Skip to main content
Glama
runapi-ai

RunAPI Qwen Image MCP Server

Official
by runapi-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

remix_image

Create a Qwen Image remix task from a prompt and source image URL. Returns task ID, status, and output URLs for polling.

Instructions

Create a Qwen Image task on RunAPI (remix image). Returns a task id, status, and output URLs.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
seedNoInteger seed for reproducible results. Declared type: integer.
waitNoPoll until the task reaches a terminal status.
modelNoRunAPI model slug for this model line.
promptYesPrompt describing the requested remix. Declared type: string.
strengthNoCreative deviation from the source image, from 0 (faithful) to 1 (creative). Declared type: number.
timeout_msNo
callback_urlNoWebhook URL for asynchronous task updates. Declared type: string.
output_formatNoOutput image format. Declared type: string. Known values: "png", "jpeg".
poll_interval_msNo
source_image_urlYesPublic HTTPS source image URL (JPEG, PNG, or WebP; maximum 10 MB). Declared type: string.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed16 schema fields changedv0.2.0
    • changedInput schema / additionalProperties
      Previous value: -falseNew value: +{}
    • changedInput schema / properties / callback_url / description
      Previous value: -"Webhook URL for asynchronous task updates."New value: +"Webhook URL for asynchronous task updates. Declared type: string."
    • removedInput schema / properties / model / enum
      Removed value: -[
-  "qwen-image-remix-image"
-]
    • changedInput schema / properties / output_format / description
      Previous value: -"Output image format."New value: +"Output image format. Declared type: string. Known values: \"png\", \"jpeg\"."
    • removedInput schema / properties / output_format / enum
      Removed value: -[
-  "png",
-  "jpeg"
-]
    • addedInput schema / properties / poll_interval_ms / maximum
      Added value: +9007199254740991
    • changedInput schema / properties / prompt / description
      Previous value: -"Prompt describing the requested remix."New value: +"Prompt describing the requested remix. Declared type: string."
    • removedInput schema / properties / prompt / maxLength
      Removed value: -5000
    • removedInput schema / properties / prompt / minLength
      Removed value: -1
    • changedInput schema / properties / seed / description
      Previous value: -"Integer seed for reproducible results."New value: +"Integer seed for reproducible results. Declared type: integer."
    • changedInput schema / properties / seed / type
      Previous value: -"number"New value: +"integer"
    • changedInput schema / properties / source_image_url / description
      Previous value: -"Public HTTPS source image URL (JPEG, PNG, or WebP; maximum 10 MB)."New value: +"Public HTTPS source image URL (JPEG, PNG, or WebP; maximum 10 MB). Declared type: string."
    • changedInput schema / properties / strength / description
      Previous value: -"Creative deviation from the source image, from 0 (faithful) to 1 (creative)."New value: +"Creative deviation from the source image, from 0 (faithful) to 1 (creative). Declared type: number."
    • removedInput schema / properties / strength / maximum
      Removed value: -1
    • removedInput schema / properties / strength / minimum
      Removed value: -0
    • addedInput schema / properties / timeout_ms / maximum
      Added value: +9007199254740991
  2. First observedv0.1.1

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden, and it does disclose the async task-creation model and the return shape (task id, status, output URLs), which is genuinely useful. It omits any mention of authentication, cost/pricing implications (a sibling check_pricing hints these matter), or how the wait/polling behavior affects the call, leaving meaningful gaps.

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?

Two short sentences, zero waste, with the core action front-loaded and the return contract appended. Nothing is padded or redundant.

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?

For a 10-parameter creation tool with no annotations and no output schema, the description partially compensates by naming the return fields (task id, status, output URLs). However, it says nothing about the async/polling workflow, cost, or when to prefer this over sibling image tools, so an agent still lacks key context.

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 80%, so the schema already documents most parameters (seed, strength, source image constraints, output format, callback URL). The description adds no parameter-level meaning beyond what the schema provides, which matches the baseline of 3 when schema coverage is high.

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 ('Create a Qwen Image task on RunAPI') with the remix intent parenthetically clarified, so the agent knows this generates an image from a source image. It does not, however, contrast itself with siblings like edit_image or text_to_image, so the agent must infer which image tool applies.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool versus edit_image or text_to_image, and no prerequisites or exclusions are given. The agent is left to infer usage purely from the name and the required source_image_url parameter.

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