Skip to main content
Glama
ntworm

Ableton MCP Server

build_extension

Compile an Ableton Extension project by running npm install and npm run build in a given directory, returning build status, entrypoint, artifacts, and per-step output.

Instructions

Run a build of an Ableton Extension project.

Side effects: runs npm install and npm run build in the supplied project directory.

Contract (v0.5.1): the JSON document returned by this tool has the following shape::

{
    "status": "built" | "error",
    "entrypoint": "dist/extension.js",
    "entrypoint_exists": true,
    "steps": [
        {"step": "install", "returncode": 0,
         "stdout": "...", "stderr": "..."},
        {"step": "build", "returncode": 0,
         "stdout": "...", "stderr": "..."}
    ],
    "artifacts": ["dist/extension.js", "..."]
}

entrypoint is read from package.json["main"] (falling back to manifest.json["entry"] when main is missing) so the contract reflects the project's own declaration. artifacts is populated when status == "built" and lists every file under dist/ relative to the project root. When the build completes but the declared entrypoint is missing on disk, status flips to "error" and entrypoint_exists is false.

Example: build_extension("/path/to/my-extension") runs npm install then npm run build and returns the JSON document above. Requires Node.js and npm on the host machine. Edge cases: returns {"status": "error", "message": ...} when package.json is missing; never raises during the subprocess execution — every step's returncode is reported in the steps array instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_pathYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.7.0

TDQS

A3.8/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and does so well: it names the side effects (npm install, npm run build in the supplied directory), states that it never raises during subprocess execution, reports each step's returncode instead, lists host requirements, and specifies the missing-package.json error shape. This is exactly the behavioral disclosure a mutation-capable tool needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded correctly, but the bulk of the description is a full restatement of the JSON return contract — including field-by-field semantics — even though an output schema already exists for this tool. That block is largely redundant and crowds out the smaller amount of information the schema cannot supply.

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?

For a build-runner with filesystem side effects and no annotations, the description covers side effects, error modes, host prerequisites, and failure semantics well enough to invoke safely. Its only meaningful gap is the directory-path contract for project_path, which is left to inference.

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 0% for the single project_path parameter, so the schema contributes nothing. The description partially compensates — it implies the value is a project root directory ('supplied project directory', 'relative to the project root') and shows an example call — but never states whether the path must be absolute, whether it must contain package.json, or how relative paths resolve.

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 and resource: 'Run a build of an Ableton Extension project.' It is clearly a build/compile operation, distinct from the read-oriented Ableton Live siblings. However, it never names the nearest sibling (scaffold_extension) or otherwise explicitly draws the boundary between scaffolding and building, so the agent must infer the distinction.

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 implied rather than stated: the example shows a direct invocation and prerequisites (Node.js and npm) are named. There is no explicit guidance on when to invoke this versus scaffold_extension, or at what point in a workflow a rebuild is warranted. Adequate but leaves sequencing to inference.

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