ableton-mcp

Overview Schema Source Related Servers Discussions Admin

run_production_task

Run configured creative or functional specialists to propose Ableton production changes, returning an immutable reference without applying Live edits.

Instructions

Run configured creative and/or functional specialists with bounded private context. Returns an immutable proposal reference, never executes Live changes. Optional caller postconditions define required final field checks. Provider use follows explicit server configuration.

Input Schema

Name	Required	Description
`goal`	Yes	Requested musical or operational outcome.
`roles`	No
`scope`	No
`intent`	No	change (default) requires operations or fresh caller criteria proving no change is needed. inspect permits observations without operation proposals.
`workflow`	No
`projectId`	Yes	Private project namespace.
`constraints`	No
`contextRefs`	No
`postconditions`	No	Optional caller-owned required final field checks. Specialist checks remain suggestions when supplied.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.3.1Oct 23, 2026

addedInput schema / properties / intent

Added value: +{
+  "description": "change (default) requires operations or fresh caller criteria proving no change is needed. inspect permits observations without operation proposals.",
+  "enum": [
+    "change",
+    "inspect"
+  ],
+  "type": "string"
+}

removedOutput schema / additionalProperties
```
Removed value: -true
```

addedOutput schema / anyOf

Added value: +[
+  {
+    "properties": {
+      "checkSource": {
+        "enum": [
+          "caller",
+          "specialist"
+        ]
+      },
+      "contextRef": {
+        "pattern": "^[a-f0-9]{64}$",
+        "type": "string"
+      },
+      "intent": {
+        "enum": [
+          "inspect",
+          "change"
+        ]
+      },
+      "operationCount": {
+        "maximum": 16,
+        "minimum": 0,
+        "type": "integer"
+      },
+      "questions": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "readsUsed": {
+        "minimum": 0,
+        "type": "integer"
+      },
+      "resultRefs": {
+        "items": {
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "setFingerprint": {
+        "type": "string"
+      },
+      "stateVersion": {
+        "minimum": 1,
+        "type": "integer"
+      },
+      "status": {
+        "enum": [
+          "proposed",
+          "observed",
+          "no_change_needed",
+          "incomplete",
+          "budget_exhausted",
+          "stale_context",
+          "needs_input"
+        ]
+      },
+      "summary": {
+        "type": "string"
+      },
+      "taskId": {
+        "pattern": "^[a-f0-9]{64}$",
+        "type": "string"
+      },
+      "turnRefs": {
+        "items": {
+          "type": "object"
+        },
+        "type": "array"
+      }
+    },
+    "required": [
+      "taskId",
+      "intent",
+      "status",
+      "checkSource",
+      "operationCount",
+      "summary",
+      "stateVersion",
+      "setFingerprint",
+      "questions",
+      "contextRef",
+      "resultRefs",
+      "turnRefs",
+      "readsUsed"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "error": {
+        "properties": {
+          "message": {
+            "type": "string"
+          },
+          "outcome": {
+            "enum": [
+              "unknown",
+              "not_executed"
+            ]
+          }
+        },
+        "required": [
+          "message",
+          "outcome"
+        ],
+        "type": "object"
+      }
+    },
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  }
+]

Addedv0.3.0Oct 19, 2026

TDQS

B3.4/5.0

Behavior4/5

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

This is the strongest part: with readOnlyHint=false, an agent could otherwise assume mutation, and the description corrects that by stating it never executes Live changes and returns an immutable proposal reference. It also flags that postconditions are caller-owned required checks and that provider usage depends on explicit server configuration. It stops short of describing runtime cost, latency, or failure behavior.

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?

Four tight sentences, front-loaded with the core action and the non-execution guarantee. No filler, though the provider-configuration sentence is abstract and low-value for tool selection.

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

Completeness3/5

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

The output contract and non-mutation guarantee are covered and an output schema exists, so return values need no explanation. But for a 9-parameter, nested-object, open-world tool the description leaves most of the input surface and the specialist/proposal lifecycle unexplained, which is a meaningful gap.

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

Parameters2/5

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

Schema description coverage is only 44% across 9 parameters, so the description needs to compensate and does not. It clarifies only postconditions; goal, scope (clip/track/device targeting), roles, intent, workflow.name, constraints and contextRefs get no explanation beyond the schema, and the crucial change-vs-inspect default behavior is left to the schema text alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb+resource ('Run configured creative and/or functional specialists') and states the output contract ('Returns an immutable proposal reference'). It implicitly distinguishes itself from the apply/operation siblings by saying it never executes Live changes, though it never names an alternative tool outright.

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

Usage Guidelines3/5

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

Usage is only implied: the reader deduces this is the propose step that precedes apply_production_operation. Nothing states when to prefer it over apply_production_operation or start_production_session, and there are no exclusions or prerequisites for the caller.

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

Deploy Server