Introduction
The DoiT Model Context Protocol (MCP) server integrates DoiT Cloud Intelligence and AI tools (like Cursor or Claude) that support SSE (Server-Sent Events) or STDIO (Standard Input/Output). This enables seamless connection with your existing systems and AI-assisted processes. It allows your clients to connect to the DoiT MCP server over the internet using standard web protocols. The DoiT MCP server maintains live connections to your DoiT Cloud Intelligence data, ensuring everyone has access to the same information and enabling near real-time access.
Before you connect, confirm your DoiT user has the Required permissions.
Once you have integrated your AI tool with 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. See Usage examples.
Authorizationβ
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:
-
Remote connectors (for example Claude or ChatGPT in the browser): The flow prompts you for your DoiT API key and your DoiT Customer ID.
-
Local STDIO clients (for example Cursor or Gemini CLI): You set
DOIT_API_KEYin the client configuration. See Connections. -
After you connect, what each tool can access still follows your Console role and API rules (in addition to the Required permissions above). See Authorization and security.
Connection methodsβ
You can connect to the DoiT MCP server remotely or locally. For example, you might choose to connect locally if you want to maximize speed and control for individual, machine-specific tasks and remotely if you need to share capabilities across a team, enable web-based AI agents, or scale for production workloads.