Execute a GET request using curl
AI agents invoke curl_get to trigger actions in Curl MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes external HTTP requests via curl. Although GET requests are nominally read-only, an AI agent could direct this tool to any URL including internal network resources, metadata endpoints (e.g., cloud instance metadata), or services that trigger side effects on GET. The server description explicitly mentions 'curl command execution capabilities', confirming this is an Execute category tool.
From the tool's definition "Execute a GET request using curl" — this tool runs curl commands to make HTTP requests to arbitrary URLs
Attacks that exploit this kind of access
Execute a GET request using curl. It is categorised as a Execute tool in the Curl MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Curl MCP Server MCP server in PolicyLayer and add a rule for curl_get: 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 Curl MCP Server. Nothing to install.
curl_get is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the curl_get 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 curl_get. 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.
curl_get is provided by the Curl MCP Server MCP server (neeraj15022001/curl-mcp-server). 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 →