# MCP

> Connect AI agents to Cloud Management Platform (CMP) using the Model Context Protocol

---

Site [llms.txt](/llms.txt)

---

[Model Context Protocol](https://modelcontextprotocol.io/docs/getting-started/intro) (MCP) is an open standard that enables AI agents to call structured tools exposed by an MCP server. By connecting an MCP-compatible AI agent to CMP, you can manage cloud infrastructure, order from the catalog, and run custom operations using natural language.

All operations are scoped to the authenticated user's permissions, so agents can only see and act on resources the user has access to in CMP.

## Supported clients

CMP's MCP server is compatible with MCP clients that support OAuth 2.0 with Authorization Code Flow. Currently supported clients:

- [OpenCode](https://opencode.ai/docs) (recommended)
- [Claude Desktop](https://code.claude.com/docs/en/desktop-quickstart)
- [Cursor](https://cursor.com/docs)
- [Visual Studio Code](https://code.visualstudio.com/docs)

For connection and authentication instructions, see [MCP server integration](/docs/cmp/developer-resources/mcp/server/).

---

Section pages:

- [MCP server integration](/docs/cmp/developer-resources/mcp/server/): Connect an AI agent to the Cloud Management Platform (CMP) Model Context Protocol server and interact with your cloud infrastructure using natural language
- [MCP catalog operations](/docs/cmp/developer-resources/mcp/catalog-operations/): Order, track, and approve catalog items using natural language from any MCP-compatible AI agent
- [MCP custom tools](/docs/cmp/developer-resources/mcp/custom-tools/): Build your own agent tools using MCP Tool Actions and existing server and resource actions