Runware MCP Server

AI Media Generation for Any MCP Client

Turn any MCP-compatible AI assistant into a creative powerhouse.
Images. Videos. Audio. Vectors. All from natural language.

What Is This?

An MCP server that connects your AI coding assistant directly to Runware's AI media generation infrastructure. Works with any client that supports the Model Context Protocol.

flowchart TB
    subgraph Client["MCP Client"]
        direction LR
        C1["Claude Code"] ~~~ C2["Cursor"] ~~~ C3["Windsurf"] ~~~ C4["VS Code"] ~~~ C5["Any MCP Client"]
    end

    Client <-->|"MCP Protocol"| Server

    subgraph Server["Runware MCP Server"]
        direction LR
        Tools["22 Tools"] ~~~ Resources["6 Resources"] ~~~ RL["Rate Limiting"] ~~~ Cache["Caching"] ~~~ Batch["Batch Processing"]
    end

    Server -->|"REST API"| Cloud

    subgraph Cloud["Runware Cloud"]
        direction LR
        FLUX["FLUX"] ~~~ SDXL["SDXL"] ~~~ Kling["Kling"] ~~~ Veo["Veo"] ~~~ EL["ElevenLabs"] ~~~ More["+more"]
    end

    style Client fill:#0d9488,stroke:#2dd4bf,stroke-width:2px,color:#fff
    style C1 fill:#0f766e,stroke:#2dd4bf,color:#fff
    style C2 fill:#0f766e,stroke:#2dd4bf,color:#fff
    style C3 fill:#0f766e,stroke:#2dd4bf,color:#fff
    style C4 fill:#0f766e,stroke:#2dd4bf,color:#fff
    style C5 fill:#0f766e,stroke:#2dd4bf,color:#fff
    style Server fill:#1e3a5f,stroke:#3b82f6,stroke-width:2px,color:#fff
    style Tools fill:#2563eb,stroke:#60a5fa,color:#fff
    style Resources fill:#2563eb,stroke:#60a5fa,color:#fff
    style RL fill:#2563eb,stroke:#60a5fa,color:#fff
    style Cache fill:#2563eb,stroke:#60a5fa,color:#fff
    style Batch fill:#2563eb,stroke:#60a5fa,color:#fff
    style Cloud fill:#854d0e,stroke:#facc15,stroke-width:2px,color:#fff
    style FLUX fill:#a16207,stroke:#fde047,color:#fff
    style SDXL fill:#a16207,stroke:#fde047,color:#fff
    style Kling fill:#a16207,stroke:#fde047,color:#fff
    style Veo fill:#a16207,stroke:#fde047,color:#fff
    style EL fill:#a16207,stroke:#fde047,color:#fff
    style More fill:#a16207,stroke:#fde047,color:#fff

One config. Zero complexity. Infinite creativity.

Installation

Add the server to your MCP client config:

{
  "mcpServers": {
    "runware": {
      "command": "npx",
      "args": ["-y", "runware-mcp"],
      "env": {
        "RUNWARE_API_KEY": "your-api-key"
      }
    }
  }
}

Config locations by client

Note: Config format may vary slightly by client. Check your client's MCP documentation for exact syntax. Codex CLI uses TOML — see the Codex MCP docs for setup.

That's it. No pip install. No virtual environments. No Python version conflicts. Just paste, restart, create.

Capabilities at a Glance

flowchart LR
    R((Runware MCP)) --> IMG[Images]
    R --> VID[Video]
    R --> AUD[Audio]
    R --> BATCH[Batch Ops]
    R --> INT[Intelligence]

    IMG --> I1[Text to Image]
    IMG --> I2[Img to Img · Inpaint · Outpaint]
    IMG --> I3[Upscale · BG Removal · Caption]
    IMG --> I4[Masking · Vectorize]

    VID --> V1[Text/Image to Video]
    VID --> V2[Lip Sync · 9 Providers]

    AUD --> A1[Music · SFX · TTS]
    AUD --> A2[Transcription]

    BATCH --> B1[Folder Processing]
    BATCH --> B2[Batch Generate · Watch]

    INT --> N1[Prompt Enhance · ControlNet]
    INT --> N2[Model Search · Cost Est.]

    style R fill:#0d9488,stroke:#2dd4bf,stroke-width:2px,color:#fff
    style IMG fill:#2563eb,stroke:#60a5fa,color:#fff
    style VID fill:#7c3aed,stroke:#a78bfa,color:#fff
    style AUD fill:#059669,stroke:#34d399,color:#fff
    style BATCH fill:#d97706,stroke:#fbbf24,color:#fff
    style INT fill:#dc2626,stroke:#f87171,color:#fff

    style I1 fill:#1e40af,stroke:#3b82f6,color:#fff
    style I2 fill:#1e40af,stroke:#3b82f6,color:#fff
    style I3 fill:#1e40af,stroke:#3b82f6,color:#fff
    style I4 fill:#1e40af,stroke:#3b82f6,color:#fff
    style V1 fill:#5b21b6,stroke:#8b5cf6,color:#fff
    style V2 fill:#5b21b6,stroke:#8b5cf6,color:#fff
    style A1 fill:#065f46,stroke:#10b981,color:#fff
    style A2 fill:#065f46,stroke:#10b981,color:#fff
    style B1 fill:#92400e,stroke:#f59e0b,color:#fff
    style B2 fill:#92400e,stroke:#f59e0b,color:#fff
    style N1 fill:#991b1b,stroke:#ef4444,color:#fff
    style N2 fill:#991b1b,stroke:#ef4444,color:#fff

The Complete Toolset

Image Generation & Manipulation

Video Generation

Audio Generation

Creative Tools

Utilities

Batch Operations

Provider-Specific Features

This server exposes the full capabilities of each provider:

MCP Resources

Access your generated content programmatically:

Prompt Templates

Pre-built workflows for common tasks:

Documentation

This MCP server includes comprehensive built-in documentation accessible as MCP resources. Any connected client can discover and read detailed API references, feature guides, and provider docs on demand.

42 documentation resources organized across 5 categories:

Example URIs: runware://docs/tools/image-inference, runware://docs/features/controlnet-guide, runware://docs/providers/kling-ai, runware://docs/guides/cost-optimization

Ask your AI assistant to list or read any runware://docs/* resource for detailed reference information.

Architecture

flowchart LR
    Client["MCP Client"] <-->|"MCP"| Handler

    subgraph Server["Runware MCP Server"]
        Handler["Protocol Handler"]
        Handler --> Tools & Core
        Core --> Data

        subgraph Tools["Tools"]
            direction TB
            IMG["Image"] ~~~ VID["Video"]
            AUD["Audio"] ~~~ BATCH["Batch"]
        end

        subgraph Core["Services"]
            direction TB
            RL["Rate Limiter"] ~~~ Cache["Cache"]
            Val["Validation"]
        end

        subgraph Data["Data"]
            direction TB
            Session["Sessions"]
            Analytics["Analytics"]
        end
    end

    Tools -->|"HTTPS"| API["Runware Cloud API"]

    style Client fill:#0d9488,stroke:#2dd4bf,stroke-width:2px,color:#fff
    style Server fill:#1e293b,stroke:#3b82f6,stroke-width:2px,color:#fff
    style Handler fill:#2563eb,stroke:#60a5fa,color:#fff
    style Tools fill:#1e40af,stroke:#3b82f6,color:#fff
    style Core fill:#065f46,stroke:#10b981,color:#fff
    style Data fill:#854d0e,stroke:#facc15,color:#fff
    style IMG fill:#2563eb,stroke:#60a5fa,color:#fff
    style VID fill:#7c3aed,stroke:#a78bfa,color:#fff
    style AUD fill:#059669,stroke:#34d399,color:#fff
    style BATCH fill:#d97706,stroke:#fbbf24,color:#fff
    style RL fill:#065f46,stroke:#10b981,color:#fff
    style Cache fill:#065f46,stroke:#10b981,color:#fff
    style Val fill:#065f46,stroke:#10b981,color:#fff
    style Session fill:#92400e,stroke:#f59e0b,color:#fff
    style Analytics fill:#92400e,stroke:#f59e0b,color:#fff
    style API fill:#854d0e,stroke:#facc15,stroke-width:2px,color:#fff

What's Included

A ground-up TypeScript rewrite covering 100% of the Runware API.

Video Model Comparison

ControlNet Preprocessors

Configuration Reference

Security

Example Workflows

Product Photography Pipeline

You: "Process all images in /photos/products - remove backgrounds,
      upscale 2x, and save as PNGs to /photos/processed"
Assistant uses processFolder with removeBackground and upscale pipeline

Video Storyboard

You: "Create a 3-part video story: sunrise over mountains,
      eagle soaring, landing on a branch. Use Kling, 5s each."

Assistant generates 3 coordinated videos with consistent style

Brand Asset Generation

You: "Generate 5 logo variations for 'TechFlow' - modern, minimal,
      tech-focused. Then vectorize the best one."

Assistant uses imageInference, selects best, then vectorize to SVG

Music + Video

You: "Create a 30-second promo video with matching background music"

Assistant uses videoInference + audioInference in parallel

Development

git clone https://github.com/runware/mcp-server
cd mcp-server
npm install
npm run build
npm test

Contributing

See CONTRIBUTING.md for the full development guide including project structure, how to add new tools, testing patterns, and code style.

1. Fork it
2. Create a feature branch
3. Make it pass: npm run build && npm run lint && npm test
4. Submit PR

For version history and release notes, see CHANGELOG.md.

License

MIT

Built for creators who demand more from their AI tools.

_{22 tools. 9 providers. 100% API coverage. Zero complexity.}