Introduction
The DoiT Model Context Protocol (MCP) server integrates DoiT Cloud Intelligence with AI tools that support the MCP protocol over remote Streamable HTTP or local (stdio) connections. Clients can reach your DoiT Cloud Intelligence data using standard web protocols or a locally launched server process.
Before you connect, confirm your DoiT user has the Required permissions.
Once you have connected your AI tool to the DoiT MCP server, you can ask questions or make requests related to DoiT Cloud Intelligence data. Your AI tool may be integrated with other MCP servers. To ensure your request yields the intended results, you should frame your request with relevant contextual cues for the DoiT MCP server. Usage examples show common queries.
Authorization
What you provide at connect time and what the MCP server can do afterward depends on your client and your DoiT account. Be aware of the following:
-
Streamable HTTP: Uses a browser-based DoiT sign-in and consent flow. Local stdio: Authenticates with a personal API token via
DOIT_API_KEY. See Connection methods. -
Once connected, the tools available to you depend on the permissions assigned to your signed-in user (HTTP) or API token (stdio), as well as the rules governing each operation in the DoiT API. Authorization and security describes how MCP access is enforced.
Connection methods
DoiT supports remote Streamable HTTP and local stdio. Choose the method your client supports. The Connections page describes both methods and includes client examples.
The legacy SSE endpoint (https://mcp.doit.com/sse) is deprecated. It does not expose the full tool set. Use Streamable HTTP or stdio for new connections. See Legacy SSE.