mcp-runware

Create high-quality images and videos fast from text or reference images.

CommunityOnlineAPI key requiredGlobalFreeCan modify data

What it can do

  • ImageInference: Generate an image using Runware's image inference API with all available parameters. If user provides an image and asks to generate an image based on it, then use model "bytedance:4@1"
  • PhotoMaker: Transform and style images using PhotoMaker's advanced personalization technology. Create consistent, high-quality image variations with precise subject fidelity and style control. This fu
  • ImageUpscale: Enhance the resolution and quality of images using Runware's advanced upscaling API. Transform low-resolution images into sharp, high-definition visuals. This function enables high-quali

What data it sees

Do you need an account

An API key from the service settings is required

Create high-quality images and videos fast from text or reference images. Personalize subjects, upscale, remove backgrounds, generate captions, and auto-mask faces, hands, and people. Upload local files or URLs, discover suitable models, and get shareable links to your results.

How to connect

How to connect mcp-runware to Claude

The server address to paste into Claude settings:

https://mcp-runware--elijahdev0.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect mcp-runware to ChatGPT

The server address to paste into ChatGPT settings:

https://mcp-runware--elijahdev0.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect mcp-runware to Cursor

The server address to paste into Cursor settings:

https://mcp-runware--elijahdev0.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (11)

Raw names from tools/list. Only developers need these.

imageInference Generate an image using Runware's image inference API with all available parameters. If user provides an image and asks to generate an image based on it, then use model "bytedance:4@1", and use seedImage parameter to pass the reference image. This function accepts all IImageInference parameters directly and generates images using the Runware API directly via HTTP requests. It supports the full range of parameters including basic settings, advanced features, and specialized configurations. Note: Display the url of the image inside the chat IMPORTANT: For image inputs (seedImage, referenceImages, maskImage), only accept: 1. Publicly available URLs (e.g., "https://example.com/image.jpg") 2. File paths that can be processed by imageUpload tool first 3. Runware UUIDs from previously uploaded images Workflow: If user provides a local file path, first use imageUpload to get a Runware UUID, then use that UUID here. Args: positivePrompt (str): Text instruction to guide the model on generating the image, If you wish to generate an image without any prompt guidance, you can use the special token __BLANK__ model (str): Model identifier (default: "civitai:943001@1055701") height (int): Image height (128-2048, divisible by 64, default: 1024) width (int): Image width (128-2048, divisible by 64, default: 1024) numberResults (int): Number of images to generate (1-20, default: 1). If user says "generate 4 images ..." then numberResults should be 4, says "create 2 images ... " then numberResults should be 2, etc. steps (int, optional): number of iterations the model will perform to generate the image (1-100, default: 20). The higher the number of steps, the more detailed the image will be CFGScale (float, optional): Represents how closely the images will resemble the prompt or how much freedom the AI model has (0-50, default: 7). Higher values are closer to the prompt.
photoMaker Transform and style images using PhotoMaker's advanced personalization technology. Create consistent, high-quality image variations with precise subject fidelity and style control. This function enables instant subject personalization without additional training. By providing up to four reference images, you can generate new images that maintain subject fidelity while applying various styles and compositions. IMPORTANT: For inputImages, only accept: 1. Publicly available URLs (e.g., "https://example.com/image.jpg") 2. File paths that can be processed by imageUpload tool first 3. Runware UUIDs from previously uploaded images Workflow: If user provides a local file path, first use imageUpload to get a Runware UUID, then use that UUID here. Args: positivePrompt (str): Text instruction to guide the model (2-300 chars). The trigger word 'rwre' will be automatically prepended if not included in the prompt. inputImages (List[str]): 1-4 reference images of the subject. ACCEPTS ONLY: Public URLs, Runware UUIDs, or file paths (use imageUpload first to get UUID). Must contain clear faces for best results. model (str): SDXL-based model identifier (default: "civitai:139562@344487" - RealVisXL V4.0) height (int): Image height (128-2048, divisible by 64, default: 1024) width (int): Image width (128-2048, divisible by 64, default: 1024) style (str): Artistic style to apply ("No Style", "Cinematic", "Disney Character", "Digital Art", "Photographic", "Fantasy art", "Neonpunk", "Enhance", "Comic book", "Lowpoly", "Line art") strength (int): Balance between subject fidelity and transformation (15-50, default: 15). Lower values provide stronger subject fidelity. numberResults (int): Number of images to generate (1-20, default: 1) steps (int): Number of inference iterations (1-100, default: 20) CFGScale (float): How closely images match the prompt (0-50, de
imageUpscale Enhance the resolution and quality of images using Runware's advanced upscaling API. Transform low-resolution images into sharp, high-definition visuals. This function enables high-quality image upscaling with support for various input formats and flexible output options. The maximum output size is 4096x4096 pixels - larger inputs will be automatically resized to maintain this limit. IMPORTANT: For inputImage, only accept: 1. Publicly available URLs (e.g., "https://example.com/image.jpg") 2. File paths that can be processed by imageUpload tool first 3. Runware UUIDs from previously uploaded images Workflow: If user provides a local file path, first use imageUpload to get a Runware UUID, then use that UUID here. Args: inputImage (str): Image to upscale. ACCEPTS ONLY: Public URLs, Runware UUIDs, or file paths (use imageUpload first to get UUID). Supported formats: PNG, JPG, WEBP upscaleFactor (int): Level of upscaling (2-4). Each level multiplies image size by that factor.For example, factor 2 doubles the image size. (default: 2) outputType (str, optional): Output format ('URL', 'dataURI', 'base64Data', default: 'URL') outputFormat (str, optional): Image format ('JPG', 'PNG', 'WEBP', default: 'JPG'). Note: PNG required for transparency. outputQuality (int, optional): Output image quality (20-99, default: 95) includeCost (bool, optional): Include generation cost in response taskUUID (UUID, optional): Unique task identifier Returns: dict: A dictionary containing the upscaling result with status, message, result data, parameters, and both image data for direct display and URLs. Note: Maximum output size is 4096x4096. If input size * upscaleFactor would exceed this, the input is automatically resized first. Example: 2048x2048 with factor 4 is reduced to 1024x1024 before upscaling.
imageBackgroundRemoval Remove backgrounds from images effortlessly using Runware's low-cost image editing API. Isolate subjects from their backgrounds, creating images with transparent backgrounds. This function enables high-quality background removal with support for various input formats and advanced settings like alpha matting for enhanced edge quality. IMPORTANT: For inputImage, only accept: 1. Publicly available URLs (e.g., "https://example.com/image.jpg") 2. File paths that can be processed by imageUpload tool first 3. Runware UUIDs from previously uploaded images Workflow: If user provides a local file path, first use imageUpload to get a Runware UUID, then use that UUID here. Args: inputImage (str): Image to process. ACCEPTS ONLY: Public URLs, Runware UUIDs, or file paths (use imageUpload first to get UUID). Supported formats: PNG, JPG, WEBP model (str): Background removal model to use (default: "runware:109@1" - RemBG 1.4) Available models: - runware:109@1: RemBG 1.4 - runware:110@1: Bria RMBG 2.0 - runware:112@1: BiRefNet v1 Base - runware:112@2: BiRefNet v1 Base - COD - runware:112@3: BiRefNet Dis - runware:112@5: BiRefNet General - runware:112@6: BiRefNet General Resolution 512x512 FP16 - runware:112@7: BiRefNet HRSOD DHU - runware:112@8: BiRefNet Massive TR DIS5K TR TES - runware:112@9: BiRefNet Matting - runware:112@10: BiRefNet Portrait outputType (str, optional): Output format ('URL', 'dataURI', 'base64Data', default: 'URL') outputFormat (str, optional): Image format ('JPG', 'PNG', 'WEBP', default: 'PNG') outputQuality (int, optional): Output image quality (20-99, default: 95) includeCost (bool, optional): Include generation cost in response taskUUID (UUID, optional): Unique task identifier settings (Dict[str, Any], opti
imageCaption Generate image descriptions using Runware's API. Analyzes images to produce accurate and concise captions that can be used to create additional images or provide detailed insights into visual content. This function enables AI-powered image analysis to generate descriptive text prompts from images. It's useful for understanding image content or generating prompts for further image creation. IMPORTANT: For inputImage, only accept: 1. Publicly available URLs (e.g., "https://example.com/image.jpg") 2. File paths that can be processed by imageUpload tool first 3. Runware UUIDs from previously uploaded images Workflow: If user provides a local file path, first use imageUpload to get a Runware UUID, then use that UUID here. Args: inputImage (str): Image to analyze. ACCEPTS ONLY: Public URLs, Runware UUIDs, or file paths (use imageUpload first to get UUID). Supported formats: PNG, JPG, WEBP includeCost (bool, optional): Include generation cost in response taskUUID (UUID, optional): Unique task identifier Returns: dict: A dictionary containing the caption generation result with status, message, result data (including the generated text), and cost if requested.
imageMasking Generate precise masks automatically for faces, hands, and people using AI detection. Enhance your inpainting workflow with smart, automated masking features. This function provides intelligent detection and mask generation for specific elements in images, particularly optimized for faces, hands, and people. Built on advanced detection models, it enhances the inpainting workflow by automatically creating precise masks around detected elements. IMPORTANT: For inputImage, only accept: 1. Publicly available URLs (e.g., "https://example.com/image.jpg") 2. File paths that can be processed by imageUpload tool first 3. Runware UUIDs from previously uploaded images Workflow: If user provides a local file path, first use imageUpload to get a Runware UUID, then use that UUID here. Args: inputImage (str): Image to process. ACCEPTS ONLY: Public URLs, Runware UUIDs, or file paths (use imageUpload first to get UUID). Supported formats: PNG, JPG, WEBP model (str): Detection model to use: Face Detection Models: - "runware:35@1" - face_yolov8n: Lightweight model for 2D/realistic face detection - "runware:35@2" - face_yolov8s: Enhanced face detection with improved accuracy - "runware:35@6" - mediapipe_face_full: Specialized for realistic face detection - "runware:35@7" - mediapipe_face_short: Optimized face detection with reduced complexity - "runware:35@8" - mediapipe_face_mesh: Advanced face detection with mesh mapping Specialized Face Features: - "runware:35@9" - mediapipe_face_mesh_eyes_only: Focused detection of eye regions - "runware:35@15" - eyes_mesh_mediapipe: Specialized eyes detection - "runware:35@13" - nose_mesh_mediapipe: Specialized nose detection - "runware:35@14" - lips_mesh_mediapipe: Specialized lips detection - "runware:35@10" - eyes_lips
modelSearch Search and discover AI models available in the Runware platform. This tool enables discovery of available models on the Runware platform, providing powerful search and filtering capabilities. Whether exploring public models from the community or managing private models within your organization, this API helps find the perfect model for any image generation task. Models discovered through this tool can be immediately used in image generation tasks by referencing their AIR identifiers. This enables dynamic model selection in applications and helps discover new models for specific artistic styles. Args: search (str, optional): Search term to filter models. The search is performed across multiple fields: - Model name as exact phrase (boost: 10) - Model AIR identifier with wildcard matching (boost: 5) - Model name with wildcard matching (boost: 5) - Model version (exact word matching) - Model tags (exact word matching) The search is case-insensitive and results are ordered by relevance. tags (List[str], optional): Filter models by matching any of the provided tags. Models that contain at least one of these tags will be included in the results. category (str, optional): Filter models by their category: - "checkpoint": Base models that serve as the foundation for image generation - "lora": LoRA (Low-Rank Adaptation) models for specific styles or concepts - "lycoris": Alternative to LoRA models with different adaptation techniques - "controlnet": Models for guided image generation with specific conditions - "vae": Variational Autoencoders for improving image quality and details - "embeddings": Textual embeddings for adding new concepts to the model's vocabulary type (str, optional): Filter checkpoint models by
videoInference Generate videos from text prompts and/or reference images using Runware's video generation API. Model Recommendations: - For Image-to-Video (I2V): Use 'klingai:5@2' if model is not provided, and use frameImages to guide the video generation, and do not use steps, CFGScale, or numberResults. - For Text-to-Video (T2V): Use 'google:3@1' if model is not provided, for pure text-based generation Args: positivePrompt: Text description of the video to generate model: Video generation model ID (recommended: klingai:5@2 ("width": 1920, "height": 1080) for I2V, google:3@1 ("width": 1280, "height": 720) for T2V) duration: The length of the generated video in seconds (min: 1, max: 10). This parameter directly affects the total number of frames produced based on the specified frame rate. Total frames are calculated as duration × fps. For example, a 5-second video at 24 fps will contain 120 frames. Longer durations require significantly more processing time and computational resources. Consider your specific use case when choosing duration length. width: Video width in pixels (optional, will be validated against model requirements) height: Video height in pixels (optional, will be validated against model requirements) outputType: Specifies the output type in which the video is returned. Currently, only URL delivery is supported for video outputs( default: "url") outputFormat: Specifies the format of the output video. Supported formats are: MP4 and WEBM (default: "mp4") outputQuality: Sets the compression quality of the output video. Higher values preserve more quality but increase file size, lower values reduce file size but decrease quality. (default: 95) uploadEndpoint: uploadEndpoint (str, optional): Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method such as Cloud storage, Webhook services, CDN integration. The content data wil
listVideoModels List all available video models and their supported dimensions. This tool provides a comprehensive overview of all supported video generation models on the Runware platform, organized by provider with their specific dimension requirements. Returns: dict: A dictionary containing all supported video models organized by provider, with their identifiers and supported dimensions. Note: Use the returned model identifiers directly in the videoInference tool. Each model has specific dimension requirements that must be followed.
getVideoModelInfo Get detailed information about a specific video model including supported dimensions. This tool provides comprehensive information about a specific video generation model, including its supported dimensions, provider, and usage recommendations. Args: model_id (str): The model identifier (e.g., "bytedance:2@1", "klingai:1@2") Returns: dict: A dictionary containing detailed model information including supported dimensions, provider details, and usage recommendations. Note: Use the returned dimensions in your videoInference requests to avoid errors.
imageUpload Upload an image to Runware by providing a file path on the local file system or publicurl. This function reads the image file directly from the file path or public url and uploads it to Runware. It returns a Runware UUID that can be used in other tools that require image inputs. IMPORTANT: This tool should be used FIRST when you need to process local images with other Runware tools. The returned UUID can then be used as input for tools like imageInference, photoMaker, imageUpscale, etc. Workflow: 1. Use this tool to upload a local image and get a Runware UUID 2. Use the returned UUID in other Runware tools that require image inputs 3. This prevents context pollution and ensures proper image handling Args: file_path (str): Path to the image file on the local file system Examples: "/path/to/image.jpg", "images/photo.png", "./uploads/file.webp" Supported formats: PNG, JPG, WEBP, JPEG, BMP, GIF Returns: dict: A dictionary containing the upload result with status, message, result data, and the uploaded image UUID for future reference. Note: - Images are deleted 30 days after last use, but remain available indefinitely while in use - File path must be accessible - Use the returned UUID in other Runware tools instead of file paths or base64 data