PostFader V12 — FL Studio MCP Server

Overview Schema Source Related Servers Discussions Admin

plugin_select_preset

Destructive

Load a known preset on one mixer effect or Channel Rack instrument using an exact name or index; verifies the landed preset.

Instructions

Load a known preset on one mixer effect or Channel Rack instrument.

Supply an exact name and/or index from plugin_list_presets. Requires write
mode. FL steps through presets to reach the target, which changes the sound
through intermediate presets, bounded by max_navigation_steps; the landed
preset's identity is read back. Inspect verified and warnings. Use
sound_apply_palette for planned multi-role choices. This selects a preset;
it does not set a parameter or load a new plug-in (plugin_load).

Input Schema

TableJSON Schema

Name	Required	Description
`target`	Yes	Loaded plug-in: {"kind": "mixer_effect", "track_index", "slot_index"} (Master also needs "allow_master": true) or {"kind": "channel_generator", "channel_index"}. Read targets with plugin_list_loaded.
`preset_name`	No	Exact preset name from plugin_list_presets.
`preset_index`	No	Exact preset index from plugin_list_presets.
`expected_current`	No	Optional current preset name and/or index; refuse if it changed.
`settle_tick_limit`	No	Later FL ticks allowed for the plug-in to settle.
`target_fingerprint`	No	Optional target identity from plugin_list_presets; refuse if a different plug-in is now loaded there.
`session_fingerprint`	No	Optional session_fingerprint from a recent read. The call refuses after a bridge reload or a reported project load. This is a concurrency guard, not authentication or a durable project identity.
`max_navigation_steps`	No	Bound on next/previous preset steps.

Output Schema

TableJSON Schema

Name	Required	Default
`after`	Yes
`before`	Yes
`plugin`	Yes
`target`	Yes
`outcome`	Yes
`verified`	Yes
`warnings`	No
`applied_at`	Yes
`project_saved`	No
`bridge_command`	No	plugin.select_preset
`schema_version`	No	1.0
`navigation_steps`	Yes
`settle_tick_limit`	Yes
`target_fingerprint`	No
`undo_point_created`	No
`verification_basis`	No	readback_on_a_later_fl_idle_tick
`session_fingerprint`	No
`max_navigation_steps`	Yes
`navigation_direction`	Yes
`verification_summary`	Yes
`requested_preset_name`	No
`requested_preset_index`	No
`expected_before_applied`	No
`session_precondition_applied`	No

Schema Changelog

Changes observed during successful MCP inspections.

Addedv11.0.2Oct 5, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only give the coarse profile (destructive=true, not idempotent, openWorld). The description adds behavior that is nowhere in the structured fields: FL navigates through intermediate presets to reach the target, audibly changing the sound en route, bounded by max_navigation_steps, and the landed preset identity is read back. It also directs the agent to inspect 'verified' and 'warnings', which is exactly the kind of consequence disclosure a destructive, non-idempotent tool needs.

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?

The description is front-loaded with what the tool does, followed by input sourcing, preconditions, behavioral side effects, and sibling exclusions. Every sentence contributes a distinct piece of information with no repetition of the schema or annotations.

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

Completeness5/5

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

An output schema exists, so return values need not be explained, and the description still tells the agent to inspect 'verified' and 'warnings'. For a destructive, non-idempotent, 8-parameter mutation tool, the definition covers preconditions, side effects, navigation bounds, and alternative tools, leaving no material gap for correct invocation.

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 every parameter (target, preset_name, preset_index, expected_current, fingerprints, settle_tick_limit, max_navigation_steps) is already documented in the schema. The description references the 'exact name and/or index' sourcing and the navigation bound, but adds little syntax or semantics beyond what the schema already states, so the baseline of 3 applies.

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 first sentence names a specific verb and resource ('Load a known preset on one mixer effect or Channel Rack instrument') and the final sentence explicitly delimits the scope against siblings ('does not set a parameter or load a new plug-in (plugin_load)'). An agent can distinguish this from plugin_set_parameter, plugin_load, and sound_apply_palette without opening any 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 states the precondition ('Requires write mode'), where to source valid inputs ('from plugin_list_presets'), and names an alternative with its selecting condition ('Use sound_apply_palette for planned multi-role choices'). It also carves out the two nearest siblings, so the when/when-not routing is essentially complete.

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

Deploy Server