AI agents use share_ips to create or update resources in Linode MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Linode MCP Server environment.
Sharing IP addresses between Linodes is a network configuration change that modifies routing/assignment of IP resources. It is reversible (IPs can be unshared), so it falls under Write rather than Destructive. Misuse could disrupt network connectivity between instances, hence medium severity.
From the tool's definition Share IP addresses between Linodes
Documented attack patterns abuse exactly the kind of access share_ips gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Linode MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for share_ips:
{
"version": "1",
"default": "deny",
"tools": {
"share_ips": {
"limits": [
{
"counter": "share_ips_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}share_ips 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.
Share IP addresses between Linodes. It is categorised as a Write tool in the Linode MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Linode MCP Server MCP server in PolicyLayer and add a rule for share_ips: 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 Linode MCP Server. Nothing to install.
share_ips 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 share_ips 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 share_ips. 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.
share_ips is provided by the Linode MCP Server MCP server (takashito/linode-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Linode MCP Server, 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.
416 Linode MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.