Sugra API is a Model Context Protocol (MCP) server: Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog. In practice that means any MCP-compatible AI assistant can call Sugra API's tools directly — the model decides when to use them in a conversation or agent run.
You can run Sugra API two ways: connect to the hosted endpoint at https://app.sugra.ai/mcp with no local install, or run it on your own machine via the Python package sugra-api-mcp (via uvx). Configuration happens through environment variables — you'll need SUGRA_API_KEY. The current release is v0.9.1, published under the MIT license, with source at Sugra-Systems/sugra-api-mcp on GitHub.
Sugra API is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Sugra API for sugra.ai, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
