AI agents invoke switch-chain to trigger actions in MetaMask MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Switching the active blockchain network changes the execution context for all subsequent operations (transactions, contract calls, etc.). It triggers an external operation in MetaMask that affects which chain future actions are performed on.
From the tool's definition Switch the target chain
Documented attack patterns abuse exactly the kind of access switch-chain gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MetaMask MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for switch-chain:
{
"version": "1",
"default": "deny",
"tools": {
"switch-chain": {
"limits": [
{
"counter": "switch-chain_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}switch-chain stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Switch the target chain. It is categorised as a Execute tool in the MetaMask MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MetaMask MCP server in PolicyLayer and add a rule for switch-chain: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MetaMask MCP. Nothing to install.
switch-chain is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the switch-chain rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for switch-chain. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
switch-chain is provided by the MetaMask MCP server (xiawpohr/metamask-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MetaMask MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
29 MetaMask MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.