> For the complete documentation index, see [llms.txt](https://www.cakewalk.security/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.cakewalk.security/docs/open-api-and-mcp/introduction-to-mcp.md). # MCP ### What is MCP? Model Context Protocol (MCP) is an open standard by Anthropic that lets AI assistants connect to external tools and data sources. Think of it as a universal plug that lets your AI assistant talk to other software. Cakewalk runs an MCP server. When you connect your AI assistant to it, the assistant can query your users, apps and access requests directly from Cakewalk, using natural language. *** ### What Can You Do With It? Once connected, you can ask your AI assistant things like: * "Who has access to GitHub in our org?" * "Show me all pending access requests." * "What permission levels does Figma have?" * "Look up Jane's profile and current app access." * "Which apps does the marketing team use?" Your assistant calls Cakewalk behind the scenes, gets the answer, and responds in plain language. *** ### Who Is This For? MCP is useful for anyone who already works inside an AI assistant and wants quick answers about access, without switching to the Cakewalk dashboard. * **IT and Security teams** running audits or reviewing access * **Engineering leads** checking who has access to dev tools * **Managers** looking up their team's app access during onboarding or reviews *** ### How It Works (High Level) 1. You add Cakewalk's MCP server URL to your AI assistant's settings. 2. You authorize the connection through Cakewalk's OAuth consent screen. 3. You choose which scopes (permissions) the assistant gets: users, apps, requests. 4. Your assistant can now query Cakewalk directly. No API keys. No code. Setup takes a few minutes. {% hint style="info" %} MCP gives your AI assistant **read access** to Cakewalk data based on the scopes you authorize. It does not make changes to your workspace. {% endhint %} *** ### Supported Clients Cakewalk's MCP server works with any MCP-compatible client that supports OAuth, including: * **Cursor** (one click install) * **Claude Desktop** (CLI or manual) See [Connect an MCP Client](/docs/open-api-and-mcp/introduction-to-mcp/connect-an-mcp-client.md) for setup instructions per client. *** ### Next Steps * [Connect an MCP Client](/docs/open-api-and-mcp/introduction-to-mcp/connect-an-mcp-client.md): Setup instructions for every supported client. * [MCP Tool Reference](/docs/open-api-and-mcp/introduction-to-mcp/mcp-tool-reference.md): Full list of available tools, scopes and parameters. --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://www.cakewalk.security/docs/open-api-and-mcp/introduction-to-mcp.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.