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

# AI Agents & MCP Server

Carbon DeFi has an MCP (Model Context Protocol) server that allows AI agents to create and manage on-chain trading strategies programmatically.

{% hint style="info" %}
Experimental — still being worked on. Use at your own risk.
{% endhint %}

* MCP endpoint: [https://mcp.carbondefi.xyz](https://mcp.carbondefi.xyz/)
* REST API: <https://mcp.carbondefi.xyz/tools/:toolName>
* OpenAPI spec: <https://mcp.carbondefi.xyz/openapi.json>
* Plugin manifest: <https://mcp.carbondefi.xyz/.well-known/ai-plugin.json>
* Server info: <https://mcp.carbondefi.xyz/info>

#### Claude Desktop setup

Add this to your Claude Desktop config to connect:

json

```json
{
  "mcpServers": {
    "carbon-defi": {
      "command": "npx",
      "args": ["mcp-remote", "https://mcp.carbondefi.xyz"]
    }
  }
}
```

#### Key conventions for agents

* All write operations return unsigned transactions — the user always signs and broadcasts
* Always call get\_strategies first to check existing positions
* Market price is auto-fetched from the Carbon API — no need to provide it manually
* Prices are always in quote token per 1 base token
* buy\_budget is always in quote token; sell\_budget is always in base token
* Check the warnings array in every response before presenting a transaction

<br>


---

# 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://docs.carbondefi.xyz/rest-api/ai-agents-and-mcp-server.md?ask=<question>&goal=<endgoal>
```

`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.