Agentic AI is likely to reshape how users interact with their crypto wallets in the future – especially in trading and payments. While AI and blockchain executives note that it can be secure, it also does not come without a new set of risks.
Last week, Crypto Exchange Coinbase announced its new tool, Payment MCP, which AI agents are provided Access to the same Onchain financial tools that people use.
Announcing MCP payments, the easiest way for AI agents to get onchain via x402. 🚀
This allows LLM models like Claude, Gemini, and ChatGpt to gain access to Onchain tools like wallets, onramp, and payments without the need for an API key. 🧵 pic.twitter.com/msniaecx0o
– Coinbase Developer Platform🛡️ (@coinbasedev) October 22, 2025
When the tool is paired with an LLM like Claude, Gemini and Codex, they are allowed to Access crypto wallets and make payments autonomously, the coinbase developer platform said in a statement.
AI agents powered by MCP payments can pay, calculate, retrieve paywalled data, tip creators and manage several business operations through the X402 protocol, an open, web-native payment protocol that facilitates Instant StableCoin paymentsaccording to the Coinbase developer platform.
“This marks a new era of agent innovation where AI agents can act in the global economy,” Coinbase’s development platform said.
AI agent in crypto can be safe
Aaron Ratcliff, the properties lead at blockchain intelligence firm Merkle Science, told Cointelegraph that from a security standpoint, giving an AI agent access to your wallet adds a layer of trust to something designed to be untrustworthy.
It can be safe if the system is built correctly, but Ratcliff argued that “safety” ultimately depends on the user of the crypto.
“Safe use depends on users understanding how to prompt and on AI pulling blockchain data seamlessly. It also depends on trading credentials staying secure; if trading credentials leak, the damage writes itself.”
AI in your portfolio can add excessive security risks
An April survey of 2,632 crypto users from Crypto Data Aggregator Coingecko found that most users are comfortable with AI trading on their behalf; 87% said they would let AI agents Manage at least one tenth of their crypto portfolio.
Ratcliff says there are several security risks bad actors can be exploited if AI is used in one’s portfolio. Injecting a prompt or instruction may allow someone to hijack the system.
A man-in-the-middle attack, where the hacker inserts themselves between entities in a communication channel to steal data, can also redirect trades.
“AI can also deal with scam tokens, miss honeypots or rug-pulls, or handle slippage so users’ funds are badly burned,” Ratcliff added.
“I want proof that AI can catch front-running, apply slippage limits, scam tokens, and audit contracts in real time before it makes a trade. It should also sandbox signals, prevent injection, and block human access.”
At the same time, Ratcliff believes that compliance gaps can lead to issues, such as the absence of controls to prevent an AI from sending funds to a penal or an exchange.
Even if the AI has protections, attention is still paid
Speaking to Cointelegraph, Sean Ren, co-founder of the AI-native blockchain platform Sahara AI, said that in the case of Coinbase, the exchange tool uses model context protocols, “Which is the gold standard for security when set up correctly.”
“They essentially act as a gatekeeper between the AI model and your wallet. The agent can only perform specific, approved actions – such as checking balances or preparing a payment for you to confirm – rather than freely moving funds or changing wallet settings,” he said.
“Those actions are restricted by design, so even if someone tries to trick the AI with a prompt injection, for example, it cannot complete a transaction on its own,” Ren added.
However, Ren also said that Safer is by no means foolproof, and users still need to pay attention to whatever the AI agent is doing in their portfolio.
“Users still need to stay alert, double-check what they’re approving, and never assume the agent is automatically doing the right thing. You still need to review and sign transactions.”
It’s still early days for AI agents
Brian Huang, co-founder and CEO of Glider, an AI portfolio management platform, told Cointelegraph that core functionality, such as sending, exchanging, and lending, is a good place to start with agents, but it’s still early days in the space.
Related: AI agents need crypto to operate in financial markets: Coinbase exec
“These are simple actions that can be done with one click – you don’t ask your friends on Chatgpt, do you? Many of these actions take more time with agents,” he said.
“Agents, in contrast, are like assistants, we all know Defi is too complex to participate in. These agents help users land and feel guided through the process.”
Huang predicts that more sophisticated actions, such as portfolio management, rebalancing, and personalized financial advice, will likely follow and become more effective use cases.
“The customization that agents can provide here, the number of variables they can take into account, is far beyond what any human can provide,” he said.
Magazine: How do the world’s major religions view bitcoin and cryptocurrency?
