MCP server tools

Splunk's MCP server provides several tools to interact with Splunk software.

Splunk's MCP server provides several tools to interact with Splunk software.

Tool NameDescription
run_splunk_queryRuns a Splunk query and streams the results. See the guardrails for this tool later in this topic.
get_splunk_infoRetrieves Splunk version and server details.
get_indexesLists all accessible Splunk indexes.
get_index_infoProvides detailed information about a specific index.
get_metadataRetrieves metadata (hosts, sources, sourcetypes) for index discovery and query assistance.
get_user_infoFetches current user information, roles, and permissions.
get_user_listLists all users in the Splunk instance.
get_knowledge_objectsRetrieve a list of knowledge objects from Splunk for the specified type. Refer to the list of supported types later in this topic.

Guardrails for usage of run_splunk_query

The run_splunk_query tool is intended for quick searches that are deemed safe and non-destructive. The tool might fail for one or more of the following reasons:

  1. If the search contains commands that are deemed unsafe or destructive, the MCP server may not execute the search.

  2. The execution time exceeds 1 minute.

  3. The number of events in the response exceeds 1000.

List of knowledge object types supported by get_knowledge_objects

  • saved_searches

  • alerts

  • field_extractions

  • field_aliases

  • calculated_fields

  • lookups

  • automatic_lookups

  • lookup_transforms

  • macros

  • tags

  • data_models

  • workflow_actions

  • views

  • panels

  • apps