AI agents invoke stop_search to trigger actions in NGSIEM 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.
Stopping a running search is an actionable operation that modifies the state of an external system (NGSIEM). While not destructive (the search data remains) or financial, it executes a command that has real-world effects on security operations. It falls into Execute rather than Write because it terminates an operation rather than creating/modifying persistent data.
From the tool's definition Tool name is 'stop_search' and description states 'Cancel a running NGSIEM search.' This triggers an external operation (cancellation of a running security search) whose effect depends on the search ID argument passed to it.
Documented attack patterns abuse exactly the kind of access stop_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and NGSIEM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_search:
{
"version": "1",
"default": "deny",
"tools": {
"stop_search": {
"limits": [
{
"counter": "stop_search_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stop_search 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.
Cancel a running NGSIEM search. It is categorised as a Execute tool in the NGSIEM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the NGSIEM MCP Server MCP server in PolicyLayer and add a rule for stop_search: 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 NGSIEM MCP Server. Nothing to install.
stop_search 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 stop_search 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 stop_search. 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.
stop_search is provided by the NGSIEM MCP Server MCP server (rodkinal/cs-ngsiem-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from NGSIEM 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.
10 NGSIEM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.