CoinGecko for AI agents
CoinGecko provides cryptocurrency prices, market data, and onchain data, giving a team a single source for tracking coins and token pools. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in CoinGecko.
Check a coin's current price
Check a coin's current price and market cap before including it in a report.
Pull a coin's price history
Pull a coin's market chart over a date range to analyze recent price movement.
Look up trending assets
Look up which assets are trending right now before deciding what to research next.
18 CoinGecko actions, graded by risk.
Every CoinGecko action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
18Look things up. Allowed by default.
- coingecko.get_coin_ohlcGet Coin OHLC
- coingecko.search_assetsSearch Assets
- coingecko.get_coin_pricesGet Coin Prices
- coingecko.get_coin_detailsGet Coin Details
- coingecko.list_coin_marketsList Coin Markets
- coingecko.list_onchain_poolsList Onchain Pools
- coingecko.get_trending_assetsGet Trending Assets
- coingecko.search_onchain_poolsSearch Onchain Pools
- coingecko.get_coin_market_chartGet Coin Market Chart
- coingecko.list_onchain_networksList Onchain Networks
- coingecko.get_global_market_dataGet Global Market Data
- coingecko.get_onchain_pool_ohlcvGet Onchain Pool OHLCV
- coingecko.list_new_onchain_poolsList New Onchain Pools
- coingecko.get_onchain_token_pricesGet Onchain Token Prices
- coingecko.list_onchain_pool_tradesList Onchain Pool Trades
- coingecko.list_trending_onchain_poolsList Trending Onchain Pools
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
CoinGecko in three steps.
- 01Your users connect CoinGeckoThey add their CoinGecko api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls CoinGecko through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('coingecko', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How CoinGecko connects.
Users add their CoinGecko api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same CoinGecko connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use CoinGecko from any agent.
CoinGecko and Arc0, answered.
Can I use CoinGecko with Claude, ChatGPT or Cursor?
Yes. Connect CoinGecko to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the CoinGecko actions you allow.
How do users connect CoinGecko?
Users add their CoinGecko api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which CoinGecko actions can my agent take?
18 in total: 18 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in CoinGecko?
Yes. Allow read actions and deny writes in the CoinGecko policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call CoinGecko too?
Yes. The same CoinGecko connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug CoinGecko into your agent.
Your users connect CoinGecko once, under your brand. Your agent gets 18 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan