Execute a Splunk search query using SPL (Search Processing Language).
AI agents invoke search_splunk to trigger actions in Splunk 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.
This tool executes arbitrary SPL queries, which can include not just search/read operations but also SPL commands that write, delete, or trigger external actions (e.g., outputlookup, sendemail, collect). The open-ended query execution surface makes this Execute category with high severity, as a misconfigured or malicious query could exfiltrate sensitive log data, modify lookups, or trigger alerting pipelines.
From the tool's definition 'Execute a Splunk search query using SPL (Search Processing Language)' — runs arbitrary SPL queries against Splunk
Attacks that exploit this kind of access
Execute a Splunk search query using SPL (Search Processing Language). It is categorised as a Execute tool in the Splunk MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Splunk MCP Server MCP server in PolicyLayer and add a rule for search_splunk: 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 Splunk MCP Server. Nothing to install.
search_splunk 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 search_splunk 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 search_splunk. 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.
search_splunk is provided by the Splunk MCP Server MCP server (rootiq-ai/splunk-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 →