Easy-Peasy.AI MCP Server
Generate text, images, videos, speech and transcripts from any MCP client, on your Easy-Peasy.AI account.
Website · Docs · Tools reference · Support
Easy-Peasy.AI is an AI content platform. Its hosted Model Context Protocol server lets Claude, ChatGPT, Cursor, VS Code, Gemini CLI and other MCP clients use it directly:
- Write with 200+ templates: blog posts, product descriptions, ads, emails, social captions and more.
- Create and edit images with models such as Nano Banana, FLUX, Seedream and GPT Image.
- Make videos from text or an image with Veo, Kling, Seedance, MiniMax and other models.
- Turn text into speech with 1,000+ voices, including your own cloned voices.
- Transcribe audio and video files or links (YouTube, TikTok, Instagram, X, Loom and more) with speaker labels.
- See results in the chat: clients that support MCP Apps show images in a gallery and play videos inline.
This repository holds the listing metadata, client configs and docs. The server itself is hosted by Easy-Peasy.AI, so there is nothing to install or run.
| URL | https://easy-peasy.ai/mcp |
| Transport | Streamable HTTP (stateless) |
| Auth | OAuth 2.1 sign-in, or an API key in the x-api-key header (Authorization: Bearer <key> also works) |
| MCP Registry name | ai.easy-peasy/mcp |
Connect
Claude (claude.ai and Claude Desktop)
- Open Settings → Connectors → Add custom connector.
- Paste
https://easy-peasy.ai/mcpand click Add. - Click Connect, sign in to Easy-Peasy.AI and approve. No API key needed.
ChatGPT
With developer mode on, add https://easy-peasy.ai/mcp as a custom MCP connector, then sign in to Easy-Peasy.AI and approve. No API key needed.
Claude Code
claude mcp add --transport http easy-peasy https://easy-peasy.ai/mcp --header "x-api-key: YOUR_API_KEY"
Cursor
Add this to ~/.cursor/mcp.json, or to .cursor/mcp.json in a project:
{
"mcpServers": {
"easy-peasy": {
"url": "https://easy-peasy.ai/mcp",
"headers": { "x-api-key": "YOUR_API_KEY" }
}
}
}
This repository is also a Cursor plugin (.cursor-plugin/plugin.json and mcp.json). Set EASY_PEASY_API_KEY when you install it.
VS Code (GitHub Copilot)
Add this to .vscode/mcp.json. VS Code asks for the key the first time the server starts:
{
"inputs": [
{
"type": "promptString",
"id": "easy-peasy-api-key",
"description": "Easy-Peasy.AI API key",
"password": true
}
],
"servers": {
"easy-peasy": {
"type": "http",
"url": "https://easy-peasy.ai/mcp",
"headers": { "x-api-key": "${input:easy-peasy-api-key}" }
}
}
}
Windsurf
Add this to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"easy-peasy": {
"serverUrl": "https://easy-peasy.ai/mcp",
"headers": { "x-api-key": "YOUR_API_KEY" }
}
}
}
Gemini CLI
gemini extensions install https://github.com/Easy-Peasy-AI/easy-peasy-mcp
The extension asks for your API key once and keeps it in your system keychain.
Other clients
Any client that connects to remote MCP servers over Streamable HTTP can use https://easy-peasy.ai/mcp with the x-api-key header. A client that only runs local (stdio) servers can bridge with mcp-remote:
{
"mcpServers": {
"easy-peasy": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://easy-peasy.ai/mcp", "--header", "x-api-key:YOUR_API_KEY"]
}
}
}
API key
Create a key in Settings → API. Each key is shown once, when you create it. Treat it like a password: anyone who has it can generate on your account. Clients that sign in with OAuth, such as Claude and ChatGPT, don't need a key.
Tools
| Tool | What it does |
|---|---|
get_account |
Checks that the connection works. Returns only connected: true, no account details. |
list_templates |
Lists writing templates with their slugs and categories. |
get_template |
Shows the input fields of one template. |
generate_text |
Runs a template and returns the text. |
generate_image |
Generates an image, or edits images you pass by URL. |
get_image |
Gets a generated image by its ID. |
generate_video |
Starts a video from text or an image and returns its ID. |
get_video |
Checks a video and returns its URL once it's ready. |
display_media |
Shows existing images in a gallery or videos in a player, in clients that support MCP Apps. Spends no credits. |
list_voices |
Lists text-to-speech voices, including your cloned voices. |
generate_speech |
Turns text into speech and returns the audio URL. |
transcribe_audio |
Starts transcribing a media file or a video page link and returns its ID. |
get_transcription |
Checks a transcription and returns the transcript once it's done. |
Videos and transcriptions run in the background: the start tool returns an ID right away, and the matching get_ tool checks on it. No tool deletes data, publishes anything or contacts anyone.
Plans and credits
Connecting is free. Tools spend the credits and quotas of the connected Easy-Peasy.AI account, the same as the web app and the REST API. Image generation and transcription need a paid plan. See pricing.
Security and privacy
- OAuth 2.1 with PKCE and dynamic client registration. Access tokens expire after one hour.
- OAuth tokens and API keys are stored only as SHA-256 hashes.
- Tools act only on the connected account, through the same API routes, plan checks and rate limits as the web app.
- Privacy policy · Terms of use
Support
Email support@easy-peasy.ai. For a problem with the configs in this repository, open an issue.
License
The docs and configuration files in this repository are released under the MIT License. The Easy-Peasy.AI service itself is proprietary and covered by its Terms of Use.