This record as markdown: /tools/openclaw/proxy.md
What proxy does on OpenClaw
AI agents invoke proxy to trigger actions in OpenClaw. 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.
Why proxy is rated High
This tool executes a network debugging proxy that captures and inspects traffic. While not immediately destructive, it performs external operations (launching a proxy service, capturing traffic) whose effects and scope depend on how the proxy is configured and what network it monitors. This is categorized as Execute rather than Read because it actively runs a service, not merely retrieves pre-existing data.
From the tool's definition Tool explicitly states it 'Run[s] the OpenClaw debug proxy' which invokes and executes a proxy service. The ability to inspect captured traffic indicates execution of a network debugging tool that can intercept and observe system communications.
Attacks that exploit this kind of access
The rule that runs proxy safely
PolicyLayer is an MCP gateway: it sits between your AI agents and OpenClaw, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For proxy, this is the rule to start with:
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.
The button opens the PolicyLayer dashboard: create your workspace, connect OpenClaw, apply this rule, and every proxy call is checked against it from then on.
Questions about proxy
Run the OpenClaw debug proxy and inspect captured traffic. It is categorised as a Execute tool in the OpenClaw MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OpenClaw MCP server in PolicyLayer and add a rule for 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 OpenClaw. Nothing to install.
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 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 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.
proxy is provided by the OpenClaw MCP server (openclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on OpenClaw, and thousands of servers like it.
Across the catalogue