Get all headers that were sent with the current request
AI agents call get-request-headers to retrieve information from Debug Test without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves request header data for inspection purposes only. It performs no modifications, deletions, code execution, or financial operations. The blast radius is minimal since headers typically contain standard HTTP metadata and are non-sensitive in a controlled debug environment. The tool is informational and read-only.
From the tool's definition Tool name is 'get-request-headers' and description states 'Get all headers that were sent with the current request' - this is purely a retrieval/inspection operation with no side effects.
Attacks that exploit this kind of access
Get all headers that were sent with the current request. It is categorised as a Read tool in the Debug Test MCP Server, which means it retrieves data without modifying state.
Register the Debug Test MCP server in PolicyLayer and add a rule for get-request-headers: 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 Debug Test. Nothing to install.
get-request-headers 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 get-request-headers 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 get-request-headers. 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.
get-request-headers is provided by the Debug Test MCP server (matsjfunke/debug-test-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 →