Natural language search using semantic embeddings.
AI agents call semantic-search to retrieve information from APLCart MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from a read-only idiom collection. It has no side effects—it does not create, modify, delete, execute code, or perform financial operations. The natural language search capability is a lookup mechanism that returns matching results only.
From the tool's definition The tool performs 'Natural language search using semantic embeddings' on the 'APLCart idiom collection'. This is a search operation that queries and retrieves data without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Natural language search using semantic embeddings. It is categorised as a Read tool in the APLCart MCP Server MCP Server, which means it retrieves data without modifying state.
Register the APLCart MCP Server MCP server in PolicyLayer and add a rule for semantic-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 APLCart MCP Server. Nothing to install.
semantic-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 semantic-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 semantic-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.
semantic-search is provided by the APLCart MCP Server MCP server (xpqz/ac-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 →