AI agents call inspect_flow 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.
This tool retrieves network traffic data without side effects. However, severity is elevated to medium rather than low because the data exposed (HTTP/HTTPS flow details) may contain sensitive information such as credentials, API keys, personal data, or authentication tokens that could be misused if extracted by a compromised AI agent.
From the tool's definition The tool 'inspect_flow' is described as retrieving 'full details of a captured flow.' The verb 'get' and 'inspect' indicate read-only access to flow metadata, headers, request/response bodies, and related information without modification.
Documented attack patterns abuse exactly the kind of access inspect_flow 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_flow:
{
"version": "1",
"default": "deny",
"tools": {
"inspect_flow": {}
}
}inspect_flow 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.
Get full details of a captured flow. 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_flow: 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_flow 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_flow 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_flow. 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_flow 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.