Carbon DeFi MCP Server

On-chain automated trading strategies (DEX) for AI agents. Create limit orders, range orders, recurring buy-low-sell-high strategies, and concentrated liquidity positions across Ethereum, Sei, Celo, TAC, and COTI. Unlike traditional AMMs and liquidity pools, Carbon lets you set asymmetric price ranges - your buy and sell orders are independent, not mirrored. Backtest any strategy against historical prices before going on-chain, explore market liquidity, find discount entry points, and swap tokens against Carbon DeFi's maker liquidity. 25 tools. Returns unsigned transactions — agents never hold funds or private keys. Zero gas on fills.

View on carbondefi.xyz

Documentation

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
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

{
  "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

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:

GET https://docs.carbondefi.xyz/rest-api/ai-agents-and-mcp-server.md?ask=<question>

The question should be specific, self-contained, and written in natural language. 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.