Fetch Cloudflare Worker settings for a specific script.
AI agents call get_worker to retrieve information from Universal Mcp Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves Worker configuration data without modifying or executing anything. However, Cloudflare Worker settings may contain sensitive information (API keys, secrets, environment variables, routing rules), so unauthorized exposure poses a moderate risk. Classified as Read with medium severity due to potential information disclosure impact.
From the tool's definition Tool name 'get_worker' and description 'Fetch Cloudflare Worker settings for a specific script' indicate a retrieval operation. The verb 'Fetch' and context of reading configuration settings confirm read-only behavior.
Attacks that exploit this kind of access
Fetch Cloudflare Worker settings for a specific script. It is categorised as a Read tool in the Universal Mcp Toolkit MCP Server, which means it retrieves data without modifying state.
Register the Universal Mcp Toolkit MCP server in PolicyLayer and add a rule for get_worker: 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 Universal Mcp Toolkit. Nothing to install.
get_worker 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 get_worker 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 get_worker. 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.
get_worker is provided by the Universal Mcp Toolkit MCP server (markgatcha/universal-mcp-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →