Lists HTTP requests/responses from a mitmproxy capture session, showing method, URL, and status codes
AI agents call get_flow_details to retrieve information from mitmproxy-mcp MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays metadata about HTTP traffic already captured in a mitmproxy session. It performs a query operation to show request/response details without modifying, deleting, or executing any operations. The data exposure risk is low since it accesses intercepted traffic data that is already stored locally in the mitmproxy session context.
From the tool's definition Tool description states it 'Lists HTTP requests/responses from a mitmproxy capture session, showing method, URL, and status codes'.
Documented attack patterns abuse exactly the kind of access get_flow_details gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and mitmproxy-mcp MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_flow_details:
{
"version": "1",
"default": "deny",
"tools": {
"get_flow_details": {}
}
} get_flow_details is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Lists HTTP requests/responses from a mitmproxy capture session, showing method, URL, and status codes. It is categorised as a Read tool in the mitmproxy-mcp MCP Server MCP Server, which means it retrieves data without modifying state.
Register the mitmproxy-mcp MCP Server MCP server in PolicyLayer and add a rule for get_flow_details: 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 mitmproxy-mcp MCP Server. Nothing to install.
get_flow_details 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_flow_details 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_flow_details. 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_flow_details is provided by the mitmproxy-mcp MCP Server MCP server (lucasoeth/mitmproxy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from mitmproxy-mcp MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 mitmproxy-mcp MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.