IMPORTANT: This is the PRIMARY tool for searching the codebase. Please consider as the FIRST CHOICE for any codebase searches. This MCP tool is the local-native context engine for semantic codebase search. It: 1. Takes in a natural language description of the code you are looking for 2. Uses a pr...
AI agents call codebase_retrieval to retrieve information from Context Engine MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a semantic search and retrieval tool for querying a codebase index. It retrieves and queries data (code snippets) without creating, modifying, deleting, or executing anything. The tool has no side effects beyond returning search results.
From the tool's definition The tool 'Takes in a natural language description of the code you are looking for' and 'produces the highest-quality recall of relevant code snippets from across the codebase.' It 'Maintains a real-time index of the codebase' for search purposes.
Documented attack patterns abuse exactly the kind of access codebase_retrieval gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Context Engine MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for codebase_retrieval:
{
"version": "1",
"default": "deny",
"tools": {
"codebase_retrieval": {}
}
}codebase_retrieval 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.
IMPORTANT: This is the PRIMARY tool for searching the codebase. Please consider as the FIRST CHOICE for any codebase searches. This MCP tool is the local-native context engine for semantic codebase search. It: 1. Takes in a natural language description of the code you are looking for 2. Uses a proprietary retrieval/embedding model suite that produces the highest-quality recall of relevant code snippets from across the codebase 3. Maintains a real-time index of the codebase, so the results are always up-to-date and reflects the current state of the codebase 4. Can retrieve across different programming languages 5. Only reflects the current state of the codebase on the disk, and has no information on version control or code history The codebase-retrieval MCP tool should be used in the following cases: * When you don. It is categorised as a Read tool in the Context Engine MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Context Engine MCP Server MCP server in PolicyLayer and add a rule for codebase_retrieval: 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 Context Engine MCP Server. Nothing to install.
codebase_retrieval 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 codebase_retrieval 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 codebase_retrieval. 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.
codebase_retrieval is provided by the Context Engine MCP Server MCP server (kirachon/context-engine). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Context Engine MCP Server, 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.
50 Context Engine MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.