ableton-mcp

Overview Schema Source Related Servers Discussions Admin

get_live_audio_capture

Read-onlyIdempotent

Read a live audio capture's status, native track/clip IDs, cleanup errors, and completed file provenance; omit the capture ID to list handles after a reconnect or timed-out start.

Instructions

Read a capture's status, current native track/clip IDs, cleanup errors and stable completed file provenance. Omit captureId to list handles after reconnect or a timed-out start. No edits; runtime handles are not saved in the Set.

Input Schema

Name	Required	Description	Default
`captureId`	No	Capture ID from start or listing.

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": {
+      "beats": {
+        "type": "number"
+      },
+      "captureId": {
+        "type": "string"
+      },
+      "captures": {
+        "items": {
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "cleanupErrors": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "clipId": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "deviceId": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "file": {
+        "anyOf": [
+          {
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "fileUnchanged": {
+        "anyOf": [
+          {
+            "type": "boolean"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "identityToken": {
+        "type": "string"
+      },
+      "partialSourcePath": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "reason": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "scope": {
+        "type": "string"
+      },
+      "setFingerprint": {
+        "type": "string"
+      },
+      "stateVersion": {
+        "minimum": 1,
+        "type": "integer"
+      },
+      "status": {
+        "type": "string"
+      },
+      "supported": {
+        "type": "boolean"
+      },
+      "trackId": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "stateVersion"
+    ],
+    "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

A4.1/5.0

Behavior4/5

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

The annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the description earns credit for adding non-obvious traits: cleanup errors, stable completed file provenance, and the fact that runtime handles are not saved in the Set. It does not explain how invalid or stale captureIds are reported, but that may be visible in the output schema.

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 two compact sentences. It front-loads what the tool reads and what data it returns, then follows with the special omit behavior and persistence caveat. No sentence is filler.

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?

With rich annotations and an output schema present, the description covers the tool's purpose, return highlights, and the unusual captureId-omitted case. A minor gap is how invalid or expired capture IDs are surfaced, though that may be handled by the output schema.

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

Parameters4/5

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

Schema coverage is already 100%, so the baseline is 3, but the description adds important semantics beyond the schema by explaining what happens when captureId is omitted: it lists handles. That omission behavior is the key parameter nuance an agent needs.

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?

The description states a specific verb and resource ('Read a capture's status') and enumerates what it returns (track/clip IDs, cleanup errors, file provenance). It is clearly distinguishable from capture_live_audio and finish_live_audio_capture, but it never names those siblings explicitly.

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?

It gives a concrete usage rule: omit captureId to list handles after reconnect or a timed-out start. That is strong contextual guidance, but it does not state when not to use this tool or name an alternative tool to call instead.

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

Deploy Server