Find code entities that are semantically similar to a specific node
AI agents call get_similar_code to retrieve information from CodeRAG without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only query operation against the Neo4J knowledge graph to find semantically similar code entities. It retrieves information based on a search criterion (similarity to a node) but does not create, modify, delete, or execute anything. This is a classic Read category operation with low blast radius if misused — an AI agent querying for similar code presents minimal security risk.
From the tool's definition Tool description: 'Find code entities that are semantically similar to a specific node' — this is a retrieval/query operation that searches the knowledge graph for similar code entities without modifying, deleting, or executing any code.
Documented attack patterns abuse exactly the kind of access get_similar_code gives an agent:
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 get_similar_code:
{
"version": "1",
"default": "deny",
"tools": {
"get_similar_code": {}
}
}get_similar_code 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.
Find code entities that are semantically similar to a specific node. It is categorised as a Read tool in the CodeRAG MCP Server, which means it retrieves data without modifying state.
Register the CodeRAG MCP server in PolicyLayer and add a rule for get_similar_code: 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.
get_similar_code 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 get_similar_code 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 get_similar_code. 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.
get_similar_code 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.
Start from CodeRAG, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
38 CodeRAG tools catalogued and risk-classified — across an index of 43,000+ MCP servers.