AI Agents & LLM Apps

Set up your API key

Build faster with AI

TL;DR
Connect via MCP for zero-code data access, use the SDK for function calling in custom agents, and query /simple/price, /search, /search/trending, and onchain endpoints for real-time context.

Replace YOUR_API_KEY in the examples below with your actual key. Get one here →

Option 1: MCP Server (Zero-Code)

The fastest way to give an AI agent access to CoinGecko data. No SDK code needed — the agent calls tools directly through the Model Context Protocol.

Connect the MCP server

Claude Code
Cursor / IDE
Python (MCP Client)

claude mcp add --transport http \
  coingecko https://mcp.api.coingecko.com/mcp

For higher limits, use https://mcp.pro-api.coingecko.com/mcp and authenticate via /mcp.

Add to ~/.cursor/mcp.json (or your IDE’s MCP config):

{
  "mcpServers": {
    "coingecko": {
      "command": "npx",
      "args": ["mcp-remote", "https://mcp.api.coingecko.com/mcp"]
    }
  }
}

from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

async with streamablehttp_client(
    "https://mcp.api.coingecko.com/mcp"
) as (read, write, _):
    async with ClientSession(read, write) as session:
        await session.initialize()
        tools = await session.list_tools()

Full setup for all platforms: CoinGecko MCP → | MCP Tools →

Add Docs MCP (optional)

Let your agent search CoinGecko documentation for endpoint details and parameter info.

claude mcp add --transport http \
  coingecko-docs https://docs.coingecko.com/mcp

Docs MCP →

Ask your agent

The agent now has access to 85+ CoinGecko tools. Try:

“What’s the current price of Bitcoin, Ethereum, and Solana?”
“Show me the top 10 trending pools on Base”
“Find all tokens related to ‘AI’ and get their market data”

Option 2: SDK Function Calling (Custom Agents)

For custom AI agents where you control the tool definitions and execution flow — use the SDK as the function calling backend.

Install the SDK

pip install coingecko_sdk

npm install @coingecko/coingecko-typescript

Initialize the client

import os
from coingecko_sdk import Coingecko

client = Coingecko(
    pro_api_key=os.environ.get("COINGECKO_PRO_API_KEY"),
    environment="pro",  # or "demo" with demo_api_key
)

import Coingecko from '@coingecko/coingecko-typescript';

const client = new Coingecko({
  proAPIKey: process.env['COINGECKO_PRO_API_KEY'],
  environment: 'pro',  // or 'demo' with demoAPIKey
});

Full SDK setup: Python → | TypeScript →

Define tools for your LLM

Map SDK methods to tool definitions your LLM can call. Example tool schema:

{
  "name": "get_crypto_price",
  "description": "Get current prices for one or more cryptocurrencies",
  "parameters": {
    "type": "object",
    "properties": {
      "ids": {
        "type": "string",
        "description": "Comma-separated CoinGecko coin IDs (e.g. bitcoin,ethereum)"
      },
      "vs_currencies": {
        "type": "string",
        "description": "Comma-separated target currencies (e.g. usd,eur)"
      }
    },
    "required": ["ids", "vs_currencies"]
  }
}

Execute tool calls

When the LLM returns a tool call, execute it against the SDK:

def execute_tool(name, args):
    if name == "get_crypto_price":
        return client.simple.price.get(**args)
    elif name == "search_coins":
        return client.search.get(**args)
    elif name == "get_trending":
        return client.search.trending.get()

async function executeTool(name: string, args: Record<string, any>) {
  if (name === 'get_crypto_price') {
    return client.simple.price.get(args);
  } else if (name === 'search_coins') {
    return client.search.get(args);
  } else if (name === 'get_trending') {
    return client.search.trending.get();
  }
}

All available methods: TypeScript → | Python →

Key Endpoints for AI Agents

The most useful endpoints for agent tool definitions — each maps to a common user intent.

Intent	Endpoint	What it returns
”What’s the price of X?”	/simple/price	Spot prices with optional market cap, volume, 24h change
”Find tokens matching Y”	/search	Coins, categories, and markets matching a query
”What’s trending?”	/search/trending	Top trending coins, NFTs, and categories (24h)
“Show me market data”	/coins/markets	Bulk market data — rankings, sparklines, price changes
”Price of this token address”	/onchain/…/token_price	Onchain token price by contract address
”Token info for address”	/onchain/…/tokens/{addr}	Token metadata, price, volume, and top pools
”Trending DEX pools”	/onchain/…/trending_pools	Hottest liquidity pools across all networks

Use /search as your agent’s resolver — when a user mentions a coin by name or symbol, search first to get the correct CoinGecko ID, then pass it to other endpoints.

Prompt Engineering Tips

Always resolve IDs first. Coin names are ambiguous — use /search or /coins/list to resolve to a CoinGecko ID before querying price or market data.
Include units in responses. When returning prices, always include the currency (e.g. “$67,432 USD” not just “67432”).
Handle missing data. Not all coins have market cap, volume, or contract addresses. Instruct your agent to check for null fields.
Rate limit awareness. Tell your agent to batch requests where possible (e.g. ids=bitcoin,ethereum,solana in one call instead of three).

SDK Prompts

AI prompt rules for generating correct CoinGecko SDK code.

Get Started

Guides

Resources

Set up your API key

Build faster with AI

Option 1: MCP Server (Zero-Code)

Option 2: SDK Function Calling (Custom Agents)

Key Endpoints for AI Agents

Prompt Engineering Tips

SDK Prompts

Set up your API key

Build faster with AI

​Option 1: MCP Server (Zero-Code)

​Option 2: SDK Function Calling (Custom Agents)

​Key Endpoints for AI Agents

​Prompt Engineering Tips

SDK Prompts

Option 1: MCP Server (Zero-Code)

Option 2: SDK Function Calling (Custom Agents)

Key Endpoints for AI Agents

Prompt Engineering Tips