Performs a vector similarity search across all indexed files and code entities (functions, classes) from Python, JavaScript, and TypeScript files to find the most relevant code snippets or files for a natural language query (Retrieval-Augmented Generation/RAG).
AI agents call search_code_context to retrieve information from Code Context Manager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries indexed code data and returns matching results without creating, modifying, executing, deleting, or transferring anything. It has no side effects beyond reading and returning semantic search results. Even if an agent misuses it, the blast radius is minimal—it can only retrieve already-indexed information.
From the tool's definition Tool performs 'vector similarity search across all indexed files' and 'find the most relevant code snippets' — these are retrieval operations with no mutation or execution capability.
Attacks that exploit this kind of access
Performs a vector similarity search across all indexed files and code entities (functions, classes) from Python, JavaScript, and TypeScript files to find the most relevant code snippets or files for a natural language query (Retrieval-Augmented Generation/RAG). It is categorised as a Read tool in the Code Context Manager MCP Server, which means it retrieves data without modifying state.
Register the Code Context Manager MCP server in PolicyLayer and add a rule for search_code_context: 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 Code Context Manager. Nothing to install.
search_code_context 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_code_context 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_code_context. 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_code_context is provided by the Code Context Manager MCP server (theraaz/code-context-manager-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 →