2dai-mcp-server
This server enables AI agents to control a 2DAI account for media generation, content management, discovery, and account monitoring, all with scoped permissions and spend controls.
Generate media: Create images from text (
generate_image), from references (generate_with_refsfor face, character, style, smart edits), animate images into videos (generate_video), create variations (generate_similar), and expand to wallpapers (generate_wallpaper). Credit is spent only on explicit invocation.Manage jobs: Poll with
check_generationand cancel queued jobs withcancel_generation.Upload/download: Upload images as references (
upload_image) and download creations or previews (download_creation), with paths confined to the working directory unless allowed.Organize library: List and search creations (
list_creations), manage folders and groups (list_folders,manage_folder), and organize creations (organise_creation) via move, trash, restore, delete, like. Publish or unpublish to the public feed (publish_creation).Discover: Browse the public feed for inspiration (
browse_feed).Account & spend: Get account status, credit, tier, scopes (
get_account), stats (get_stats), wallet status (get_wallet_status), staking lock (get_lock), transaction history (get_wallet_history), and token price (get_token_price). Wallet tools are read-only and opt-in; no tool transfers money.Security: API key with scoped permissions (
read,generate,manage,publish,finance) ensures least privilege; spend controls and explicit invocations prevent unintended charges.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@2dai-mcp-serverGenerate an image of a futuristic city skyline at sunset."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
2dai-mcp-server
MCP server for 2DAI — lets Claude, Cursor, Cline, Windsurf and any other MCP host generate images and video, upload references, browse the public feed, and organise your cloud drive on your own 2DAI account.
Runs locally over stdio via
npx— nothing to install permanently.Authenticates with a 2DAI API key (create one at 2dai.io → Dashboard → Integrations → API keys).
Finished images come back as inline previews so the model can see what it made and iterate.
Quick start
Claude Code
claude mcp add 2dai --env TWODAI_API_KEY=2dai_sk_... -- npx -y 2dai-mcp-serverClaude Desktop / Cursor / Cline / Windsurf (JSON config)
{
"mcpServers": {
"2dai": {
"command": "npx",
"args": ["-y", "2dai-mcp-server"],
"env": { "TWODAI_API_KEY": "2dai_sk_..." }
}
}
}The key is read from the environment only — never pass it as a tool argument.
Related MCP server: Krea MCP Server
Tools
Tool | What it does | Scope | Spends credit |
| Account status: credit, tier, key label/scopes/spend cap | read | no |
| Text-to-image (style/quality default to auto) | generate | yes |
| Image from references: | generate | yes |
| Animate a still creation into a short clip | generate | yes |
| Re-run an existing creation ("more like this one") | generate | yes |
| Expand a creation into a wallpaper dimension ( | generate | yes |
| Poll a queued generation by queueId | read | no |
| Cancel a still-waiting generation (charge refunded); explains itself when it is too late | generate | no |
| Upload a local image / base64 as a reference | generate | no |
| Save the full-resolution asset to disk, or return an inline preview | read | no |
| Page, search, sort and filter the library (folders, trash, activity lenses, smart collections, shared folders, random pick). Rows include | read | no |
| Page through the public feed (other creators' published work) | read | no |
| Page through the account's folders | read | no |
| Folder CRUD + favorites, poster, and sidebar groups (create/rename/delete/move-to-group/list-groups) | manage | no |
| Move / trash / restore / like / unlike one creation; | manage | no |
| Publish / unpublish a creation on the public feed | publish | no |
| One consolidated stats read: counters, streak, storage, 30/90-day generation volume + spend, top refs/styles/keywords | read | no |
| $2DAI balance, USD credit, effective tier + the four signals it derives from | finance | no |
| Staking-lock status (none / active / expiring-soon) | finance | no |
| Transactions, balance chart, credit chart, or credit sources | finance | no |
| Cached $2DAI/USD quote with its staleness | read | no |
All wallet tools are read-only — no tool on this server can move money. The finance
scope is opt-in and never part of a key's defaults; enable it in the dashboard's key settings
when you want an agent to see wallet data.
Least privilege
Scopes are set per key in the dashboard. A coding agent that only generates needs
read + generate; add manage for drive organisation, publish only if you want it
posting to the public feed, and finance only for wallet reads. You can also set a
per-key spend cap — the server reports actionable errors when a cap or scope blocks a call.
Configuration (env)
Variable | Default | Meaning |
| — (required) | Your 2DAI API key |
|
| Attach downscaled inline previews to finished generations |
|
| Longest edge of those previews, in px |
|
| How long a generation call blocks before degrading to a queueId |
|
| Window in which an identical re-submit is treated as a retry, not a new charge |
|
| Allow file reads/writes outside the working directory |
| production API | API origin override (for self-hosted testing) |
Notes for agents
Generation spends real credit. Check
get_accountfirst when unsure, and never generate speculatively.Long generations return a
queueId— collect withcheck_generation; re-submitting would be charged again.Rapid identical submits inside the idempotency window are deduplicated, never double-charged.
upload_image/download_creationpaths are confined to the working directory unlessTWODAI_ALLOW_ANY_PATH=1.
The 2DAI stack
We currently use our Gen 7.1 model, and unlike others, we don't resell model access. All our models originate from the open-source community or our own R&D — we then disassemble, modify, fine-tune and optimize them to align with our legacy and 2DAI❤️ART lines. They also run on our own private cloud network.
Every tool response carries the model version and stack summary (via
get_account.platform), so an agent can hand these facts back to a user who
asks "what powers you?" without extra plumbing.
License
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server for Pruna AI — ultra-fast image generation, editing, upscaling, and video generation directly from your AI assistant.Last updated82MIT
- AlicenseAqualityDmaintenanceMCP server for Krea.ai enabling AI image and video generation using models like Flux, Hailuo, Runway, Kling, and others via natural language prompts.Last updated9397Apache 2.0
- Flicense-qualityBmaintenanceMCP server enabling AI agents to generate AI videos and images, analyze video content, and download videos from Douyin and Xiaohongshu.Last updated
- AlicenseAqualityBmaintenanceMCP server for generating images and videos using Z.AI models (GLM-Image, CogView-4, CogVideoX-3, Vidu Q1, etc.) with support for synchronous and asynchronous generation, downloads, and multiple input modes.Last updated102MIT
Related MCP Connectors
MCP server for Hailuo (MiniMax) AI video generation
MCP server for ByteDance Seedream AI image generation
MCP server for Wan AI video generation
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/2DAICommunity/2dai-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server