Replay a captured flow, optionally with modified method, headers, or body.
AI agents invoke replay_flow 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.
Replaying HTTP flows sends real network requests to external systems. The ability to modify method, headers, or body before replay means an AI agent could forge or manipulate requests, trigger state changes on remote APIs, bypass authentication, or perform actions on behalf of a user. This is Execute-level because it triggers external operations whose effects depend on arguments.
From the tool's definition 'Replay a captured flow, optionally with modified method, headers, or body' — replays HTTP/HTTPS requests, triggering external operations with potentially modified parameters
Documented attack patterns abuse exactly the kind of access replay_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 replay_flow:
{
"version": "1",
"default": "deny",
"tools": {
"replay_flow": {
"limits": [
{
"counter": "replay_flow_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}replay_flow 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.
Replay a captured flow, optionally with modified method, headers, or body. 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 replay_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.
replay_flow 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 replay_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 replay_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.
replay_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.