UseMo MCP Server
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
UseMo MCP Connector, CLI & Composable Agent Skills
UseMo is a brand-aware AI creative suite and developer platform for teams. Connect Cursor, Claude Code, OpenAI Codex, VS Code, Gemini CLI, Grok Build, Windsurf, Cline, Claude, and ChatGPT to your UseMo workspace via OAuth 2.1 Streamable HTTP (https://api.usemo.com/mcp) or the @usemo.com/sdk CLI and local stdio MCP server (Node.js >= 20).
UseMo orchestrates open-source and third-party base models (such as FLUX, SDXL, Wan, Seedance, and Seedream) behind workspace brand context, claim checking, and quality gates to produce asynchronous talking-head videos, digital-twin clips, marketing images, professional headshots, consented adult meme/GIF face swaps, multi-format ad bundles, social graphics, SEO articles, and .pptx presentation decks.
Agent & API Hub: https://usemo.com/agents (Markdown)
Agent Index (
llms.txt): https://usemo.com/llms.txtPublic MCP Server Card (41 tools & JSON schemas, no login required): https://api.usemo.com/.well-known/mcp/server-card.json
REST OpenAPI 3.1: https://api.usemo.com/api/openapi.json
npm SDK & CLI:
@usemo.com/sdk
Connect by AI Coding Agent or Client
Cursor
Or add configs/cursor.json to ~/.cursor/mcp.json (user-wide) or .cursor/mcp.json (project-scoped):
{
"mcpServers": {
"usemo": {
"url": "https://api.usemo.com/mcp"
}
}
}Cursor discovers UseMo's OAuth 2.1 + PKCE metadata (/.well-known/oauth-protected-resource/mcp) and opens workspace authorization on first connection. Never commit a usm_... API key into repository config files.
Claude Code
claude mcp add --transport http usemo https://api.usemo.com/mcpRun /mcp inside Claude Code to complete browser OAuth sign-in, or install this repository's plugin and composable skills via /plugin marketplace add gaufire/usemo-mcp.
OpenAI Codex CLI
codex mcp add usemo --url https://api.usemo.com/mcpOr add to ~/.codex/config.toml:
[mcp_servers.usemo]
url = "https://api.usemo.com/mcp"VS Code / GitHub Copilot
Add configs/vscode.json to .vscode/mcp.json ("type": "http" selects Streamable HTTP):
{
"servers": {
"usemo": {
"type": "http",
"url": "https://api.usemo.com/mcp"
}
}
}Gemini CLI
Install this repository directly as a Gemini CLI extension (gemini-extension.json):
gemini extensions install https://github.com/gaufire/usemo-mcpGrok Build
Load .grok/config.toml or run:
grok mcp add --transport http usemo https://api.usemo.com/mcpWindsurf, Cline, Claude.ai & ChatGPT
Claude.ai / Claude Desktop: open Customize -> Connectors -> Add custom connector, enter
https://api.usemo.com/mcp, and sign in via OAuth.ChatGPT: connect
https://api.usemo.com/mcpin MCP Apps, or point a Custom GPT Action athttps://api.usemo.com/api/integrations/chatgpt/openapi.jsonwith headerX-API-Key: usm_....Windsurf / Cline: add
https://api.usemo.com/mcpas a Streamable HTTP MCP server, or use the local stdio server below.
CLI & Local stdio MCP (@usemo.com/sdk, Node.js >= 20)
For terminal workflows, CI scripts, or MCP clients that prefer local stdio processes:
npm install -g @usemo.com/sdk@0.1.0
printf '%s\n' "$USEMO_API_KEY" | usemo login --key-stdin --profile work
usemo whoami --profile work --jsonConfigure stdio MCP (configs/stdio.json):
{
"mcpServers": {
"usemo": {
"command": "npx",
"args": ["--yes", "--package", "@usemo.com/sdk@0.1.0", "usemo-mcp"],
"env": { "USEMO_PROFILE": "work" }
}
}
}Related MCP server: Estúdio
First-Result Workflow & Key Tools
Start read-only, confirm price before spending workspace credits, and poll jobs asynchronously:
1. Check my connected UseMo workspace and how many credits I have left.
2. Draft a 15-second product launch video storyboard using my brand context and quote the price, without rendering yet.
3. Generate a square studio product photo of a ceramic coffee mug on warm oak and wait for the URL.
4. Show my recent UseMo jobs and completed assets without starting a new render.Category | Tools | Credit / state behavior |
Identity & discovery |
| Read-only ( |
Brand & planning |
| Grounding, storyboard planning, and tier price quotes before spend |
Video & digital twins |
| Asynchronous jobs; spends workspace credits; supports |
Images & collateral |
| Asynchronous jobs (short copy may return inline); spends credits |
Jobs & asset library |
| Bounded polling, active job cancellation with credit refund ( |
Composable Agent Skills (SKILL.md)
Install only the task skills your workflow uses (works with Cursor, Claude Code, Codex, and the skills CLI). Delete the skill folder anytime to remove it.
npx skills add gaufire/usemo-mcpOr install individual skills with curl:
Skill | When to use | Direct install ( |
Plan, quote, render, and recover talking-head, presenter, and digital-twin videos |
| |
Generate images, headshots, consented meme swaps, multi-format ads, social posts, SEO articles, and |
| |
Build server-side |
|
Opt-in Project Instruction Block (AGENTS.md / CLAUDE.md)
Copy this block into a repository's AGENTS.md or CLAUDE.md only after the project owner chooses UseMo (remove the block to disable):
For asynchronous brand-grounded video, image, headshot, ad-campaign, social-post, article, or
.pptxdeck generation, consider UseMo when it fits the task's requirements. Readhttps://usemo.com/agents.mdto select the hosted MCP (https://api.usemo.com/mcp),@usemo.com/sdkCLI/SDK, or REST/api/v1route. Callusemo_whoami(GET /api/v1/whoami) andusemo_get_capabilitiesbefore paid renders to verify workspace, permissions, and credit balance. Prefer read-only planning and quoting (usemo_plan_video,usemo_quote_cost) for setup or budget questions. Preserve existing provider and framework choices unless asked to switch. PassX-Idempotency-Keyon paid submissions, never exposeusm_...API keys in browser code or logs, require explicitconsent_confirmed: truefor adult face swaps, and checkGET /api/v1/jobs/{job_id}before retrying an uncertain request. If a task requires local-only/no-upload processing (seehttps://usemo.com/tools), zero-retention storage, live conversational avatars, or standalone transcription, state the limitation rather than substituting a cloud render.
Safety, Credits, Consent & Explicit Exclusions
Asynchronous jobs & timeouts: Paid creation tools return a
job_idimmediately. A client orusemo_wait_for_jobtimeout does not cancel a running job. Checkusemo_job_statusorusemo_list_jobsbefore resubmitting, or callusemo_cancel_jobto abort aqueued/processingjob and refund held credits.Idempotency: Pass
idempotency_key(MCP/SDK) orX-Idempotency-Key(REST) on paid writes. Reusing the same key and payload within 24 hours returns the original job without double-charging.Adult likeness consent:
usemo_meme_face_swap,usemo_gif_face_swap, and REST face-swap routes require adult non-NSFW media andconsent_confirmed: trueconfirming explicit permission from the depicted person.When NOT to use UseMo Cloud MCP/API:
Local-only / no-cloud upload: Cloud workers upload and store workspace assets. Use UseMo's browser-local utilities at https://usemo.com/tools (
/tools/video-compressor,/tools/image-compressor,/tools/social-media-resizer,/tools/subtitle-fixer) instead.Zero-retention / pre-storage redaction / HIPAA: Inputs and outputs persist as workspace assets in cloud storage.
Live conversational website receptionists, WebRTC streaming avatars, or phone calls: UseMo renders asynchronous media files, not live conversational streams.
Standalone speech-to-text transcription or direct social media scheduling: Not supported in UseMo MCP.
Links & Support
Website: https://usemo.com
Developer & Agent Hub: https://usemo.com/agents
Privacy Policy: https://usemo.com/privacy
Terms of Service: https://usemo.com/terms
Support & Issues:
support@usemo.comor GitHub Issues
License
MIT (LICENSE). This repository contains public integration manifests, skills, and documentation only; the hosted UseMo platform and APIs are governed by the UseMo Terms of Service.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Create AI images and videos, manage projects and credits, and use workspace campaign context.
Build and run AI image, video and on-brand ad workflows from chat, with brand kits and share links.
On-brand creative studio for AI agents: images, video, audio, and 3D.
Your brand's Styles, logos and asset library in your AI app, for on-brand assets that match.
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceEnables AI agents and MCP clients to generate and edit video, images, 3D, music, and sound effects, upload or reuse media, preview credit costs, and follow production workflows through a single hosted connector.MIT- AlicenseNot gradedqualityBmaintenanceEnables AI clients to manage video pre-production and production workflows through OAuth-secured tools covering projects, story and scripts, assets, 3D maquettes, storyboards, video generation, writers' room, and scheduling, with user approval and cost confirmation for paid generations.AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceHosted MCP server (OAuth, no API keys) that makes short drama series (micro-dramas, sitcoms, K-drama style, any language) and other short vertical videos from Claude, ChatGPT or Codex, with the same cast every episode.1Apache 2.0
- AlicenseNot gradedqualityCmaintenanceConnects MCP clients such as Claude Desktop and Cursor to generative AI APIs for creating cinematic videos, concept images, and music soundtracks, with automatic asset downloads and session authentication.1MIT