Test direct access to HTTP endpoint (debug tool)
AI agents call test_http_endpoint to retrieve information from DevTools MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Testing an HTTP endpoint is typically a read operation (sending a GET or similar request to check connectivity/response). The description labels it a 'debug tool', suggesting its purpose is diagnostic. However, confidence is modestly reduced because the description is vague — 'test' could involve side-effecting HTTP methods (POST, PUT, DELETE), but absent evidence of that, Read is the most likely category.
From the tool's definition 'Test direct access to HTTP endpoint (debug tool)' — describes testing/checking an endpoint, which is a read/query operation
Attacks that exploit this kind of access
Test direct access to HTTP endpoint (debug tool). It is categorised as a Read tool in the DevTools MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DevTools MCP Server MCP server in PolicyLayer and add a rule for test_http_endpoint: 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 DevTools MCP Server. Nothing to install.
test_http_endpoint 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 test_http_endpoint 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 test_http_endpoint. 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.
test_http_endpoint is provided by the DevTools MCP Server MCP server (shabaraba/devtools-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 →