Batch fetch coins by address and chainId.
AI agents call zora_get_coins to retrieve information from Zora Coins MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query operation to retrieve coin data in batch. It fetches information based on provided addresses and chain IDs without creating, modifying, deleting, or executing any operations. The 'fetch' verb and lack of any state-changing capability classify it as a Read operation with low severity.
From the tool's definition Tool name 'zora_get_coins' and description 'Batch fetch coins by address and chainId' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Batch fetch coins by address and chainId. It is categorised as a Read tool in the Zora Coins MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Zora Coins MCP Server MCP server in PolicyLayer and add a rule for zora_get_coins: 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 Zora Coins MCP Server. Nothing to install.
zora_get_coins 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 zora_get_coins 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 zora_get_coins. 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.
zora_get_coins is provided by the Zora Coins MCP Server MCP server (r4topunk/zora-coins-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →