strings_create_screenshot · Phrase MCP: Risk & Policy

WHAT IT DOES

What strings_create_screenshot does on Phrase

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

WHY IT NEEDS A POLICY

Why strings_create_screenshot needs a policy

This tool creates and stores new data (screenshots) in a localization project, which is a reversible write operation. It does not delete, execute code, or move money. Severity is medium because screenshots are typically non-critical project metadata, though creating spurious or misleading screenshots could degrade project quality or cause workflow confusion if an agent generates them at scale.

From the tool's definition Tool description states 'Create a new screenshot' — a clear create operation that modifies project state by adding a new resource.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

strings_create_screenshot Rate-limited

strings_create_screenshot 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": {
    "strings_create_screenshot": {
      "limits": [
        {
          "counter": "strings_create_screenshot_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 Phrase, so you can run agents against it safely.

FAQ

Questions about strings_create_screenshot

What does the strings_create_screenshot tool do? +

Create a new screenshot in a Phrase Strings project. Provide either file_path (host filesystem path, for local MCP server use) or file_content + file_name (base64-encoded image bytes, for Claude Desktop uploaded files). The image file is optional — you can create a screenshot with just a name and description. It is categorised as a Write tool in the Phrase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on strings_create_screenshot? +

Register the Phrase MCP server in PolicyLayer and add a rule for strings_create_screenshot: 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 Phrase. Nothing to install.

What risk level is strings_create_screenshot? +

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

Can I rate-limit strings_create_screenshot? +

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

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

strings_create_screenshot is provided by the Phrase MCP server (phrase-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.