AI agents invoke performance to trigger actions in MCP SSH SRE. 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.
While the description is sparse, the tool name combined with the server's SSH/SRE monitoring context and sibling tools like 'docker', 'resource', and 'monitoring' suggests this executes system performance commands or diagnostics.
From the tool's definition The tool is named 'performance' with description 'Performance ops.' which indicates execution of performance-related operations on Linux/Unraid systems.
Documented attack patterns abuse exactly the kind of access performance gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP SSH SRE, and nothing reaches the server without passing your rules. This is the rule we recommend for performance:
{
"version": "1",
"default": "deny",
"tools": {
"performance": {
"limits": [
{
"counter": "performance_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}performance 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.
Performance ops. It is categorised as a Execute tool in the MCP SSH SRE MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP SSH SRE MCP server in PolicyLayer and add a rule for performance: 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 MCP SSH SRE. Nothing to install.
performance 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 performance 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 performance. 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.
performance is provided by the MCP SSH SRE MCP server (jeprecated/mcp-ssh-sre). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP SSH SRE, 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.
13 MCP SSH SRE tools catalogued and risk-classified — across an index of 43,000+ MCP servers.