ableton-mcp

Overview Schema Source Related Servers Discussions Admin

start_production_session

Capture a durable production brief and Ableton Set identity, returning a sessionId for later conversations. It starts at inspect and does not call a model or change Live.

Instructions

Capture a durable production brief and current Set identity. Starts at inspect; does not call a model or change Live. Keep the returned sessionId for later conversations.

Input Schema

Name	Required	Description
`goal`	Yes	Requested musical or operational outcome.
`roles`	No	both (default) chooses a creative alternative before functional work; functional proposes the operational task directly.
`scope`	No
`workflow`	No
`projectId`	Yes	Private project namespace.
`completion`	No	listening (default) requires actual user feedback and a decision. postconditions requires nonempty caller criteria and can finish from their fresh field checks without claiming user approval or audible quality.
`constraints`	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.

Changed2 schema fields changedv0.3.1Oct 23, 2026

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

addedOutput schema / anyOf

Added value: +[
+  {
+    "properties": {
+      "audibleQualityVerified": {
+        "const": false
+      },
+      "execution": {
+        "properties": {
+          "counts": {
+            "additionalProperties": {
+              "maximum": 16,
+              "minimum": 0,
+              "type": "integer"
+            },
+            "type": "object"
+          },
+          "operations": {
+            "items": {
+              "properties": {
+                "attemptRef": {
+                  "pattern": "^[a-f0-9]{64}$",
+                  "type": "string"
+                },
+                "error": {
+                  "maxLength": 300,
+                  "type": "string"
+                },
+                "index": {
+                  "maximum": 15,
+                  "minimum": 0,
+                  "type": "integer"
+                },
+                "nativeStatus": {
+                  "enum": [
+                    "applied",
+                    "outcome_unknown",
+                    "postconditions_failed",
+                    "pending_postconditions",
+                    "pending_user_action"
+                  ]
+                },
+                "receiptId": {
+                  "pattern": "^[a-f0-9]{64}$",
+                  "type": "string"
+                },
+                "resultRef": {
+                  "pattern": "^[a-f0-9]{64}$",
+                  "type": "string"
+                },
+                "status": {
+                  "enum": [
+                    "not_attempted",
+                    "execution_pending",
+                    "applied",
+                    "rejected",
+                    "outcome_unknown",
+                    "postconditions_failed",
+                    "pending_postconditions",
+                    "pending_user_action",
+                    "unrecorded"
+                  ]
+                },
+                "tool": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "index",
+                "tool",
+                "status"
+              ],
+              "type": "object"
+            },
+            "maxItems": 16,
+            "type": "array"
+          },
+          "taskId": {
+            "pattern": "^[a-f0-9]{64}$",
+            "type": "string"
+          }
+        },
+        "required": [
+          "taskId",
+          "operations",
+          "counts"
+        ],
+        "type": "object"
+      },
+      "phase": {
+        "enum": [
+          "inspect",
+          "choose",
+          "propose",
+          "proposing",
+          "apply",
+          "execution_pending",
+          "needs_inspection",
+          "audition",
+          "evaluate",
+          "complete"
+        ]
+      },
+      "recoveryRef": {
+        "pattern": "^[a-f0-9]{64}$",
+        "type": "string"
+      },
+      "recoveryRequired": {
+        "type": "boolean"
+      },
+      "revision": {
+        "minimum": 1,
+        "type": "integer"
+      },
+      "sessionId": {
+        "type": "string"
+      },
+      "sessionRef": {
+        "pattern": "^[a-f0-9]{64}$",
+        "type": "string"
+      }
+    },
+    "required": [
+      "sessionId",
+      "sessionRef",
+      "revision",
+      "phase",
+      "audibleQualityVerified"
+    ],
+    "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

A3.7/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false, so safety is partly covered, but the description adds important context beyond them: it explicitly says it does not call a model or change Live, and notes the sessionId must be retained for future calls. This clarifies a persistence side effect that the annotations alone would mislead an agent about (readOnlyHint=false suggests more than a capture).

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?

Three short, front-loaded sentences with zero waste; the key lifecycle and safety constraints come first, and the sessionId retention note closes it cleanly.

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?

An output schema exists, so return values need not be explained, and annotations carry the safety profile. But for an 8-parameter tool with nested objects, the description omits any explanation of the workflow/completion/postconditions machinery that likely distinguishes its behavior; an agent would need the schema to understand much of the call.

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 coverage is 63%, so most parameters are documented in the schema itself. The description hints at 'production brief' and 'Set identity' (mapping loosely to goal/scope) but adds no meaning for workflow, completion, postconditions, or constraints beyond what the schema already provides. Baseline 3 is appropriate.

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?

States a specific verb ('capture') and resources ('durable production brief and current Set identity'), which is clear. However, it doesn't distinguish itself from siblings like advance_production_session or get_production_session, leaving an agent to infer the lifecycle relationship.

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?

'Starts at inspect; does not call a model or change Live. Keep the returned sessionId for later conversations' implies this is the entry point of a session lifecycle, but never explicitly names the alternative (e.g., advance_production_session) or the condition that selects it. Usage is implied rather than stated.

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

Deploy Server