AI agents invoke perform_osd_mark_action to trigger actions in Ceph MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Marking an OSD in/out changes its operational state in the Ceph cluster, affecting data distribution and cluster balance. This is an operational state change that triggers rebalancing and data movement across the cluster. It's not purely destructive (data isn't deleted) but it executes a significant cluster operation. Misuse could cause data unavailability or trigger massive rebalancing operations.
From the tool's definition Mark OSD in/out status
Documented attack patterns abuse exactly the kind of access perform_osd_mark_action gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ceph MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for perform_osd_mark_action:
{
"version": "1",
"default": "deny",
"tools": {
"perform_osd_mark_action": {
"limits": [
{
"counter": "perform_osd_mark_action_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}perform_osd_mark_action stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Mark OSD in/out status. It is categorised as a Execute tool in the Ceph MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ceph MCP Server MCP server in PolicyLayer and add a rule for perform_osd_mark_action: 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 Ceph MCP Server. Nothing to install.
perform_osd_mark_action is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the perform_osd_mark_action 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 perform_osd_mark_action. 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.
perform_osd_mark_action is provided by the Ceph MCP Server MCP server (rajmohanram/ceph-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ceph 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.
18 Ceph MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.