Make HTTP requests (GET, POST, PUT, DELETE, PATCH) with custom headers and body
AI agents invoke browser_http_request to trigger actions in MCP Macaco Playwright. 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 can execute arbitrary HTTP requests including state-mutating methods (POST, PUT, DELETE, PATCH) to any URL with custom headers and body. It can trigger external operations, modify remote resources, or cause irreversible side effects depending on the target endpoint.
From the tool's definition Make HTTP requests (GET, POST, PUT, DELETE, PATCH) with custom headers and body
Attacks that exploit this kind of access
Make HTTP requests (GET, POST, PUT, DELETE, PATCH) with custom headers and body. It is categorised as a Execute tool in the MCP Macaco Playwright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Macaco Playwright MCP server in PolicyLayer and add a rule for browser_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 MCP Macaco Playwright. Nothing to install.
browser_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 browser_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 browser_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.
browser_http_request is provided by the MCP Macaco Playwright MCP server (macacoai/mcp-playwright). 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 →