Update a subordinate MCP server package to latest version and reconnect it.
AI agents use gateway.update_server to create or update resources in PMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PMCP environment.
This tool modifies subordinate server packages and their connection state. While updates are generally reversible (packages can be downgraded or rolled back), the action directly alters deployed infrastructure state and could introduce breaking changes or service disruptions.
From the tool's definition Tool description states 'Update a subordinate MCP server package to latest version and reconnect it.' The actions are 'update' (modify) and 'reconnect' (reconfigure), which are reversible changes to server state and packages.
Documented attack patterns abuse exactly the kind of access gateway.update_server gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for gateway.update_server:
{
"version": "1",
"default": "deny",
"tools": {
"gateway.update_server": {
"limits": [
{
"counter": "gateway.update_server_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} gateway.update_server 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.
Update a subordinate MCP server package to latest version and reconnect it. It is categorised as a Write tool in the PMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the P MCP server in PolicyLayer and add a rule for gateway.update_server: 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 PMCP. Nothing to install.
gateway.update_server 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 gateway.update_server 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 gateway.update_server. 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.
gateway.update_server is provided by the P MCP server (viperjuice/pmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PMCP, 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.
26 PMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.