Skip to main content
Glama
Sign In
streamdeck-mcp

streamdeck-mcp

by hugoacfs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

streamdeck_find_actions

Search configured Stream Deck buttons and dials across profiles/pages, then return paste-ready native action objects for writing pages. Filter by plugin, action, name, or controller.

Instructions

Search configured buttons and dials across Stream Deck profiles/pages and return paste-ready native action objects for streamdeck_write_page. Prefer this FIRST when building layouts that reuse installed plugins (Home Assistant, Hue, OBS, Spotify, Wave Link, etc.): each hit includes a 'button' object ready for write_page (controller + key + action) so encoder/dial hits stay on the Encoder grid. You can also pass hit.action with controller=hit.controller yourself. Filters: query (substring), plugin_uuid, action_uuid, plugin_name, controller (keypad|encoder), optional profile scope. Returns a fresh ActionID per hit so multi-copy pastes are safe. For protected Elgato manifests that streamdeck_read_plugins cannot enumerate, this is the reliable path — configure once in the Stream Deck app, then find and reuse.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "streamdeck_find_actions"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax hits to return (default 50, hard cap 200). When more match, truncated=true.
queryNoCase-insensitive substring matched against plugin name, action name, title, plugin_uuid, and action_uuid.
controllerNoLimit to 'keypad' (buttons) or 'encoder' (dials). Omit to search both.
profile_idNoLimit the scan to one profile by .sdProfile folder stem.
action_uuidNoExact action UUID filter (case-insensitive).
plugin_nameNoExact plugin display name filter (case-insensitive).
plugin_uuidNoExact plugin UUID filter (case-insensitive).
profile_nameNoLimit the scan to one profile by display name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.3/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden and largely meets it: it discloses that each hit includes a 'button' object with controller/key/action, that a fresh ActionID is generated per hit making multi-copy pastes safe, and that results can be truncated at the 200 cap. It never explicitly states the operation is read-only/side-effect free, which is the one behavioral trait left implicit.

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

Conciseness4/5

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

The most decision-relevant content ('Prefer this FIRST', the write_page paste-ready claim) is front-loaded, and the sentence about protected manifests is genuinely load-bearing. It is dense but somewhat clause-heavy, packing the return-value, filter, and workaround notes into one long paragraph rather than separating them.

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?

With eight optional parameters, no annotations, and no output schema, the description does the necessary work of explaining the return shape (button object, fresh ActionID, truncated flag) that structured fields cannot supply. Remaining gaps are minor, such as whether results are ordered or how the scan behaves across multiple profiles.

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 coverage is 100%, so the schema already documents all eight filters, and the description mostly restates them ('query (substring)', 'controller (keypad|encoder)', 'optional profile scope') without new syntax or precedence rules. The one piece of added meaning is the note that passing hit.action with controller=hit.controller keeps encoder hits on the Encoder grid.

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?

States a specific verb and resource ('Search configured buttons and dials across Stream Deck profiles/pages') plus the return payload ('paste-ready native action objects for streamdeck_write_page'). It is clearly distinguishable from siblings like streamdeck_read_page and streamdeck_read_plugins by naming them as the fallback/inferior path.

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?

Explicitly prescribes 'Prefer this FIRST when building layouts that reuse installed plugins,' names the alternative it supersedes (streamdeck_read_plugins) and the condition where that alternative fails (protected Elgato manifests). It also tells the agent to configure via the Stream Deck app first, then find and reuse.

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