Skip to main content
Glama
BACH-AI-Tools

Midjourney Best Experience MCP Server

by BACH-AI-Tools
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoHost configuration (optional/not applicable).
PORTNoPort configuration (optional/not applicable).
API_KEYYesAPI 密钥 (API Key) for accessing the Midjourney Best Experience API.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
action_relaxuu0026vC

  • Do the relax action - You can perform upsample (same as the UI, U2...), variation (V1, V2...), zoom out 1.5x, zoom out 2x, pan, and other operations on the images generated in the first step

action_fastuu0026vC

  • Do the fast action - You can perform upsample (same as the UI, U2...), variation (V1, V2...), zoom out 1.5x, zoom out 2x, pan, and other operations on the images generated in the first step

generate_relaxC

generate the images relax Generate queue asynchronous notifications to hook_ url, overall generation time is Depends on account status and task queuing

generate_fastC

generate the images fast Generate queue asynchronous notifications to hook_ url, overall generation time is around 40-60s

get_job_by_task_idB

you can get the generate job and action job status by the task_id, and the task_id will expired at 24 hours after

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

C2.8/5.0

Scored across 5 tools

Disambiguation4/5

Tools are mostly distinct by mode (fast vs relax) and purpose (generate vs action vs status), but the 'action_fastuu0026v' and 'action_relaxuu0026v' have confusing suffixes that could cause ambiguity.

Naming Consistency2/5

Naming pattern is inconsistent: 'generate_fast' and 'generate_relax' use underscore, while 'action_fastuu0026v' and 'action_relaxuu0026v' append a cryptic suffix. 'get_job_by_task_id' follows a different verb_noun pattern.

Tool Count5/5

With 5 tools, the server is well-scoped for its purpose of image generation and manipulation. Each tool covers a distinct aspect: fast/relax generation, corresponding actions, and status checking.

Completeness4/5

The set covers the core workflow: generate (fast/relax), apply actions (upsample, variation, zoom), and check status. A minor gap is the lack of a tool to directly retrieve the generated image URL, but status likely provides this.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources