> For the complete documentation index, see [llms.txt](https://docs.unitlab.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.unitlab.ai/api-sdk-cli/mcp.md).

# MCP

- [Unitlab MCP](https://docs.unitlab.ai/api-sdk-cli/mcp/overview.md): Connect your AI assistant to Unitlab with Model Context Protocol to organize data, annotate across modalities, automate workflows, and export datasets.
- [MCP quickstart](https://docs.unitlab.ai/api-sdk-cli/mcp/quickstart.md): Connect an assistant, create a project from an image folder, label selected object classes, and review the results in Unitlab.
- [Connect your AI assistant with MCP](https://docs.unitlab.ai/api-sdk-cli/mcp/connect-your-assistant.md): Set up Unitlab MCP in Claude, Claude Code, ChatGPT, Codex, Cursor, Gemini CLI, VS Code, or another compatible client.
- [MCP authentication and permissions](https://docs.unitlab.ai/api-sdk-cli/mcp/authentication-and-permissions.md): Understand OAuth, workspace scope, read and write access, role permissions, connection controls, and revocation in Unitlab MCP.
- [MCP tool reference](https://docs.unitlab.ai/api-sdk-cli/mcp/tools.md): Browse all 97 Unitlab MCP tools for projects, data, annotation, AI labeling, workflows, quality, releases, and administration.
- [MCP workflows and automation](https://docs.unitlab.ai/api-sdk-cli/mcp/workflows.md): Use Unitlab MCP for folder uploads, multimodal annotation, AI labeling, model workflows, review, quality checks, and dataset exports.
- [MCP troubleshooting and FAQs](https://docs.unitlab.ai/api-sdk-cli/mcp/troubleshooting.md): Fix Unitlab MCP sign-in, permissions, uploads, stale annotation revisions, AI model runs, rate limits, and export issues.