AI agents invoke http_request to trigger actions in PSKit. 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.
An http_request tool typically executes external network requests (GET, POST, PUT, DELETE, etc.) to arbitrary URLs, which can trigger side effects on remote systems, exfiltrate data, or interact with external APIs. Given the server context (AI agent automation with command execution capabilities), this tool likely allows making arbitrary HTTP calls.
From the tool's definition Tool name 'http_request' implies making outbound HTTP calls; description is empty and uninformative, lowering confidence.
Attacks that exploit this kind of access
http_request. It is categorised as a Execute tool in the PSKit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PSKit MCP server in PolicyLayer and add a rule for http_request: 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 PSKit. Nothing to install.
http_request 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 http_request 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 http_request. 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.
http_request is provided by the PSKit MCP server (nickalus12/pskit). 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 →