set_api_key · Screenshot Analyzer MCP: Risk & Policy

WHAT IT DOES

What set_api_key does on Screenshot Analyzer MCP

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

WHY IT NEEDS A POLICY

Why set_api_key needs a policy

This tool modifies stored configuration state by setting a credential. While not destructive (the change is reversible by setting a different key), it is a Write operation that affects how the service authenticates with OpenAI. The high severity reflects that a compromised API key could lead to unauthorized API usage, cost overruns (Financial impact), or exposure of analysis results.

From the tool's definition Tool name 'set_api_key' and description 'Set the OpenAI API key' indicate modification of configuration data (the API key credential).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

set_api_key Rate-limited

set_api_key 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": {
    "set_api_key": {
      "limits": [
        {
          "counter": "set_api_key_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 Screenshot Analyzer MCP, so you can run agents against it safely.

FAQ

Questions about set_api_key

What does the set_api_key tool do? +

Set the OpenAI API key. It is categorised as a Write tool in the Screenshot Analyzer MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on set_api_key? +

Register the Screenshot Analyzer MCP server in PolicyLayer and add a rule for set_api_key: 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 Screenshot Analyzer MCP. Nothing to install.

What risk level is set_api_key? +

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

Can I rate-limit set_api_key? +

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

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

set_api_key is provided by the Screenshot Analyzer MCP server (sasuke-inu/ui-screenshot-android-review-openai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.