Qwen 2 MCP Server
This server provides AI agents with access to Qwen 2 image generation and editing capabilities via the MCP protocol. Here's what you can do:
Generate images from text (
text_to_image): Create a new image from a text prompt, with options for aspect ratio and output format.Edit an image (
edit_image): Submit an image editing task by providing a source image URL and a prompt, with aspect ratio and output format options.Remix an image (
remix_image): Create a remix of an existing image using a source URL and prompt, with support for acceleration levels (none,regular,high) and output format.Check task status (
get_task): Poll or retrieve the current status and result (including output URLs) of any previously created task by its ID.Check pricing (
check_pricing): Look up current pricing for Qwen 2 models and endpoints without requiring an API key.
All task creation tools support an optional waiting/polling mode. The server is compatible with MCP-enabled hosts such as Claude Code, Codex, and Cursor.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Qwen 2 MCP Server generate a sunset over the ocean"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Why This Package?
@runapi.ai/qwen-2-mcp is a focused Model Context Protocol server for the Qwen 2 model line on RunAPI.
It gives MCP-compatible assistants direct access to 2 endpoints and 2 model variants without loading the full RunAPI catalog.
Use this per-model server when an agent should stay scoped to Qwen 2. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.
Related MCP server: grok-imagine-mcp
Install
Add it to Claude Code:
claude mcp add qwen-2 -s user -- npx -y @runapi.ai/qwen-2-mcpUse project scope when the server should be shared with a repository:
claude mcp add qwen-2 -s project -- npx -y @runapi.ai/qwen-2-mcpCodex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:
{
"mcpServers": {
"qwen-2": {
"command": "npx",
"args": ["-y", "@runapi.ai/qwen-2-mcp"]
}
}
}check_pricing works before sign-in. For task creation and status polling, ask your assistant to call the login tool. It opens a browser login and saves credentials to ~/.config/runapi/config.json, the same file used by runapi login.
Headless and CI hosts can still set RUNAPI_API_KEY before starting the MCP host.
Ready-made examples are in examples/ for Claude, Cursor, Windsurf, VS Code, and Roo Code.
Tools
Tool | Auth | Purpose |
| Yes | Create a Qwen 2 edit image task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Create a Qwen 2 text to image task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Fetch the current status and latest payload for an existing task. |
| No | Look up current pricing for a Qwen 2 model and endpoint. |
Models
Qwen 2 covers 2 model variants across 2 endpoints. Each tool accepts the models listed for it:
Tool | Models |
|
|
|
|
Model availability can change between releases. Use check_pricing or the Qwen 2 model page for the current catalog view.
Agent Prompts
Ask your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.
Create a task
Run a Qwen 2 edit image task with RunAPI.The assistant can call check_pricing, then edit_image, and return the task id, status, and output URLs.
Submit without waiting
Create the task but don't wait for it to finish.The assistant calls the create tool with wait: false and returns the task id. Check on it later with get_task.
Check pricing before creating
Check current Qwen 2 pricing, then create the task if it matches my request.The assistant calls check_pricing and can link to the Qwen 2 model page for the canonical catalog entry.
Configuration
The server resolves auth in this order:
RUNAPI_API_KEYenvironment variable, useful for headless and CI hosts~/.config/runapi/config.json, created by the MCPlogintool orrunapi loginNo key, which still allows
check_pricing
The config file is normally managed by login. A pre-provisioned headless config can use:
{
"apiKey": "your_runapi_key"
}Do not commit real API keys.
Links
Resource | URL |
Qwen 2 model page | |
npm package | |
GitHub repository | |
RunAPI MCP overview | |
RunAPI docs |
License
Licensed under the Apache License, Version 2.0.
Available Tools
5 toolscheck_pricingC
Look up RunAPI pricing for the qwen-2 model line.
Inputs: model, action.
edit_imageB
Create a Qwen 2 task on RunAPI (edit image). Returns a task id, status, and output URLs.
Inputs: prompt (required), source_image_url (required), seed, wait, +7 more.
get_taskB
Fetch the current status and latest result payload for a qwen-2 task.
Inputs: action (required), task_id (required).
loginA
Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.
Inputs: force.
text_to_imageB
Create a Qwen 2 task on RunAPI (text to image). Returns a task id, status, and output URLs.
Inputs: prompt (required), seed, wait, model, +6 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
edit_image and text_to_image both 'create a Qwen 2 task' but their names and descriptions clearly separate the two modes; check_pricing, login, and get_task serve distinct purposes. Slight residual overlap in task-creation semantics but overall clear.
check_pricing, edit_image, text_to_image, and get_task follow a clean verb_noun snake_case pattern. Only 'login' is a bare verb, a minor deviation.
Five tools is well-scoped for a single-model API wrapper covering auth, pricing, generation, editing, and status. Each tool earns its place with no redundancy.
Core lifecycle is covered: authenticate, check pricing, create tasks, and poll status. Minor gaps exist (no list-tasks or cancel-task operation), but agents can work around this with task ids.
Maintenance
Related MCP Connectors
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
Generate and edit images, create videos, quote credit costs, and retrieve private results.
Create images and videos from prompts, with options for image mixing, reference images, and start/…
Generate images, videos and music with model discovery, cost estimates and asynchronous results.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables creating and managing GPT Image tasks (edit and text-to-image) via RunAPI, with options to poll status and check pricing.5136 npmApache 2.0
- AlicenseBqualityBmaintenanceEnables AI image and video generation tasks (text-to-image, image-to-video, edit, upscale, etc.) via RunAPI, with support for polling and pricing lookups.1084 npm1Apache 2.0
- AlicenseBqualityBmaintenanceEnables background removal and upscaling of images using Recraft models via RunAPI, with task polling and pricing lookup.553 npmApache 2.0
- AlicenseAqualityBmaintenanceEnables text-to-image generation using Z Image models via RunAPI, with task management and pricing lookup.453 npmApache 2.0