Search code by meaning using AI embeddings
AI agents call search to retrieve information from Smart Code Search MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that searches and retrieves code information using AI embeddings. It has no side effects, does not modify data, execute commands, or perform destructive operations. The tool merely returns search results based on semantic similarity, making it a standard Read category tool with low risk.
From the tool's definition Tool description states 'Search code by meaning using AI embeddings' and server description emphasizes 'semantic code search', 'find code', and 'symbol analysis'. The tool retrieves and queries code data without modifying, deleting, or executing it.
Attacks that exploit this kind of access
Search code by meaning using AI embeddings. It is categorised as a Read tool in the Smart Code Search MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Smart Code Search MCP Server MCP server in PolicyLayer and add a rule for 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 Smart Code Search MCP Server. Nothing to install.
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 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 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.
search is provided by the Smart Code Search MCP Server MCP server (stevenjjobson/scs-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 →