midjourney-mcp

Overview Schema Source Related Servers Discussions Admin

Save a job's images to disk

download_job

Idempotent

Download the finished images from a Midjourney job and write them to disk as PNGs, returning local paths and byte counts. Bypasses CDN restrictions by using the browser.

Instructions

Download the finished images from a job and write them to disk, returning the local paths and byte counts.

These are the real files as the CDN served them, not screenshots: full resolution, original encoding. Files are named <job-id>-<index>.png so a directory of downloads from different jobs stays usable.

Midjourney's CDN refuses ordinary HTTP clients, so this goes through the browser. Expect a second or two per image.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "job_id": "<job_id>"
    },
    "name": "download_job"
  }
}

Input Schema

Name	Required	Description
`job_id`	Yes	The job whose images to download.
`indexes`	No	Which images to take, zero-based. Omit for all of them.
`out_dir`	No	Directory to write into, created if needed. Defaults to MIDJOURNEY_DOWNLOAD_DIR.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Sep 2, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Adds significant behavior beyond annotations: real files vs screenshots, full resolution and original encoding, deterministic filename pattern, browser-based download due to CDN restrictions, and expected per-image latency. No contradiction with idempotentHint or destructiveHint.

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?

Five sentences, all carrying useful information, with the core action front-loaded. No filler or redundant restating of the schema.

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

Completeness5/5

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

Complete for a 3-parameter tool with no output schema: it describes what it returns, side effects, naming behavior, why the browser is needed, and how long it takes. Annotations already cover idempotence and destructiveness.

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 100%, so parameters are already fully documented. The description adds useful context like the filename pattern and byte-count return, but does not need to further explain job_id, indexes, or out_dir.

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 and resource: download finished job images and write them to disk. It also distinguishes the tool's output from screenshots, clarifying that it saves the actual CDN-served files.

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?

Clear context: use this when you need a job's finished images saved locally. It notes CDN restrictions and browser routing, which helps set expectations, but it does not explicitly name alternatives like download_url or give a when-not-to-use rule.

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