ask_codebase

SERVERACE-MCP SOURCE0215andrewfeng/ace-mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/0215andrewfeng-ace-mcp/ask-codebase.md

WHAT IT DOES

What ask_codebase does on ACE-MCP

AI agents call ask_codebase to retrieve information from ACE-MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why ask_codebase is rated Low

Even though ask_codebase only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs ask_codebase safely

PolicyLayer is an MCP gateway: it sits between your AI agents and ACE-MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ask_codebase, this is the rule to start with:

ask_codebase Allowed

ask_codebase is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

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

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect ACE-MCP, apply this rule, and every ask_codebase call is checked against it from then on.

FAQ

Questions about ask_codebase

What does the ask_codebase tool do? +

Ask a natural language question about the codebase. Uses RAG: retrieves relevant code and documentation, then synthesizes an answer via LLM. Supports full-file context mode for deeper analysis. Requires LLM API to be configured. It is categorised as a Read tool in the ACE-MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on ask_codebase? +

Register the ACE MCP server in PolicyLayer and add a rule for ask_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 ACE-MCP. Nothing to install.

What risk level is ask_codebase? +

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

Can I rate-limit ask_codebase? +

Yes. Add a rate_limit block to the ask_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.

How do I block ask_codebase completely? +

Set action: deny in the PolicyLayer policy for ask_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.

What MCP server provides ask_codebase? +

ask_codebase is provided by the ACE MCP server (0215andrewfeng/ace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on ACE, and thousands of servers like it.

This server

All 17 ACE tools →

Across the catalogue

ask_about_cocktail on Cocktails RAG MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →