AI agents invoke local_curl to trigger actions in Net. 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.
The name 'local_curl' strongly implies executing a curl command locally, which would trigger external HTTP/network operations whose effects depend on arguments. This falls under Execute as it runs an external tool/command. However, confidence is low due to the empty description — the tool could be more or less dangerous than assumed.
From the tool's definition Tool name 'local_curl' suggests executing HTTP requests via curl locally; description is empty and uninformative.
Attacks that exploit this kind of access
local_curl. It is categorised as a Execute tool in the Net MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Net MCP server in PolicyLayer and add a rule for local_curl: 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 Net. Nothing to install.
local_curl 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 local_curl 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 local_curl. 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.
local_curl is provided by the Net MCP server (steelcutoatmeal/net-mcp). 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 →