apply_profile · Mcp Director MCP: Risk & Policy

WHAT IT DOES

What apply_profile does on Mcp Director

AI agents use apply_profile to create or update resources in Mcp Director — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Director environment.

WHY IT NEEDS A POLICY

Why apply_profile needs a policy

Based on the server description, applying a profile means 'dynamically updating configuration to load only the necessary MCP servers for the current session.' This is a Write/configuration-change action — it modifies the active MCP configuration.

From the tool's definition Tool name 'apply_profile' on a server that manages MCP configuration profiles; sibling tools include 'create_profile', 'delete_profile', 'update_profile', suggesting profiles are configuration entities that get applied/switched.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

apply_profile Rate-limited

apply_profile 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": {
    "apply_profile": {
      "limits": [
        {
          "counter": "apply_profile_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 Mcp Director, so you can run agents against it safely.

FAQ

Questions about apply_profile

What does the apply_profile tool do? +

apply_profile. It is categorised as a Write tool in the Mcp Director MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on apply_profile? +

Register the Mcp Director MCP server in PolicyLayer and add a rule for apply_profile: 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 Mcp Director. Nothing to install.

What risk level is apply_profile? +

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

Can I rate-limit apply_profile? +

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

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

apply_profile is provided by the Mcp Director MCP server (yut0takagi/mcp-director). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.