Create or manage an exchange-side grid or DCA bot
Two or three companies' docs show a full fit.
What counts as done
The bot is created and visible in a list call with its parameters, and the create call either succeeds or returns an error naming the wrong field.
Measured, for our own tests: the bot is created in one create call. No docs we read state these figures, so they don't count against a listing here.
How agents ask for it: set up a grid bot on SUI perp between 3 and 4 dollars
, list my running grid bots
, amend the DCA bot's amount
Does the job 2
The docs show it meets the test above, and nothing we read says otherwise.
| Listing | Why |
|---|---|
| Bitget C BTG Technology Holdings Limited | Grid section has validate, create, modify, add investment, close and detail endpoints for grid and neutral grid bots; validate checks parameters without creating. source |
| Crypto.com Exchange API D Foris DAX Limited | cdcx bot create, list, pause, resume, update and terminate for DCA and GRID bots, in the mutate tier with terminate as dangerous. source |
Does the job, with a limit 3
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| Bybit C Bybit Virtual Asset Platform Operator L.L.C. S.P.C | Futures grid bot endpoints exist, but creating one through the MCP skill failed with 400006 naming no field and the correct schema was only in the TypeScript source (acc-17). source |
| Gate C Gate | AI hub tools create spot, margin, infinite and futures grid and martingale bots, list running ones and stop them; there is no amend tool and no first-hand success. source |
| OKX API B Aux Cayes FinTech Co. Ltd. | Grid and DCA endpoints and 18 bot tools exist, but creating a contract grid bot was refused with 51000 for an instrument the list and amend endpoints accept (acc-14); DCA amend is missing (acc-39). source |
Doesn't do this job 16
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| Binance API B Binance | No grid or DCA bot endpoints in the spot API reference or the MCP scopes. source |
| Bitfinex API C iFinex Inc. | No grid or DCA bot endpoints in the reference. source |
| Bithumb Open API D Bithumb Co., Ltd. | No bot endpoints; TWAP split orders are the only server-side strategy. source |
| Bitstamp API D Bitstamp Ltd. | No bot endpoints in the API reference. source |
| Coinbase Advanced Trade API B Coinbase, Inc. | No bot endpoints in the spec. source |
| Coinbase MCP server (Coinbase for Agents) C Coinbase, Inc. | No bot tools. source |
| Deribit C Deribit FZE | No grid or DCA bot methods. source |
| dYdX BB dYdX Trading Inc. | No server-side bots. source |
| Gemini Exchange API BB Gemini Trust Company, LLC | No bot endpoints. source |
| HTX trading API E HTX | Grid orders are listed as not supported by API. source |
| Hyperliquid D Hyperliquid Labs | No server-side grid or DCA bots; TWAP and trailing stop are order types. source |
| Kraken API BB Payward, Inc. | Grid and DCA skills run in the agent, not on the exchange. source |
| KuCoin C KuCoin | No bot endpoints in the reference navigation. source |
| MEXC API C MEXC (Comoros) Ltd | No bot endpoints. source |
| Uniswap Trading API B Uniswap Labs | No server-side bots. source |
| Upbit Open API C Dunamu Inc. | No bot endpoints. source |
What stops agents finishing
- create refused for an instrument the list and amend endpoints accept
- documented parameter names and types differ from the API's
Around it
Before: crypto-exchanges.mcp-from-assistant, crypto-exchanges.market-data-read. After: crypto-exchanges.read-back-state.
Where this comes from
Weight 2 of 100 in Crypto exchanges: 2 of 40 accounts, both failures on create (Bybit 400006, OKX 51000)
The same as data: /api/v1/use-cases/crypto-exchanges.exchange-bots.json, or the MCP tool get_use_case with id crypto-exchanges.exchange-bots. Other jobs in this category: /api/v1/niches?category=crypto-exchanges.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.