Performs intelligent hybrid code search combining semantic understanding with exact text matching. Ideal for finding code by meaning (e.g.,
AI agents call a_semantic_search to retrieve information from Smart Coding MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches existing code using semantic embeddings and text matching. It has no side effects: it does not create, modify, delete, or execute any code. The description emphasizes search and discovery only. The related tools (indexing, cache clearing, status checks) support read-only operations.
From the tool's definition Tool performs 'intelligent hybrid code search' and 'finding code by meaning' — purely a query/retrieval operation with no modification, deletion, or execution capabilities.
Documented attack patterns abuse exactly the kind of access a_semantic_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Smart Coding MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for a_semantic_search:
{
"version": "1",
"default": "deny",
"tools": {
"a_semantic_search": {}
}
}a_semantic_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Performs intelligent hybrid code search combining semantic understanding with exact text matching. Ideal for finding code by meaning (e.g.,. It is categorised as a Read tool in the Smart Coding MCP MCP Server, which means it retrieves data without modifying state.
Register the Smart Coding MCP server in PolicyLayer and add a rule for a_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 Smart Coding MCP. Nothing to install.
a_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 a_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 a_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.
a_semantic_search is provided by the Smart Coding MCP server (omar-haris/smart-coding-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Smart Coding MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Smart Coding MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.