A
licenseNot graded
qualityD
maintenanceLocal AI generation for images, audio, speech, and 3D models using open source models.
3
GPL 3.0
kokon
Related Servers
Alternatives to kokon
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients on a local network to generate and edit images with a self-hosted uncensored Qwen-Image-2.1 model over Streamable HTTP. Supports text-to-image at any aspect ratio, multi-image editing, transparent backgrounds, seamless textures with height and normal maps, 360 panoramas, upscaling, and watermark removal.115MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to generate and edit images locally on Apple silicon using FLUX.2 Klein models, fully offline, with tools for generation, editing, and listing available models.2MIT
- AlicenseAqualityBmaintenanceGenerate images with OpenAI gpt-image-2.5 (or any OpenAI-compatible relay) using your own API key: 1K-4K, quality up to max, reference images, mask inpainting and per-image cost tracking, plus a local web gallery that shows your agent's generations live.41MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to generate and edit local PNG images from text prompts or reference images through an OpenAI-compatible Images API, with selectable style templates and offline reference examples.MIT
postward-creative-mcpofficial
AlicenseBqualityBmaintenanceEnables AI assistants to generate images, videos, music, and voiceovers with your own provider keys, and edit video locally with ffmpeg — all on your machine with no account, watermark, or telemetry.3543 npmMIT
TDQS
A3.7/5.0
Scored across 8 tools
Disambiguation4/5
Each tool maps to a distinct operation (generate, single-image edit, multi-image edit, outpaint, upscale, mask inpaint, info, status), and the descriptions explicitly disambiguate the trickiest pair by telling the agent when to prefer generate_image with reference_images over edit_images. The only residual overlap is edit_image vs inpaint_image vs edit_images, which share the 'modify an image' space but differ in inputs.
Naming Consistency4/5
All names are snake_case verb_noun following a predictable pattern (generate_image, edit_image, edit_images, outpaint_image, upscale_image, inpaint_image, get_image_info). The sole deviation is get_generator_status, whose noun ('generator') breaks the image-centric pattern, and edit_image/edit_images differ only by plural.
Tool Count5/5
Eight tools sit squarely in the well-scoped range, and each covers a genuinely different image workflow (generate, edit, multi-reference edit, outpaint, upscale, inpaint, inspect, status). No redundant or filler tools are present.
Completeness4/5
The lifecycle is well covered — generation, several editing modalities, upscaling, and metadata inspection. Minor gaps: status reports an active job and queue but there is no cancel/queue-listing tool, and there is no way to list or manage previously generated files; agents can work around both via absolute paths and get_image_info.
Maintenance
ActivityActive
ResponsivenessUsually handled