run_pmc_query · PTP MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_pmc_query does on PTP MCP Server

AI agents invoke run_pmc_query to trigger actions in PTP 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.

WHY IT NEEDS A POLICY

Why run_pmc_query needs a policy

The tool executes queries against live PTP infrastructure in OpenShift clusters. While PMC queries are typically read-heavy and diagnostic in nature, the 'execute' action combined with real-time system access to timing-critical infrastructure creates potential for misuse — an agent could execute queries that disrupt cluster timing synchronization or extract sensitive timing configuration data.

From the tool's definition Tool name includes 'run' and description states 'Execute PMC (PTP Management Client) queries' — both indicate active execution of external operations against PTP systems.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_pmc_query Rate-limited

run_pmc_query 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_pmc_query": {
      "limits": [
        {
          "counter": "run_pmc_query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches PTP MCP Server, so you can run agents against it safely.

FAQ

Questions about run_pmc_query

What does the run_pmc_query tool do? +

Execute PMC (PTP Management Client) queries for real-time PTP data. It is categorised as a Execute tool in the PTP MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_pmc_query? +

Register the PTP MCP Server MCP server in PolicyLayer and add a rule for run_pmc_query: 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 PTP MCP Server. Nothing to install.

What risk level is run_pmc_query? +

run_pmc_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_pmc_query? +

Yes. Add a rate_limit block to the run_pmc_query 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.

How do I block run_pmc_query completely? +

Set action: deny in the PolicyLayer policy for run_pmc_query. 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.

What MCP server provides run_pmc_query? +

run_pmc_query is provided by the PTP MCP Server MCP server (redhat-cne/ptp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.