osc-bridge

export_device

Read-onlyIdempotent

Write one driver in a format other tools read: 'oscquery' gives its OSC namespace as OSCQuery JSON (every route with type tags, ranges and access, for OSC controllers and browsers); 'midnam' gives its MIDI names as a MIDI Name Document (controllers incl. NRPN/RPN, named values, drum notes per channel, for DAWs such as Ardour or Logic). Both carry the credit and licence of the driver's sources. The document is the text content; an OSCQuery namespace is large (every address, each CC 0-127 included).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "device": "<device>",
      "format": "<format>"
    },
    "name": "export_device"
  }
}

Input Schema

Name	Required	Description
`device`	Yes	Driver id (e.g. 'korg/minilogue') or slug, from list_devices.
`format`	Yes
`user_id`	No	Your anonymous SynthHub id, if you kept it from an earlier session (see the server instructions). Optional.

Output Schema

Name	Required	Description
`bytes`	Yes	Size of the document, which is the text content.
`device`	Yes	Driver id.
`format`	Yes
`file_name`	Yes	A file name to save it under.
`media_type`	Yes	'application/json' or 'application/xml'.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 27, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint/idempotent/openWorld=false, so the bar is lower; the description still adds that the exported document is returned as text content (clarifying 'Write' means generating output, not mutating state) and that both formats embed source credit/licence. It also warns that OSCQuery output is very large (every address, CC 0-127), which is genuinely useful for an agent to avoid truncation surprises.

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?

Front-loaded with the core action and the format definitions, and the closing sentence about output size is well placed. The parenthetical enumerations ('every route with type tags, ranges and access') make it dense, but each clause carries information an agent needs to choose a format.

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 an output schema present, the description need not describe the returned structure, and it still flags the text-content medium and the large payload size. Nothing essential is missing for a two-required-param export tool, though failure behavior for an unknown device or format is not addressed.

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 67%, with 'device' and 'user_id' already documented inline; the description compensates for the undocumented 'format' enum by explaining exactly what each value produces and who consumes it. The device id sourcing is left to the schema ('from list_devices'), so it does not add beyond 4.

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 concrete verb + resource ('Write one driver') and immediately defines the two output artifacts by name and audience ('OSCQuery JSON ... for OSC controllers and browsers'; 'MIDI Name Document ... for DAWs such as Ardour or Logic'). This clearly separates it from read-only siblings like get_device_docs and list_routes.

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 per-format audience notes give real routing guidance (pick 'oscquery' for OSC controllers/browsers, 'midnam' for DAW integration), which is the main decision an agent must make. It stops short of explicit when-not-to-use guidance or naming an alternative tool, so it stays at 4.

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

All osc-bridge 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.