Call a read-only function on a contract, and returning the response.
AI agents call read-contract to retrieve information from MetaMask MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from blockchain contracts without modifying state or executing side effects. It is a pure query operation that fetches information. While the MetaMask context involves blockchain and crypto, a read-only contract call has no capacity to transfer funds, modify data, or execute state-changing operations. The risk is minimal and confined to the Read category.
From the tool's definition Tool name is 'read-contract' and description states 'Call a read-only function on a contract, and returning the response.' The explicit mention of 'read-only' and 'returning the response' indicates data retrieval with no state modification.
Documented attack patterns abuse exactly the kind of access read-contract 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 read-contract:
{
"version": "1",
"default": "deny",
"tools": {
"read-contract": {}
}
}read-contract is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Call a read-only function on a contract, and returning the response. It is categorised as a Read tool in the MetaMask MCP MCP Server, which means it retrieves data without modifying state.
Register the MetaMask MCP server in PolicyLayer and add a rule for read-contract: 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.
read-contract is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the read-contract 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 read-contract. 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.
read-contract 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.