Make a GET request (convenience method).
AI agents call http_get to retrieve information from Http Client without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
HTTP GET is a read-only operation that retrieves information from a server. It does not modify, delete, or execute code on the server. The GET method is idempotent and safe, meaning it should not cause any state changes. While the tool could theoretically be used to retrieve sensitive data depending on the endpoint, the tool itself is inherently a Read operation with low severity when considered in isolation.
From the tool's definition Tool name 'http_get' and description 'Make a GET request (convenience method)' indicate a standard HTTP GET operation, which by definition retrieves data without side effects.
Attacks that exploit this kind of access
Make a GET request (convenience method). It is categorised as a Read tool in the Http Client MCP Server, which means it retrieves data without modifying state.
Register the Http Client MCP server in PolicyLayer and add a rule for http_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 Http Client. Nothing to install.
http_get 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 http_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 http_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.
http_get is provided by the Http Client MCP server (keijeizei/http-client-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 →