PostFader V12 — FL Studio MCP Server

Overview Schema Source Related Servers Discussions Admin

run_continue

Destructive

Resume a stopped or blocked Production Run or change its unexecuted remainder after a fix, reusing completed operations and enabling write mode temporarily.

Instructions

Resume a stopped or blocked Production Run, or change its unexecuted remainder.

Use it after the user's follow-up or after fixing a blocker. Completed
operations and their receipts are kept and never re-run; an operation with
an unknown outcome is never replayed. Write mode is enabled for the run
and released afterwards, like run_execute. Find saved runs with run_list.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`delta`	Yes	mode=resume with no operations continues the saved plan; append adds operations; replace_remaining replaces only the unexecuted rest. An optional updated request may narrow scope or change task policy.
`run_id`	Yes	Production Run identifier from run_execute or run_list.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`run_id`	Yes
`status`	Yes
`summary`	Yes
`blockers`	No
`receipts`	No
`warnings`	No
`phase_plan`	No
`run_context`	No
`project_saved`	No
`timing_report`	No
`attempted_count`	Yes
`completed_count`	Yes
`creation_outcome`	No
`readiness_report`	No
`total_operations`	Yes
`generated_outputs`	No
`write_mode_active`	No
`rollback_attempted`	No
`session_fingerprint`	No
`project_state_digest`	No
`write_mode_enable_count`	No
`write_mode_disable_count`	No
`write_mode_shutdown_verified`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv12.0.3Oct 5, 2026
- changedOutput schema / $defs / ProcessingPlan / properties / missing_capabilities / maxItems
```
Previous value: -128New value: +256
```
Addedv11.0.2Oct 5, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations already carry the safety profile (destructive/openWorld/idempotent=false), yet the description adds real semantic detail beyond them: completed operations and receipts are kept and never re-run, operations with unknown outcomes are never replayed, and write mode is enabled then released. That partial-replay behavior is exactly the kind of nuance an agent needs to repeat a resume safely.

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 action ("Resume ...") in the first line, followed by when-to-use and behavioral constraints. Two short paragraphs with little waste, though the final "like run_execute" clause is slightly incidental.

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?

An output schema exists so return values need no explanation, and annotations cover the safe/mutation profile. The description covers purpose, usage trigger, replay semantics, and the pointer to run_list, leaving only minor gaps (e.g., how the delta modes interact operationally) that the schema already carries.

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 run_id and the delta/mode semantics are already documented in the schema (run_id's run_list provenance, the resume/append/replace_remaining modes). The description reinforces the "unexecuted remainder" idea but adds no syntax or format beyond the schema, 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 set ("Resume ... or change its unexecuted remainder") on the concrete resource "Production Run". The qualifiers "stopped or blocked" and "unexecuted remainder" distinguish it from sibling run_execute (fresh run) without needing the schema opened.

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?

Gives clear conditions to invoke: "Use it after the user's follow-up or after fixing a blocker," and points to run_list to find runs. It does not explicitly say when NOT to use it or contrast it against run_execute/run_validate, so it stops short of full when/when-not guidance.

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

Deploy Server