<tool> <purpose>Finds relevant code in an indexed codebase using natural language or keyword queries</purpose> <when_to_use> <scenario>Find specific functions, classes, or code patterns</scenario> <scenario>Get context before making changes to understand dependencies</scenario> <scenario>Explore ...
AI agents call search_codebase to retrieve information from DeepContext without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
search_codebase is a retrieval-only tool that queries an indexed codebase and returns matching code results. It performs no writes, deletions, or command execution. The risk is minimal as it only reads and returns existing data.
From the tool's definition Tool description states it 'Finds relevant code in an indexed codebase using natural language or keyword queries' and use cases include 'Find specific functions', 'Get context', and 'Explore how existing systems work'.
Documented attack patterns abuse exactly the kind of access search_codebase gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DeepContext, and nothing reaches the server without passing your rules. This is the rule we recommend for search_codebase:
{
"version": "1",
"default": "deny",
"tools": {
"search_codebase": {}
}
}search_codebase 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.
<tool> <purpose>Finds relevant code in an indexed codebase using natural language or keyword queries</purpose> <when_to_use> <scenario>Find specific functions, classes, or code patterns</scenario> <scenario>Get context before making changes to understand dependencies</scenario> <scenario>Explore how existing systems work</scenario> <scenario>Locate examples of API usage or patterns</scenario> </when_to_use> <parameters> <parameter name=. It is categorised as a Read tool in the DeepContext MCP Server, which means it retrieves data without modifying state.
Register the DeepContext MCP server in PolicyLayer and add a rule for search_codebase: 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 DeepContext. Nothing to install.
search_codebase 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_codebase 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_codebase. 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_codebase is provided by the DeepContext MCP server (wildcard-official/deepcontext-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 DeepContext tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 DeepContext tools catalogued and risk-classified — across an index of 42,500+ MCP servers.