Search for casts by keyword (simplified implementation)
AI agents call search-casts to retrieve information from Farcaster MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves cast data based on keyword input. It has no side effects—it does not create, modify, delete, or execute code. The operation is purely informational, consistent with Read category tools like search, query, and fetch. The blast radius of misuse is minimal; an attacker could only access publicly available cast data on the Farcaster network.
From the tool's definition Tool name 'search-casts' and description 'Search for casts by keyword' indicate a query operation that retrieves data without modification.
Attacks that exploit this kind of access
Search for casts by keyword (simplified implementation). It is categorised as a Read tool in the Farcaster MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Farcaster MCP Server MCP server in PolicyLayer and add a rule for search-casts: 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 Farcaster MCP Server. Nothing to install.
search-casts 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 search-casts 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 search-casts. 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.
search-casts is provided by the Farcaster MCP Server MCP server (manimohans/farcaster-mcp). 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 →