search_funds
AI agents call search_funds to retrieve information from Crypto Funds MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'search_funds' tool appears to query or retrieve cryptocurrency fund information from the server, consistent with the Read category: it retrieves or queries data with no side effects. Confidence is slightly reduced due to the empty description, but the name and context of sibling tools strongly indicate a retrieval operation.
From the tool's definition Tool name is 'search_funds' with no description provided. Based on naming convention and the sibling tools (get_all_funds, get_fund_basic, get_fund_detail, get_fund_team) which are all Read operations that retrieve cryptocurrency fund data, this tool is…
Attacks that exploit this kind of access
search_funds. It is categorised as a Read tool in the Crypto Funds MCP MCP Server, which means it retrieves data without modifying state.
Register the Crypto Funds MCP server in PolicyLayer and add a rule for search_funds: 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 Crypto Funds MCP. Nothing to install.
search_funds 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_funds 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_funds. 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_funds is provided by the Crypto Funds MCP server (kukapay/crypto-funds-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 →