// SCAN REPORT

Mitm

10 tools. 6 can modify or destroy data without limits.

6 write tools that can modify data. Rate limits recommended.

Last updated: 30 Jun 2026

6 can modify or destroy data

4 read-only

10 tools total

Community server · catalogue entry verified 30/06/2026

How to control Mitm ↓

TOOL MAP

What Mitm exposes to your agents

Read (4) Write / Execute (6) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Mitm tools

Execute · High start_ap The tool executes an external script (ap-toggle.sh) to initiate network infrastructure (a WiFi access point). Execute · High start_capture This tool triggers an external operation (packet capture) whose effects depend on arguments (choice of interface, duration, filters). Execute · Critical start_proxy Starting a proxy interception session is an Execute action because it triggers an external operation (mitmproxy) whose effects depend on arguments (the engagement name) and configuration. Execute · High stop_ap This tool invokes shell commands to terminate a running network service.

6 of Mitm's 10 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mitm

PolicyLayer is an MCP gateway — it sits between your AI agents and Mitm, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "capture_status": {
    "limits": [
      {
        "counter": "capture_status_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Mitm — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MITM →

Instant setup, no code required.

FULL CATALOGUE

All 10 Mitm tools

EXECUTE 6 tools

Execute start_ap Start the hostapd access point via ap-toggle.sh. Execute start_capture Start tshark packet capture on an interface for a session. Execute start_proxy Start a mitmproxy interception session for the named engagement. Execute stop_ap Stop the hostapd access point via ap-toggle.sh. Execute stop_capture Stop tshark packet capture for a session. Execute stop_proxy Stop a running mitmproxy session and finalize logs.

READ 4 tools

Read capture_status Return current proxy and capture status, flow count, and pcap size Read get_findings Extract security findings from intercepted flows for a session. Read get_flows Read intercepted HTTP/TLS flows from a session, with optional filtering. Read list_clients List DHCP clients from the dnsmasq leases file.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Mitm

Is the Mitm MCP server safe to use without restrictions? +

The Mitm server is primarily read-only with 4 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Mitm MCP server expose? +

10 tools across 2 categories: Execute, Read. 4 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Mitm? +

Register the Mitm MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Mitm tool call.

Deterministic rules across all 10 Mitm tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MITM →

Instant setup, no code required.

10 Mitm tools catalogued and risk-classified — across an index of 43,000+ MCP servers.