UGCmind MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| COMFYUI_URL | No | URL of the local ComfyUI instance. | http://localhost:8188 |
| OPENAI_MODEL | No | Model identifier for OpenAI-compatible image generation. | gpt-image-2 |
| OPENAI_API_KEY | No | API key for OpenAI-compatible image generation. | |
| UGCMIND_LOCALE | No | Locale for the UGCmind service. | en |
| OPENAI_BASE_URL | No | Base URL for OpenAI-compatible image generation API. | https://api.openai.com |
| UGCMIND_API_KEY | No | API key for UGCmind-hosted generation. Required for generation features. | |
| UGCMIND_API_URL | No | Base URL of the UGCmind API. | https://ugcmind.com |
| UGCMIND_CHAT_ID | No | Advanced: chat ID for internal deployments. | |
| UGCMIND_USER_ID | No | Advanced: user ID for internal deployments. | |
| UGCMIND_PROJECT_ID | No | Advanced: project ID for internal deployments. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| enhance_promptA | Transform a simple idea into a professional image generation prompt. Use when the user provides a brief description (e.g., "a cat in a garden") and needs a detailed, high-quality prompt. Combine with gallery inspiration for best results. Free, no API key needed. |
| ugcmind_capabilitiesA | Inspect the live UGCmind MCP tool catalog, provider availability, access rules, discovery paths, and async task contract. |
| find_skillA | Find an App-managed skill for the current task. Use this before run_skill when the user intent requires a specialized App skill. |
| run_skillA | Run and authorize an App-managed skill before calling its concrete App tools. Call this immediately before the tool that will use the skill. |
| web_fetchA | Fetch a public product or research URL through UGCmind's bounded URL materializer and return its project-safe result. Call run_skill first. This tool rejects direct calls without the active skill grant/run descriptor. |
| create_file_by_urlA | Materialize a public URL as a current-project asset. Use the returned asset id in later media calls. Call run_skill first. This tool rejects direct calls without the active skill grant/run descriptor. |
| search_project_assetsA | Search assets owned by the current UGCmind project. Call run_skill first. This tool rejects direct calls without the active skill grant/run descriptor. |
| read_project_assetA | Read metadata or bounded text content from one current-project asset. Call run_skill first. This tool rejects direct calls without the active skill grant/run descriptor. |
| prepare_reference_assetA | Create reusable project-scoped reference metadata from existing project assets. Call run_skill first. This tool rejects direct calls without the active skill grant/run descriptor. |
| search_ugc_actorsA | Search the approved UGC actor catalog. Materialize a selected public image before using it in generation. Call run_skill first. This tool rejects direct calls without the active skill grant/run descriptor. |
| visual_design_taskA | Generate a project image asset through the UGCmind Tool Runtime. Call run_skill first. This tool rejects direct calls without the active skill grant/run descriptor. If the result is queued or running, do not submit it again; return the task id and stop the turn. |
| video_generationA | Generate a project video asset through the UGCmind Tool Runtime. Call run_skill first. This tool rejects direct calls without the active skill grant/run descriptor. If the result is queued or running, do not submit it again; return the task id and stop the turn. |
| transcribe_mediaA | Transcribe a project audio or video asset into a persisted transcript asset. Call run_skill first. This tool rejects direct calls without the active skill grant/run descriptor. If the result is queued or running, do not submit it again; return the task id and stop the turn. |
| write_free_docA | Persist a Markdown brief or report as a UGCmind project document asset. Call run_skill first. This tool rejects direct calls without the active skill grant/run descriptor. If the result is queued or running, do not submit it again; return the task id and stop the turn. |
| create_voice_profileA | Create a reusable project voice profile from 1-3 authorized project audio samples. Call run_skill first. This tool rejects direct calls without the active skill grant/run descriptor. |
| speech_generationA | Generate a speech audio asset, optionally using an approved voice profile or project reference assets. Call run_skill first. This tool rejects direct calls without the active skill grant/run descriptor. If the result is queued or running, do not submit it again; return the task id and stop the turn. |
| music_generationA | Generate a project music asset through the UGCmind Tool Runtime. Call run_skill first. This tool rejects direct calls without the active skill grant/run descriptor. If the result is queued or running, do not submit it again; return the task id and stop the turn. |
| search_galleryA | Search the UGCmind prompt library for visual inspiration. Results include prompt summaries and image URLs when available; render Markdown images for visual browsing. |
| get_inspirationA | Get the full prompt, media URLs, model/type metadata, and next-action hints for one UGCmind prompt library entry. |
| list_modelsA | List UGCmind image/video generation model options from the App public model catalog. With UGCMIND_API_KEY, project-specific overrides may also be included. |
| manage_preferencesA | Read or update user preferences: default style, aspect ratio, model, style notes, and favorite prompts. Call with action "get" at conversation start to load preferences. |
| generate_imageA | Generate an image. Supports UGCmind App Runtime, local ComfyUI workflows, or OpenAI-compatible image APIs. UGCmind remains the default when UGCMIND_API_KEY is configured. |
| generate_videoA | Generate a video through the UGCmind App Tool Runtime. Video jobs are asynchronous; if queued/running, call get_tool_task_status rather than submitting again. |
| get_tool_task_statusA | Check the latest status and artifacts for a UGCmind Tool Runtime task. Use this after generate_image/generate_video returns queued or running. |
| comfyui_workflowA | Manage ComfyUI workflow templates: list, view parameters, import from file, modify settings, or delete. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| ugcmind-capabilities | |
| ugcmind-models |
TDQS
Scored across 25 tools
Multiple tool pairs appear to serve similar purposes—generate_image vs visual_design_task, generate_video vs video_generation, web_fetch vs create_file_by_url, and search_gallery vs get_inspiration—with descriptions not clearly differentiating their boundaries. This creates significant ambiguity for an agent deciding which tool to invoke.
Most tools follow a verb_noun snake_case pattern (e.g., list_models, read_project_asset), but several are noun phrases (video_generation, music_generation, ugcmind_capabilities, comfyui_workflow) and the pair generate_video/video_generation splits the same action across verb-first and noun-first names. The inconsistency is noticeable but not chaotic.
With 25 tools, the set is within the heavy range; while a content-generation server with image, video, audio, and asset management could justify many tools, the presence of redundant pairs suggests some could be consolidated, making the count feel inflated.
The surface covers core workflows: content generation (image/video/speech/music), asset management, prompt library search, model listing, skill management, and task status polling. Minor gaps include lack of update/delete operations for assets and prompts, but these do not critically hinder the primary creation lifecycle.