AI agents invoke start_proxy to trigger actions in Mitmproxy. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Starting a proxy server is an Execute action—it triggers external network operations whose effects depend on subsequent configuration and usage. While the description is empty, the server context and tool purpose are clear: it runs mitmproxy to intercept and manipulate HTTP/HTTPS traffic in real-time.
From the tool's definition Tool is part of mitmproxy-mcp server described as transforming mitmproxy to 'inspect, modify, and replay HTTP/HTTPS traffic in real-time.' The tool name 'start_proxy' indicates it initiates a proxy server that intercepts and potentially modifies network…
Documented attack patterns abuse exactly the kind of access start_proxy 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 start_proxy:
{
"version": "1",
"default": "deny",
"tools": {
"start_proxy": {
"limits": [
{
"counter": "start_proxy_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_proxy stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
start_proxy. It is categorised as a Execute tool in the Mitmproxy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mitmproxy MCP server in PolicyLayer and add a rule for start_proxy: 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.
start_proxy is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_proxy 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 start_proxy. 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.
start_proxy 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.