AI agents call get_log_stream to retrieve information from Linode MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries log stream data. There are no side effects, state changes, or destructive operations. It is a simple read operation to access monitoring/diagnostic information from Linode infrastructure. Low severity because unauthorized log access may leak some operational details but does not directly impact running infrastructure or financial systems.
From the tool's definition Tool name 'get_log_stream' and description 'Get details for a specific log stream' indicate a retrieval operation that queries existing log data without modifying, executing, or deleting anything.
Documented attack patterns abuse exactly the kind of access get_log_stream 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 get_log_stream:
{
"version": "1",
"default": "deny",
"tools": {
"get_log_stream": {}
}
}get_log_stream is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get details for a specific log stream. It is categorised as a Read tool in the Linode MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Linode MCP Server MCP server in PolicyLayer and add a rule for get_log_stream: 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.
get_log_stream is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_log_stream 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 get_log_stream. 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.
get_log_stream 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.