Skip to main content
Glama
synopsys0

PostFader V12 — FL Studio MCP Server

render_start_job

Start a background job to render a saved .flp to WAV using FL Studio's command-line exporter. Returns a job ID; poll render_get_job for the finished file.

Instructions

Render a saved .flp to a WAV with FL's command-line exporter, as a background job.

Starts a separate FL process; the open project and its unsaved changes are
not included, because only saved state renders. Returns a job_id at once;
poll render_get_job for the output. Jobs live in this MCP process. Use the
finished WAV with the audio_* or review_* tools.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
requestYesAbsolute path of a saved .flp, a parent folder for the new job directory, and an optional timeout.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNo
job_idYes
resultNo
statusYes
commandYes
platformYes
warningsNo
created_atYes
started_atNo
finished_atNo
output_pathYes
project_pathYes
launch_methodYes
process_localNo
cancel_requestedNo
output_directoryYes
process_return_codeNo
renderer_may_be_runningNo
includes_unsaved_changesNo
application_exit_observedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv11.0.2

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is partly covered. The description adds genuinely useful context beyond that: it spawns a separate FL process, unsaved project changes are excluded because only saved state renders, it returns a job_id immediately, and jobs live in the MCP process.

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 action is front-loaded in the first clause, and every following sentence earns its place: the process/unsaved-state caveat, the async job_id contract, and the follow-up tool hints. No filler.

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?

With an output schema present, return values need not be explained, and the description still covers the behavioral caveats, the async job lifecycle, and the downstream tooling an agent needs. Nothing essential to correct invocation is missing.

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% and the nested request object documents project_path, fl_studio_path, timeout_seconds, and output_directory with defaults and bounds, so the schema carries the load. The description adds no syntax or format detail about parameters beyond noting the saved-state requirement, so the baseline 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?

States a specific verb (Render), resource (saved .flp to a WAV), and mechanism (FL's command-line exporter, as a background job). This clearly distinguishes it from siblings render_get_job and render_cancel_job, which operate on an already-started job rather than initiating one.

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?

Explicitly routes the agent to render_get_job for polling the result and to the audio_* or review_* tools for consuming the WAV output, and implies the context (only saved-state rendering, not the open project). It stops short of explicit when-not-to-use guidance, but the routing and caveat are strong.

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