{
  "markdown": "# Clipia MCP\n\n**Create AI images, video, speech, music and presentations inside Claude, Cursor and ChatGPT — 60+ models in one MCP endpoint.**\n\n[![npm clipia-ai](https://img.shields.io/npm/v/clipia-ai?label=npm%20clipia-ai&logo=npm)](https://www.npmjs.com/package/clipia-ai)\n[![PyPI clipia](https://img.shields.io/pypi/v/clipia?label=PyPI%20clipia&logo=pypi&logoColor=white)](https://pypi.org/project/clipia/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](./LICENSE)\n[![MCP](https://img.shields.io/badge/Model%20Context%20Protocol-Streamable%20HTTP-7c5cff)](https://modelcontextprotocol.io)\n\nClipia is an AI creation platform. This hosted, remote **Model Context Protocol (MCP)** server lets any MCP-capable agent generate images, video, speech and music; chat with text models; plan and compose videos; create and edit presentations; poll results; browse models; search prompt templates; and read your credit balance — no SDK and no code required.\n\n**Endpoint:** `https://mcp.clipia.ai/mcp` — stateless **Streamable HTTP**, authenticated with a Clipia API key.\n\n---\n\n## Quick start\n\nConnect Clipia to Claude Code in one command (replace the placeholder with your key):\n\n```bash\nclaude mcp add --transport http clipia https://mcp.clipia.ai/mcp \\\n  --header \"Authorization: Bearer <CLIPIA_API_KEY>\"\n```\n\nThen just ask in the chat: _\"Generate a neon city image with Clipia\"_ — the preview lands right in the terminal.\n\n**Where to get a key:** create one in the [Clipia Developer Console](https://clipia.ai/en/developer). The key is shown once.\n\n**Sandbox without charges:** keys with the `clipia_test_` prefix run in a sandbox — instant mock results, no credits spent. Use a `clipia_test_*` key to validate your integration before going live.\n\n---\n\n## Connect from any client\n\nThe endpoint is the same everywhere: `https://mcp.clipia.ai/mcp`. IDEs and CLIs authenticate with an API key from the Developer Console; **claude.ai** and **ChatGPT** connect by signing in to your Clipia account over OAuth (no key needed).\n\nReady-to-paste configs live in [`examples/`](./examples).\n\n| Client                             | How to connect                                               | Auth          |\n| ---------------------------------- | ------------------------------------------------------------ | ------------- |\n| **Claude Code**                    | `claude mcp add --transport http clipia …` (see Quick start) | API key       |\n| **Claude Desktop**                 | `mcp-remote` bridge in `claude_desktop_config.json`          | API key       |\n| **claude.ai** (web/desktop/mobile) | Settings → Connectors → Add custom connector                 | OAuth         |\n| **Cursor**                         | `~/.cursor/mcp.json` (or project `.cursor/mcp.json`)         | API key       |\n| **VS Code**                        | `.vscode/mcp.json` (`servers` + `inputs`)                    | API key       |\n| **Cline**                          | `cline_mcp_settings.json` (`mcpServers`)                     | API key       |\n| **Windsurf**                       | `~/.codeium/windsurf/mcp_config.json` (`serverUrl`)          | API key       |\n| **Codex CLI**                      | `~/.codex/config.toml` (`bearer_token_env_var`)              | API key (env) |\n| **Gemini CLI**                     | `gemini mcp add --transport http clipia …`                   | API key       |\n| **ChatGPT**                        | Developer mode → Apps & Connectors → Create                  | OAuth         |\n\n### Claude Code\n\n```bash\nclaude mcp add --transport http clipia https://mcp.clipia.ai/mcp \\\n  --header \"Authorization: Bearer <CLIPIA_API_KEY>\"\n```\n\n### Claude Desktop\n\nClaude Desktop bridges to remote HTTP servers through [`mcp-remote`](https://www.npmjs.com/package/mcp-remote). Add to `claude_desktop_config.json` (Settings → Developer → Edit Config), then restart Claude Desktop:\n\n```json\n{\n  \"mcpServers\": {\n    \"clipia\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"mcp-remote\",\n        \"https://mcp.clipia.ai/mcp\",\n        \"--header\",\n        \"Authorization: Bearer <CLIPIA_API_KEY>\"\n      ]\n    }\n  }\n}\n```\n\n### claude.ai (web / desktop / mobile)\n\n1. Open **Settings → Connectors**.\n2. Click **Add custom connector** and paste the URL: `https://mcp.clipia.ai/mcp`\n3. Click **Connect** and sign in to your Clipia account — no key needed (OAuth).\n4. In a new chat, ask for an image or a video: a live Clipia card with progress and the result appears inside the message.\n\n> Credits are charged to the connected Clipia account.\n\n### Cursor\n\nAdd to `~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (project), then restart Cursor:\n\n```json\n{\n  \"mcpServers\": {\n    \"clipia\": {\n      \"url\": \"https://mcp.clipia.ai/mcp\",\n      \"headers\": { \"Authorization\": \"Bearer <CLIPIA_API_KEY>\" }\n    }\n  }\n}\n```\n\n### VS Code\n\nCreate `.vscode/mcp.json` in your workspace (or use the **MCP: Add Server** command). VS Code prompts for the key on first run and stores it securely:\n\n```json\n{\n  \"servers\": {\n    \"clipia\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.clipia.ai/mcp\",\n      \"headers\": { \"Authorization\": \"Bearer ${input:clipia_api_key}\" }\n    }\n  },\n  \"inputs\": [\n    {\n      \"type\": \"promptString\",\n      \"id\": \"clipia_api_key\",\n      \"description\": \"Clipia API Key\",\n      \"password\": true\n    }\n  ]\n}\n```\n\n### Cline\n\nCline reads `mcpServers` from its `cline_mcp_settings.json` (MCP Servers → Configure MCP Servers in the Cline panel):\n\n```json\n{\n  \"mcpServers\": {\n    \"clipia\": {\n      \"url\": \"https://mcp.clipia.ai/mcp\",\n      \"headers\": { \"Authorization\": \"Bearer <CLIPIA_API_KEY>\" }\n    }\n  }\n}\n```\n\nCline can also install this server itself — see [`llms-install.md`](./llms-install.md).\n\n### Windsurf\n\nAdd to `~/.codeium/windsurf/mcp_config.json` (note the Windsurf-specific `serverUrl` field), then refresh **Cascade → MCPs**:\n\n```json\n{\n  \"mcpServers\": {\n    \"clipia\": {\n      \"serverUrl\": \"https://mcp.clipia.ai/mcp\",\n      \"headers\": { \"Authorization\": \"Bearer <CLIPIA_API_KEY>\" }\n    }\n  }\n}\n```\n\n### Codex CLI\n\nAdd a block to `~/.codex/config.toml` and export the key into your environment — Codex injects `Authorization: Bearer` from the variable automatically:\n\n```toml\n# ~/.codex/config.toml\n[mcp_servers.clipia]\nurl = \"https://mcp.clipia.ai/mcp\"\nbearer_token_env_var = \"CLIPIA_API_KEY\"\n\n# in your environment:\n# export CLIPIA_API_KEY=<CLIPIA_API_KEY>\n```\n\n### Gemini CLI\n\n```bash\ngemini mcp add --transport http clipia https://mcp.clipia.ai/mcp \\\n  --header \"Authorization: Bearer <CLIPIA_API_KEY>\"\n```\n\nVerify the connection with `gemini mcp list`.\n\n### ChatGPT (Developer Mode)\n\n1. In ChatGPT (web): **Settings → Apps & Connectors → Advanced settings** → enable **Developer mode** (Plus, Pro, Business, Enterprise).\n2. Back in **Apps & Connectors → Create**. Name it `Clipia`, MCP Server URL: `https://mcp.clipia.ai/mcp`.\n3. Authentication — **OAuth**, tick \"I trust this application\", click **Create**.\n4. Sign in to your Clipia account in the popup. In a chat press **+ → More → Clipia**, then ask in plain text.\n\n**Supported auth header schemes:** `Authorization: Bearer clipia_*` (recommended), `Authorization: Key <key>`, or `X-Api-Key: <key>`.\n\n---\n\n## Tools\n\nThe server always exposes **10 core tools to the agent**. As of 2026-07-26, production exposes **15 agent tools**: the 10 core tools plus chat, scenario planning, server-side video composition, presentation generation and presentation editing. Seven app-only helpers are hidden from the AI agent. Compact schemas keep the agent's context window light.\n\n| Tool                    | What it does                                                                                                                                                                                                                     |\n| ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `generate_image`        | Generate image(s) from a text prompt, optionally with reference images (editing / image-to-image). Waits briefly and usually returns the finished image inline (URL + small preview). Cost in credits is returned.               |\n| `generate_video`        | Start a video generation from a text prompt (text-to-video) or from a start image (image-to-video, pass `image_url`). Returns `request_id` and cost in credits immediately — renders take 1–10 min, poll with `wait_generation`. |\n| `generate_audio`        | Generate speech from text with a selected voice and language. Returns an MP3 when complete.                                                                                                                                      |\n| `generate_music`        | Generate background music or a soundtrack from a description of mood, genre and tempo.                                                                                                                                           |\n| `wait_generation`       | Wait for a generation to finish (long-poll up to `wait_seconds`, then returns current status). Call repeatedly until `COMPLETED`, `FAILED` or `CANCELED`. Returns output URLs (and an inline preview) when done.                 |\n| `get_generation`        | Get the current status/result of a generation without waiting. When `COMPLETED`, `output.images[].url` is the inline webp preview and `output.images[].original_url` is the full-quality PNG/JPG.                                |\n| `list_models`           | List available AI models with type (text/image/video/audio), capabilities and pricing in credits. Text models expose per-1K input/output rates; generation models expose a base price. Filter by `type` / `search`.              |\n| `get_model`             | Get model details and pricing: `input_schema` for generation models; context limits and per-1K input/output rates for text models.                                                                                               |\n| `get_balance`           | Get the credit balance of the connected Clipia account and 30-day usage of the current API key.                                                                                                                                  |\n| `search_templates`      | Search 3500+ curated prompt templates (hybrid text+semantic search, Russian or English query). Each result has a ready-to-use prompt and a recommended model.                                                                    |\n| `chat`                  | _Currently enabled, feature-gated:_ chat with a text LLM using a prompt or messages array; returns reply text, token usage and credit cost.                                                                                      |\n| `generate_scenario`     | _Currently enabled, feature-gated:_ turn a brief into per-scene video prompts and a soundtrack prompt.                                                                                                                           |\n| `compose_video`         | _Currently enabled, feature-gated:_ stitch 2–20 completed scenes into a final MP4 with optional voiceover, soundtrack and subtitles.                                                                                             |\n| `generate_presentation` | _Currently enabled, feature-gated:_ render an editable PPTX, PDF and previews from a structured deck specification.                                                                                                              |\n| `edit_presentation`     | _Currently enabled, feature-gated:_ edit an existing deck, reorder or replace slides, change text and theme, and reuse unchanged illustrations.                                                                                  |\n| `app_get_generation`    | _Internal / app-only:_ status poll used by the Clipia generation viewer card (MCP Apps). Hidden from the model; prefer `get_generation`.                                                                                         |\n\n**Default models** (used when no slug is passed): `nano-banana-2` for images, `seedance-2-fast-t2v` / `seedance-2-fast-i2v` for video. Override with a model slug from `list_models`.\n\n---\n\n## Why Clipia\n\n- **Pay from Russia & CIS** — Russian bank cards, SBP, MIR, no VPN required. Western processors reject these; Clipia is built for this market (and works internationally too).\n- **60+ flagship models, one endpoint** — Western and Chinese models side by side: Veo 3.1, Sora, Kling 3, Seedance 2, Hailuo, Wan 2.7, Nano Banana, FLUX, Midjourney V7, Imagen 4, and more. No juggling multiple foreign subscriptions.\n- **Sandbox without charges** — `clipia_test_*` keys return instant mock results with no credit spend, perfect for wiring up an integration or CI.\n- **Live preview in the chat (MCP Apps)** — on claude.ai (web/desktop/mobile) every generation renders an interactive card with live progress, the finished media and an \"Original\" button. In Claude Code the preview lands inline in the terminal for vision-based iteration.\n- **3500+ prompt templates** — `search_templates` gives the agent curated, ready-to-use prompts (hybrid search, RU/EN), each with a recommended model.\n- **Cost in every response** — every generation returns its exact cost in credits, and `get_balance` shows the remaining balance. No hidden MCP markup.\n- **Compact tool surface** — 10 core tools with tight schemas keep the agent's context window light; enabled capabilities add only the tools they need.\n\n---\n\n## SDK\n\nPrefer calling Clipia from your own code instead of an agent? Use the official SDKs against the same public API (fal.ai-style `submit → status → result` queue, credits-based billing):\n\n- **TypeScript / Node:** [`clipia-ai`](https://www.npmjs.com/package/clipia-ai) — `npm install clipia-ai` (also ships a `clipia` CLI).\n- **Python:** [`clipia`](https://pypi.org/project/clipia/) — `pip install clipia` (sync + async clients).\n\nBoth support webhooks with HMAC-SHA256 signature verification and the same `clipia_test_*` sandbox keys.\n\n---\n\n## Glama server runtime\n\nThe repository includes a minimal Docker runtime so Glama can start the public\nserver entry and inspect its MCP tool definitions. The container is a stdio\nbridge to the hosted endpoint; it does not contain the Clipia application or\nany credentials.\n\nConfigure `CLIPIA_API_KEY` as a secret in Glama. Use a sandbox key with the\n`clipia_test_` prefix so validation never spends credits. The optional\n`CLIPIA_MCP_URL` setting defaults to `https://mcp.clipia.ai/mcp` and only accepts\nHTTPS URLs.\n\n```bash\ndocker build -t clipia-mcp-glama .\ndocker run --rm -i \\\n  -e CLIPIA_API_KEY='<CLIPIA_TEST_API_KEY>' \\\n  clipia-mcp-glama\n```\n\n---\n\n## Pricing\n\nBilling is in **credits** from your connected Clipia account — the same balance as the website. Every generation returns its exact credit cost, and `get_balance` shows what's left. Different models cost different credits depending on resolution, duration and quality.\n\nNew accounts receive a small pack of **welcome credits** to evaluate the platform; after that a subscription is required. Four monthly plans (Basic / Standard / Pro / Ultima) — see [clipia.ai/tariffs](https://clipia.ai/tariffs).\n\n`clipia_test_*` sandbox keys return mock results with **no credit charge** — use them to develop and test without spending.\n\n---\n\n## 🇷🇺 Для России и СНГ\n\nClipia — AI-платформа для генерации изображений, видео, речи, музыки и презентаций, а также текстовых AI-чатов и сборки готовых роликов. Для пользователей из России и СНГ доступны **оплата картой РФ, СБП и МИР, без VPN**. 60+ западных и китайских моделей (Veo 3.1, Sora, Kling 3, Seedance 2, Nano Banana, FLUX, Midjourney V7) работают через один MCP-эндпоинт прямо из Claude, Cursor и ChatGPT.\n\nПодключение в одну команду (ключ — в [консоли разработчика](https://clipia.ai/ru/developer)):\n\n```bash\nclaude mcp add --transport http clipia https://mcp.clipia.ai/mcp \\\n  --header \"Authorization: Bearer <CLIPIA_API_KEY>\"\n```\n\nКлючи `clipia_test_*` — песочница без списания кредитов для отладки. Биллинг в кредитах, стоимость каждой генерации возвращается в ответе. Тарифы: [clipia.ai/tariffs](https://clipia.ai/tariffs).\n\n---\n\n## Links\n\n- **Developers / REST API & SDK:** [clipia.ai/developers](https://clipia.ai/developers)\n- **MCP landing:** [clipia.ai/mcp](https://clipia.ai/mcp)\n- **Model catalog:** [clipia.ai/models](https://clipia.ai/models)\n- **Pricing:** [clipia.ai/tariffs](https://clipia.ai/tariffs)\n- **Get an API key:** [clipia.ai/en/developer](https://clipia.ai/en/developer)\n\n---\n\n## Support & legal\n\n- **Website:** [clipia.ai](https://clipia.ai)\n- **Documentation:** [clipia.ai/en/docs/mcp](https://clipia.ai/en/docs/mcp)\n- **Privacy Policy:** [clipia.ai/privacy](https://clipia.ai/privacy)\n- **Terms:** [clipia.ai/terms](https://clipia.ai/terms)\n- **Support:** support@clipia.ai\n\n---\n\n## License\n\nMIT — see [LICENSE](./LICENSE). © 2026 Clipia (IP Zakharov Maksim Sergeevich).\n",
  "bytes": 17121,
  "sha": "9302016bdb296fe10b7d4217e89c2c18aea520f435ef1dc11290e9ae1e352ddb",
  "repo_slug": "clipia-ai/clipia-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_clipia_ai_clipia_mcp_941f7935/readme"
}