Analyze whether a directory is a software project and return codebase confidence + signals.
AI agents call analyze_code_directory to retrieve information from ContextCore without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs static analysis and inspection of a directory structure to classify it and extract metadata about its nature. It retrieves information without modifying, executing, or deleting anything. The output is informational signals used to understand whether content is a software project, making it a pure Read operation with minimal risk.
From the tool's definition Tool description states it 'Analyze[s] whether a directory is a software project and return[s] codebase confidence + signals.' The verb 'analyze' and the return of read-only signals/metadata indicate no modification, deletion, execution, or financial impact.
Documented attack patterns abuse exactly the kind of access analyze_code_directory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ContextCore, and nothing reaches the server without passing your rules. This is the rule we recommend for analyze_code_directory:
{
"version": "1",
"default": "deny",
"tools": {
"analyze_code_directory": {}
}
}analyze_code_directory 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.
Analyze whether a directory is a software project and return codebase confidence + signals. It is categorised as a Read tool in the ContextCore MCP Server, which means it retrieves data without modifying state.
Register the ContextCore MCP server in PolicyLayer and add a rule for analyze_code_directory: 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 ContextCore. Nothing to install.
analyze_code_directory 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 analyze_code_directory 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 analyze_code_directory. 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.
analyze_code_directory is provided by the ContextCore MCP server (lucifer-ux/contextcore). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ContextCore, 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.
16 ContextCore tools catalogued and risk-classified — across an index of 43,000+ MCP servers.