// SCAN REPORT

Mitmproxy

25 tools. 12 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 11 Jun 2026

12 can modify or destroy data

13 read-only

25 tools total

Community server · catalogue entry verified 11/06/2026

How to control Mitmproxy ↓

TOOL MAP

Read (13) Write / Execute (9) Destructive / Financial (3)

MOST DANGEROUS TOOLS

Critical Risk

Destructive · High clear_traffic This tool permanently deletes all captured HTTP/HTTPS traffic records from the mitmproxy database. Destructive · High clear_rules Rule clearance is an irreversible operation that destroys configured state. Destructive · Medium remove_global_header The name 'remove_global_header' strongly suggests it irreversibly deletes a globally-configured HTTP header from mitmproxy's interception rules. Execute · High start_proxy Starting a proxy server is an Execute action—it triggers external network operations whose effects depend on subsequent configuration and usage.

12 of Mitmproxy's 25 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL MITMPROXY

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

Deny destructive operations

{
  "clear_rules": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "set_global_header": {
    "limits": [
      {
        "counter": "set_global_header_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "detect_auth_pattern": {
    "limits": [
      {
        "counter": "detect_auth_pattern_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 Mitmproxy — 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 MITMPROXY →

Free to start. No card required.

ALL 25 MITMPROXY TOOLS

DESTRUCTIVE 3 tools

Destructive clear_rules clear_rules Destructive clear_traffic Clear all captured traffic from the database. Destructive remove_global_header remove_global_header

EXECUTE 6 tools

Execute start_proxy start_proxy Execute stop_proxy stop_proxy Execute fuzz_endpoint fuzz_endpoint Execute replay_flow Replay a captured flow, optionally with modified method, headers, or body. Execute add_interception_rule add_interception_rule Execute generate_scraper_code Generate executable scraper/automation code from a comma-separated list of

WRITE 3 tools

Write set_global_header set_global_header Write set_scope set_scope Write set_session_variable Manually set a session variable to use in replayed flows.

READ 13 tools

Read detect_auth_pattern detect_auth_pattern Read extract_from_flow extract_from_flow Read extract_session_variable extract_session_variable Read get_api_patterns Cluster captured traffic into endpoint patterns. Read get_flow_schema Infer a simple schema from a flow's JSON response body. Read get_traffic_summary get_traffic_summary Read inspect_flow Get full details of a captured flow. Read inspect_flows inspect_flows Read list_rules list_rules Read list_tools List all available tools with their descriptions. Read load_traffic_file load_traffic_file Read search_traffic Search captured traffic using filters. Read export_openapi_spec Exports captured API traffic patterns to an OpenAPI v3 JSON specification.

RELATED SERVERS

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

FAQ

Can an AI agent delete data through the Mitmproxy MCP server? +

Yes. The Mitmproxy server exposes 3 destructive tools including clear_rules, clear_traffic, remove_global_header. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Mitmproxy? +

The Mitmproxy server has 3 write tools including set_global_header, set_scope, set_session_variable. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Mitmproxy.

How many tools does the Mitmproxy MCP server expose? +

25 tools across 4 categories: Destructive, Execute, Read, Write. 13 are read-only. 12 can modify, create, or delete data.

How do I enforce a policy on Mitmproxy? +

Register the Mitmproxy 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 Mitmproxy tool call.

Deterministic rules across all 25 Mitmproxy tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MITMPROXY →

Free to start. No card required.

25 Mitmproxy tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Mitmproxy

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL MITMPROXY

// ALL 25 MITMPROXY TOOLS

// RELATED SERVERS

// FAQ