> For the complete documentation index, see [llms.txt](https://missiveapp.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://missiveapp.com/docs/ai.md). # AI - [Overview](https://missiveapp.com/docs/ai/overview.md): Missive's AI assistant drafts replies, searches your emails and calendar, looks up contacts, and finds relevant canned responses. Powered by OpenAI, Anthropic Claude, or Google Gemini. - [Setting up AI](https://missiveapp.com/docs/ai/setup.md): Connect one or more AI providers to use AI features in Missive. - [OpenAI](https://missiveapp.com/docs/ai/setup/openai.md): Connect your OpenAI account to use GPT models in Missive. - [Anthropic Claude](https://missiveapp.com/docs/ai/setup/anthropic.md): Connect your Anthropic account to use Claude models in Missive. - [Google Gemini](https://missiveapp.com/docs/ai/setup/gemini.md): Connect your Google AI account to use Gemini models in Missive. - [Using AI](https://missiveapp.com/docs/ai/using-ai.md): Learn how to use the AI assistant, prompts, and instructions in Missive. - [Assistant](https://missiveapp.com/docs/ai/using-ai/assistant.md): Missive's AI assistant understands your full conversation, searches your emails and calendar, and helps you draft replies from the sidebar. - [Prompts](https://missiveapp.com/docs/ai/using-ai/prompts.md): Create reusable AI actions you can run on messages or drafts. - [Managing shortcuts](https://missiveapp.com/docs/ai/using-ai/shortcuts.md): Control which AI prompts appear as quick actions in your interface. - [Instructions](https://missiveapp.com/docs/ai/using-ai/instructions.md): Define AI behavior guidelines that apply to every assistant conversation across your organization. - [AI FAQ](https://missiveapp.com/docs/ai/using-ai/faq.md): Common questions about AI features in Missive. - [MCP](https://missiveapp.com/docs/ai/mcp.md): Missive uses MCP in two directions: the assistant reaching out to third-party apps, and AI apps like Claude and ChatGPT reaching into your Missive data. - [MCP integrations](https://missiveapp.com/docs/ai/mcp/integrations.md): Connect Missive AI to Notion, Linear, Attio, HubSpot, Stripe, Todoist, ClickUp, and custom MCP servers. - [MCP server](https://missiveapp.com/docs/ai/mcp/server.md): Connect Claude, ChatGPT, or any other MCP client to Missive and work with your conversations, contacts, and calendar from outside Missive. - [Connecting an AI app](https://missiveapp.com/docs/ai/mcp/server/connect.md): Install the Missive app in Claude or ChatGPT, or add it as a custom connector in any MCP client, then approve the permissions it asks for. - [Permissions and scopes](https://missiveapp.com/docs/ai/mcp/server/permissions.md): What each MCP permission grants, which actions it unlocks, and how to give an AI app only the access it needs. - [Managing connected apps](https://missiveapp.com/docs/ai/mcp/server/connected-apps.md): See which AI apps have access to your Missive account, what they can do, when they last used it, and how to revoke them. - [Admin controls](https://missiveapp.com/docs/ai/mcp/server/admin.md): Turn Missive's MCP server on or off for your organization, and understand what it means for members who belong to more than one. - [MCP server FAQ](https://missiveapp.com/docs/ai/mcp/server/faq.md): Common questions and connection problems with Missive's MCP server. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://missiveapp.com/docs/ai.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.