GenMagic MCP

OfficialRemoteby GenMagic (single-developer gateway)creditsverified Oct 10, 2026

One hosted endpoint over 450 models: text-to-video from Veo, Kling, Seedance and Hailuo on one pay-as-you-go balance.

What it does

GenMagic is an OpenAI-compatible gateway with a remote MCP in front of it. list_models returns each model's id, price and, for video, the resolutions, clip lengths and whether it renders audio; create_video starts a text-to-video job on any of them and get_video polls it. Speech, music and image generation sit on the same balance. For an agent that wants to compare Veo 3.1, Kling 3.0, Seedance 2.5 and Hailuo 3 without four accounts, it is a cheap place to start.

Connect

Remote endpoint (Streamable HTTP)

https://genmagic.co/api/mcp

Remote headers required: Authorization. Use a client that can attach custom MCP headers; this listing has no local stdio fallback.

Claude Code

claude mcp add --transport http genmagic https://genmagic.co/api/mcp --header "Authorization: Bearer YOUR_GENMAGIC_API_KEY"

Auth: api_key · env GENMAGIC_API_KEY — https://genmagic.co/get-api-key (keys start gm_live_; verified email unlocks a small starter credit)

Sample tools

list_modelscreate_videoget_videogenerate_imagegenerate_speechgenerate_musicgenerate_text

Field notes

Checked 10 Oct 2026 by calling the live endpoint without a key: initialize, tools/list and list_models all answer anonymously, 450 models in total and 26 video models including google/veo-3.1, kwaivgi/kling-v3.0-pro, bytedance/seedance-2.5, minimax/hailuo-3-max, alibaba/wan-3.0 and runway/gen-4.5. Video is text-to-video only: no image-to-video, no video editing or upscaling, and no Sora or Luma. Video is priced per second in USD and each result reports its exact charge in _meta; a failed render is not charged. The official MCP Registry entry is io.github.yumaheymans/genmagic, which is to say the gateway is run by one developer, so weigh uptime risk accordingly. For image-to-video or a bigger catalogue compare fal, replicate or kie-ai.

Also in Model Hubs

RunAPI MCP ServerRunAPI Official

Browse, price, and run 130+ image, video, audio and voice models through one MCP.

model-search · pricingremote · credits

fal MCP Serverfal.ai Official

One hosted endpoint to search, run and chain 1,000+ image, video and audio models.

text-to-video · image-to-videoremote · credits

EmpirioLabs AI MCPEmpirioLabs.ai LLC Official

Remote hub over 180+ hosted models: video, image, speech, 3D, plus GPUs by the hour.

text-to-video · image-to-videoremote · credits

inference.sh MCP Serverinference.sh Official

Official hosted hub: run any image, video, audio or 3D app, then poll the task.

text-to-image · text-to-videoremote · credits

Krea MCP ServerKrea Official

Official hosted MCP for Krea image/video models, schemas, uploads, and job widgets.

model-search · schema-inspectionremote · credits

Kie.ai MCP Serverfelores

Run Veo, Seedance, Kling, Runway, Suno, ElevenLabs, FLUX and more through one local MCP.

model-hub · text-to-videocredits

Pairs well with

AKOOL MCPAKOOL Official

Hosted MCP for AKOOL face swap, character swap, image-to-video, TTS and avatar lookup.

face-swap · character-swapremote · credits

Apatero Studio MCPApatero Official

Studio MCP for talking avatars, locked recurring characters, and batched output.

talking-head · avatar-videoremote · credits

bitHuman MCPbitHuman Official

Official bitHuman CLI server: build avatar agents from a face image and render WAV-driven talking video locally.

avatar-video · lip-syncremote · credits