mcpField
F
Filtrix Ai Mcp

Filtrix Ai Mcp

Local
github.com/Filtrix-AIMedia & Design0Updated 33w ago
Repository

About Filtrix Ai Mcp

An open-source collection of Filtrix AI agent skills for image and video generation. Skills use Filtrix Remote MCP, while a Seedance 2.0 prompt-design skill works without an MCP call.

Key features

  1. 01Text-to-image and image editing
  2. 02Text-to-video and image-to-video
  3. 03Poll video generation tasks
  4. 04Seedance 2.0 prompt design
  5. 05Shared MCP configuration

Use cases

  1. 01Generate images from text prompts
  2. 02Edit existing images
  3. 03Create videos from text or images
  4. 04Design prompts for stable motion and shot control

MCP support

Image and video skills call generation and editing tools through Filtrix Remote MCP and require a Filtrix MCP API key. The Seedance 2.0 prompt skill does not require an MCP call.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "filtrix-skills": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote"
      ],
      "env": {
        "AUTH_HEADER": "<AUTH_HEADER>"
      }
    }
  }
}
Run commandnpx -y mcp-remote
Environment variables to set
AUTH_HEADERSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmcp-remote

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Filtrix Skills

Open-source agent skills from Filtrix AI.

This repository is MCP-first. Skills call Filtrix Remote MCP and do not require direct provider API keys.

Available Skills

SkillWhat It DoesAccess
filtrix-image-genText-to-image + image editing via Filtrix MCPFiltrix MCP API key
filtrix-video-genText-to-video + image-to-video + task polling via Filtrix MCPFiltrix MCP API key
seedance-2-0-prompting-skillsSeedance 2.0 prompt design framework for stable motion and shot controlNo MCP call required

Install Skills

npx skills add Filtrix-AI/filtrix-skills

For local testing:

npx -y skills add /absolute/path/to/filtrix-skills --yes

Shared MCP Setup

All Filtrix MCP skills use the same server config.

1) Create API key

Create an MCP API key from your Filtrix account key-management page.

2) Add MCP server in your client
{
  "mcpServers": {
    "filtrix": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://mcp.filtrix.ai/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer <YOUR_FILTRIX_MCP_API_KEY>"
      }
    }
  }
}
3) Restart client and verify

Run:

  1. get_account_credits
  2. generate_image_text / edit_image_text / generate_video_text / generate_video_image

If these return valid responses, MCP is ready.

Tool References

Environment Variables (script mode)

export FILTRIX_MCP_API_KEY=your-mcp-key
# optional
export FILTRIX_MCP_URL=https://mcp.filtrix.ai/mcp

Notes

  • generate_video_image in MCP fixes Seedance audio to on and supports local images via base64.

License

MIT

Links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.