semantic_search

THE RISK

Low Risk

Why semantic_search needs a policy

This tool retrieves and queries information from the codebase knowledge graph based on semantic meaning. It has no side effects—it does not create, modify, delete, or execute code. The operation is read-only, similar to a search or query function. The blast radius of misuse is minimal since the tool cannot alter state or trigger external operations.

From the tool's definition Tool performs semantic search to 'find functionality' using 'natural language queries' without modifying any data in the knowledge graph.

Documented attack patterns abuse exactly the kind of access semantic_search gives an agent:

POLICY

How to control semantic_search

PolicyLayer is an MCP gateway — it sits between your AI agents and CodeRAG, and nothing reaches the server without passing your rules. This is the rule we recommend for semantic_search:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "semantic_search": {}
  }
}

semantic_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register CodeRAG — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More CodeRAG tools

Destructive clear_git_cache Clear all cached Git repositories to free up disk space. Destructive delete_edge Delete an edge by ID Destructive delete_node Delete a code node by ID Write initialize_semantic_search Initialize semantic search infrastructure including vector indexes Write scan_dir Scan a directory for source files and populate the graph Write scan_remote_repo Scan a remote Git repository and populate the graph database. Supports GitHub, GitLab, Bit Write add_edge Add a relationship edge between two nodes Write add_file Parse a single source file and add its entities to the graph

All 38 CodeRAG tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about semantic_search

What does the semantic_search tool do? +

Search for code using natural language queries to find functionality by meaning rather than syntax. It is categorised as a Read tool in the CodeRAG MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on semantic_search? +

Register the CodeRAG 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 CodeRAG. Nothing to install.

What risk level is semantic_search? +

semantic_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit semantic_search? +

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.

How do I block semantic_search completely? +

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.

What MCP server provides semantic_search? +

semantic_search is provided by the CodeRAG MCP server (jonnoc/coderag). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every CodeRAG tool call.

Start from CodeRAG, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →