AI agents call maple_marketplace_search to retrieve information from Maple without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries data from MCP marketplaces to discover available servers. It is a read-only operation with no side effects—it gathers information to inform routing decisions but does not execute code, modify data, delete resources, or move funds.
From the tool's definition Tool name contains 'search' and description states it 'Search[es] MCP marketplaces...and return[s]' information about connectable servers. No modification, deletion, execution, or financial operations are performed.
Attacks that exploit this kind of access
Search MCP marketplaces (Smithery and MCP.so) and return connectable servers Maple can route through firewall policy. It is categorised as a Read tool in the Maple MCP Server, which means it retrieves data without modifying state.
Register the Maple MCP server in PolicyLayer and add a rule for maple_marketplace_search: 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 Maple. Nothing to install.
maple_marketplace_search 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 maple_marketplace_search 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 maple_marketplace_search. 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.
maple_marketplace_search is provided by the Maple MCP server (omar2001ramadan/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 →