Shows node states using
AI agents call pcs_node_status to retrieve information from Pacemaker MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays node state information from a Pacemaker cluster. It performs a read-only query operation with no side effects, data modification, or command execution capabilities. The context of 'safe, SSH-based interaction' with 'guarded pcs commands for status queries' further confirms this is a passive information retrieval tool.
From the tool's definition Tool name 'pcs_node_status' and description 'Shows node states' indicate a query operation that retrieves cluster node status information without modifying or executing operations.
Attacks that exploit this kind of access
Shows node states using. It is categorised as a Read tool in the Pacemaker MCP MCP Server, which means it retrieves data without modifying state.
Register the Pacemaker MCP server in PolicyLayer and add a rule for pcs_node_status: 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 Pacemaker MCP. Nothing to install.
pcs_node_status 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 pcs_node_status 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 pcs_node_status. 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.
pcs_node_status is provided by the Pacemaker MCP server (rishabhkodes/pacemaker-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →