AI agents call inspect_flows to retrieve information from Mitmproxy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and server context indicate this tool inspects/queries HTTP flow data without modifying it. While the read operation itself is low-severity, the medium severity reflects that inspecting traffic in a man-in-the-middle context could expose sensitive data (credentials, tokens, PII) if an AI agent gains access to intercepted flows. Confidence is reduced from high due to the missing description.
From the tool's definition Tool name 'inspect_flows' combined with server's stated capability to 'inspect, modify, and replay HTTP/HTTPS traffic'. The inspect action is read-only. Description is empty, which lowers confidence slightly.
Documented attack patterns abuse exactly the kind of access inspect_flows gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mitmproxy, and nothing reaches the server without passing your rules. This is the rule we recommend for inspect_flows:
{
"version": "1",
"default": "deny",
"tools": {
"inspect_flows": {}
}
}inspect_flows 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.
inspect_flows. It is categorised as a Read tool in the Mitmproxy MCP Server, which means it retrieves data without modifying state.
Register the Mitmproxy MCP server in PolicyLayer and add a rule for inspect_flows: 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. Nothing to install.
inspect_flows 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 inspect_flows 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 inspect_flows. 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.
inspect_flows is provided by the Mitmproxy MCP server (snapspecter/mitmproxy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 25 Mitmproxy tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
25 Mitmproxy tools catalogued and risk-classified — across an index of 42,500+ MCP servers.