Skip to main content
Glama
deslicer

MCP Server for Splunk

by deslicer
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

List Saved Searches

list_saved_searches

List saved searches with ownership, schedule, visibility, and permission metadata. Filter by app, owner, sharing, or name, and paginate through results.

Instructions

List saved searches with ownership, schedule, visibility, and permission metadata. If has_more is true, call again with offset=next_offset. Full SPL is truncated to 200 characters; use get_saved_search_details for the complete search.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
appNoFilter by app (default all)
countNoPage size. Default 50. Maximum 200. Values above 200 are capped to 200; 0 uses 50. Do not send a count larger than 200.
ownerNoFilter by owner (default all)
offsetNoResult offset (default 0)
sharingNoFilter by sharing level
search_filterNoExtra REST search filter (e.g. 'name=*alert*')
include_disabledNoInclude disabled searches (default false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.6.12
    • changedInput schema / properties / count / description
      Previous value: -"Page size 1-200 (default 50)"New value: +"Page size. Default 50. Maximum 200. Values above 200 are capped to 200; 0 uses 50. Do not send a count larger than 200."
  2. Changed7 schema fields changedv0.6.11
    • changedInput schema / properties / app / description
      Previous value: -"Filter by application name (optional)"New value: +"Filter by app (default all)"
    • addedInput schema / properties / count
      Added value: +{
+  "default": 50,
+  "description": "Page size 1-200 (default 50)",
+  "type": "integer"
+}
    • changedInput schema / properties / include_disabled / description
      Previous value: -"Include disabled saved searches (default: False)"New value: +"Include disabled searches (default false)"
    • addedInput schema / properties / offset
      Added value: +{
+  "default": 0,
+  "description": "Result offset (default 0)",
+  "type": "integer"
+}
    • changedInput schema / properties / owner / description
      Previous value: -"Filter by owner name (optional)"New value: +"Filter by owner (default all)"
    • addedInput schema / properties / search_filter
      Added value: +{
+  "default": "",
+  "description": "Extra REST search filter (e.g. 'name=*alert*')",
+  "type": "string"
+}
    • changedInput schema / properties / sharing / description
      Previous value: -"Filter by sharing level (optional)"New value: +"Filter by sharing level"
  3. Changed4 schema fields changedv0.6.1
    • addedInput schema / properties / app / description
      Added value: +"Filter by application name (optional)"
    • addedInput schema / properties / include_disabled / description
      Added value: +"Include disabled saved searches (default: False)"
    • addedInput schema / properties / owner / description
      Added value: +"Filter by owner name (optional)"
    • addedInput schema / properties / sharing / description
      Added value: +"Filter by sharing level (optional)"
  4. Changed1 schema field changedv0.5.1
    • addedInput schema / additionalProperties
      Added value: +false
  5. First observedv0.5.0

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure, and it delivers: it discloses pagination semantics (has_more/next_offset), SPL truncation at 200 characters, and the returned metadata categories. These traits go beyond the schema, which only documents parameters.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each earning its place: the first states purpose, the second explains pagination, the third covers truncation and the sibling route. The most decision-relevant fact (what the tool lists) is front-loaded with zero filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description partially covers the output shape by naming the metadata categories and the has_more/next_offset pagination fields. For a listing tool with seven optional, fully-documented parameters, this is adequate, though it does not enumerate every response field or the permission requirements.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description references offset and next_offset in the pagination flow, but it adds no per-parameter meaning beyond what the schema already fully documents.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('List saved searches') and enumerates the exact metadata returned (ownership, schedule, visibility, permission). It distinguishes itself from its nearest sibling by noting full SPL is only available via get_saved_search_details, so an agent can select it without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit routing condition: when full SPL is needed beyond 200 characters, use get_saved_search_details instead. It also provides the pagination loop ('If has_more is true, call again with offset=next_offset'), leaving no doubt about how to use this tool versus its alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools