max4.live

Search Max for Live devices

search_devices

Read-onlyIdempotent

Search 9,000+ Max for Live devices for Ableton Live: the maxforlive.com catalogue (indexed until 2026-08-07) plus devices submitted to max4.live by their authors (origin "own", ids starting m4l_). Fuzzy full-text match (title/author/description, identical to max4.live) plus filters. Compose for natural language, e.g. "popular free MIDI devices from the last 2 weeks" -> type=[MIDI Effect,MIDI Generator,MIDI Transformation], license=[free], sort=downloads, added_after=.

Input Schema

Name	Required	Description
`sort`	No	Default relevance (Fuse ranking with a query, else newest).
`type`	No	Device types to include.
`limit`	No	Max results (default 20).
`query`	No	Free-text fuzzy search (name, author, keyword). Omit to browse by filters only.
`source`	No	all (default), mirror = maxforlive.com catalogue, own = submitted to max4.live by the author.
`license`	No	License buckets. free=freeware, commercial=paid, cc=any Creative Commons. For 'free to use' pass [free, cc].
`added_after`	No	ISO date (YYYY-MM-DD). Only devices added on/after this date.
`min_downloads`	No	Minimum download count.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 16, 2026

addedInput schema / properties / source

Added value: +{
+  "description": "all (default), mirror = maxforlive.com catalogue, own = submitted to max4.live by the author.",
+  "enum": [
+    "all",
+    "mirror",
+    "own"
+  ],
+  "type": "string"
+}

First observedJun 25, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint false), so the description's job is to add semantics — which it does: catalogue index cutoff date (2026-08-07), the two sources, and that matching is fuzzy full-text over title/author/description and identical to max4.live's own search. It doesn't discuss pagination or result-shape behavior, but for a read-only search that is a minor gap.

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?

Front-loads the corpus and scope in the first clause, then matching semantics, then the concrete query-composition example. Every sentence carries distinct information with no restatement of the name or title.

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 would ideally hint at what a result contains; it does not. Otherwise it is complete for an 8-param, all-optional search tool, and the annotations plus rich schema carry the rest.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3; the description exceeds it by demonstrating multi-parameter composition and how a natural-language request maps onto type/license/sort/added_after together. It still leaves per-parameter defaults (limit 20, sort fallback logic) entirely to the schema.

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 (Search) and resource (9,000+ Max for Live devices), and pins down the two corpora it spans (maxforlive.com mirror plus max4.live author submissions with m4l_ ids). An agent can immediately separate this from get_device (single-device lookup) and list_filters (facet enumeration) without opening a schema.

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

Usage Guidelines4/5

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

The worked example ('popular free MIDI devices from the last 2 weeks' -> type=[...], license=[free], sort=downloads, added_after=<date>) shows exactly how to translate an intent into filters, and the source field's meaning is spelled out inline. It stops short of naming siblings explicitly or stating when this tool is the wrong choice (e.g. when you already have an id).

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

All max4.live tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?