by condition text using fuzzy matching to handle paraphrased or OCR-imperfect text.
Fetch multiple problems in a single request by providing a list of problem IDs.
Retrieve the complete catalog structure for a given subject.
Get all problems from a specific catalog category with an optional limit.
Retrieve all problems belonging to a specific test by its ID.