Semantic (embedding‑based) code search using ChromaDB.
AI agents call semantic_search to retrieve information from Cursor MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a code index to find semantically similar code passages. It retrieves information without creating, modifying, deleting, or executing any code or commands. The blast radius of misuse is minimal; an AI agent could retrieve irrelevant or sensitive code, but cannot alter it or trigger external effects. This is a classic Read operation.
From the tool's definition Tool performs 'Semantic (embedding‑based) code search using ChromaDB' — a query and retrieval operation with no modification or execution of code. The description explicitly frames it as a search function, which is a read-only data retrieval operation.
Attacks that exploit this kind of access
Semantic (embedding‑based) code search using ChromaDB. It is categorised as a Read tool in the Cursor MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cursor 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 Cursor 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 Cursor MCP Server MCP server (tariqnasheed/cursor_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 →