add_explored_files · Code Intelligence MCP Server MCP

WHAT IT DOES

What add_explored_files does on Code Intelligence MCP Server

AI agents use add_explored_files to create or update resources in Code Intelligence MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Code Intelligence MCP Server environment.

WHY IT NEEDS A POLICY

Why add_explored_files needs a policy

The tool modifies internal session state (explored files list) in the READY phase of a workflow, but does not execute code, delete data, or move money. The blast radius is limited to metadata about which files have been explored, which is a reversible change. Severity is low because changing this list does not directly affect the codebase or external systems, only the agent's exploration tracking.

From the tool's definition 'Add files/directories to explored list' indicates modifying a session or configuration state by adding entries to a list. This is a write operation—it creates or modifies data (the explored files list) in a reversible manner.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_explored_files Rate-limited

add_explored_files stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_explored_files": {
      "limits": [
        {
          "counter": "add_explored_files_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Code Intelligence MCP Server, so you can run agents against it safely.

FAQ

Questions about add_explored_files

What does the add_explored_files tool do? +

Add files/directories to explored list in READY phase. It is categorised as a Write tool in the Code Intelligence MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_explored_files? +

Register the Code Intelligence MCP Server MCP server in PolicyLayer and add a rule for add_explored_files: 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 Intelligence MCP Server. Nothing to install.

What risk level is add_explored_files? +

add_explored_files is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_explored_files? +

Yes. Add a rate_limit block to the add_explored_files 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 add_explored_files completely? +

Set action: deny in the PolicyLayer policy for add_explored_files. 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 add_explored_files? +

add_explored_files is provided by the Code Intelligence MCP Server MCP server (tech-spoke/llm-helper). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.