Remove the global upstream proxy. Traffic will go directly to target servers.
AI agents use proxy_clear_upstream to create or update resources in Proxy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Proxy environment.
This tool modifies the proxy configuration by removing the upstream proxy setting. It's a reversible configuration change (the upstream proxy can be re-added), so it falls under Write rather than Destructive. However, misuse could expose traffic that was previously routed through a secure/anonymizing proxy, making it a medium severity risk.
From the tool's definition Remove the global upstream proxy. Traffic will go directly to target servers.
Documented attack patterns abuse exactly the kind of access proxy_clear_upstream gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Proxy, and nothing reaches the server without passing your rules. This is the rule we recommend for proxy_clear_upstream:
{
"version": "1",
"default": "deny",
"tools": {
"proxy_clear_upstream": {
"limits": [
{
"counter": "proxy_clear_upstream_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} proxy_clear_upstream stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Remove the global upstream proxy. Traffic will go directly to target servers. It is categorised as a Write tool in the Proxy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Proxy MCP server in PolicyLayer and add a rule for proxy_clear_upstream: 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 Proxy. Nothing to install.
proxy_clear_upstream is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the proxy_clear_upstream 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_clear_upstream. 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_clear_upstream is provided by the Proxy MCP server (yfe404/proxy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Proxy, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
89 Proxy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.