list_flows

THE RISK

Low Risk

Why list_flows needs a policy

This tool retrieves HTTP flow data without modifying, deleting, or executing operations. However, severity is elevated to medium rather than low because HTTP flows may contain sensitive information (authentication tokens, API keys, personal data, request/response bodies), and an AI agent with access could extract and exfiltrate confidential data.

From the tool's definition Tool description states it "Retrieves detailed HTTP request/response data including headers, content...and metadata from specified flows". The verb "Retrieves" and absence of modification language confirm read-only behavior.

Documented attack patterns abuse exactly the kind of access list_flows gives an agent:

POLICY

How to control list_flows

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 list_flows:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "list_flows": {}
  }
}

list_flows is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register mitmproxy-mcp MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More mitmproxy-mcp MCP Server tools

Read analyze_protection Analyze flow for bot protection mechanisms and extract challenge details Read extract_json_fields Extract specific fields from JSON content in a flow using JSONPath expressions Read get_flow_details Lists HTTP requests/responses from a mitmproxy capture session, showing method, URL, and s

All 4 mitmproxy-mcp MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about list_flows

What does the list_flows tool do? +

Retrieves detailed HTTP request/response data including headers, content (or structure preview for large JSON), and metadata from specified flows. It is categorised as a Read tool in the mitmproxy-mcp MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list_flows? +

Register the mitmproxy-mcp MCP Server MCP server in PolicyLayer and add a rule for list_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-mcp MCP Server. Nothing to install.

What risk level is list_flows? +

list_flows is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit list_flows? +

Yes. Add a rate_limit block to the list_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.

How do I block list_flows completely? +

Set action: deny in the PolicyLayer policy for list_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.

What MCP server provides list_flows? +

list_flows 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.

Enforce policy on every mitmproxy-mcp MCP Server tool call.

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.

CHECK YOUR STACK →