# MCP Server (Docs)

MCP Server (Docs) lets AI tools search Treasure AI documentation and discover API references directly, so agents answer with current, accurate information instead of relying on training data that may be outdated. Use it when an agent needs to look up a concept, check an API parameter, or find the right documentation page while you work.

The server is registered at: `https://docs.treasure.ai/mcp`

## Available Tools

### Documentation Tools

| Tool | Parameters | Description |
|  --- | --- | --- |
| `list-apis` | `name?: string` | Lists available APIs with their context and purpose. |
| `get-endpoints` | `name: string` | Returns all endpoints and their descriptions for a specific API. |
| `get-endpoint-info` | `name: string`, `path: string`, `method: string` | Returns comprehensive information about a specific endpoint, including parameters, security, and examples. |
| `get-security-schemes` | `name: string` | Gets the security schemes for a specific API. |
| `get-full-api-description` | `name: string` | Returns the complete OpenAPI description. |


### Search Tools

| Tool | Parameters | Description |
|  --- | --- | --- |
| `search` | `query: string` | Searches documentation and returns relevant content for a query. |


## Connect Your Tool

Claude Code, VS Code, and Cursor can all connect to MCP Server (Docs). See [Connect Your AI Coding Tool](/getting-started/ai#connect-your-ai-coding-tool) for tool-specific setup steps.

OpenAI Codex
Documentation search over HTTP is not currently documented for Codex. See [Connecting OpenAI Codex to Treasure AI](/getting-started/ai/openai-codex) for the platform-operations setup that is supported.

## Next Steps

- [MCP Server (Platform)](/getting-started/ai/mcp-server-platform) — query and operate on your Treasure AI data
- [Connect Your AI Coding Tool](/getting-started/ai#connect-your-ai-coding-tool)
- [Model Context Protocol (MCP)](https://modelcontextprotocol.io/)