mostai-mcp
Advanced tools
MCP server for MostAI (most-ai.com): generate images, video, music, speech and text with 60+ models from Claude Code, Claude Desktop or any MCP client
Generate images, video, music, speech and text with 60 models through your MostAI account — from Claude Code, Claude Desktop or any MCP client.
MostAI прямо в вашем ИИ-помощнике: просите словами — он генерирует картинки, видео, музыку, озвучку. Нужны Claude Code или Claude Desktop, Google Chrome и аккаунт MostAI.
# 1. Поставить uv (если ещё нет) — Windows (PowerShell):
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
# ...или macOS / Linux: curl -LsSf https://astral.sh/uv/install.sh | sh
# 2. Поставить и настроить сервер (одна команда всё сделает и откроет окно входа):
uv tool install "mostai-mcp[login]"
mostai-mcp setup
Войдите в аккаунт MostAI в открывшемся окне Chrome (Google, ВКонтакте, почта — любым способом), перезапустите Claude Code и скажите: «Сгенерируй картинку красного велосипеда на пляже через MostAI». Первые картинки на Nano Banana 2 — бесплатные. Вопросы и помощь со входом: Telegram https://t.me/mostAI_com, чат на https://most-ai.com или contact@most-ai.com.
mostai-mcp is an MCP server that connects Claude to your own MostAI
account. You sign in once (Google, VK or email — any method MostAI offers); after that Claude
can pick a model, price a job,
generate, look at the result and save the file for you. Generations spend your real MostAI
balance (₽) — with free quota used automatically wherever it exists.
The catalogue is read live from the API at every call, so new models appear without updating this package — 60 live models in the 2026-09-03 snapshot.
Prerequisites: uv, Google Chrome, a MostAI account, and an MCP client — Claude Code or Claude Desktop.
# 1. Install uv if you don't have it — Windows (PowerShell):
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
# ... or macOS / Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
# 2. Install and set up the server
uv tool install "mostai-mcp[login]"
mostai-mcp setup
The same two commands work on Windows in PowerShell — no repository download needed.
The [login] extra pulls in Playwright, used only by the one-time mostai-login
sign-in window; without it the server runs but cannot open a sign-in browser.
mostai-mcp setup does the whole install in one pass: registers the mostai server with
Claude Code at user scope (claude mcp add mostai -s user -- …), installs the usage
skill into ~/.claude/skills/mostai/SKILL.md, seeds ~/.mostai-mcp/.env with safe spend
limits, opens the sign-in window (skipped if you are already signed in), then prints your
balance, free quota and the first thing to try. Flags: --no-login, --skip-claude,
--print-desktop-config, --config-dir PATH (override CLAUDE_CONFIG_DIR / ~/.claude).
Install as above, then run mostai-mcp setup --skip-claude --print-desktop-config.
It prints the path of your claude_desktop_config.json — %APPDATA%\Claude\ on
Windows, ~/Library/Application Support/Claude/ on macOS, ~/.config/Claude/ on Linux —
and the block to paste into it:
{ "mcpServers": { "mostai": { "command": "/full/path/to/mostai-mcp" } } }
--skip-claude skips the Claude Code CLI registration, which is pointless if you only use
Desktop. Restart Claude Desktop after editing the file.
mostai-mcp is a standard stdio MCP server, so any MCP client can run it. First install it
and sign in once — the same thing mostai-mcp setup does for Claude Code:
uv tool install "mostai-mcp[login]"
mostai-login # one-time sign-in (Google, VK, email…); the session is stored in your keyring
Then point your client at the mostai-mcp command. Codex has no mcp add command, so
edit ~/.codex/config.toml directly:
[mcp_servers.mostai]
command = "mostai-mcp"
Cursor, VS Code, Windsurf and other clients — register a stdio MCP server whose command
is mostai-mcp (or uvx mostai-mcp to run it without a global install), then restart the
client. The usage skill that mostai-mcp setup installs is Claude-only; other clients rely
on the tool descriptions the server already exposes, so no extra setup is needed.
Restart Claude Code (or Desktop) and say: "Generate an image of a red bicycle on a beach
with MostAI". The first Nano Banana 2 images are free — free quota per model is
reported by get_balance().free_generations and list_free_generations(), and the tools
use it automatically.
Sign-in happens in a separate Chrome window, not your normal one. That is not a
preference: modern Chrome (App-Bound Encryption, verified against Chrome 152 on
2026-09-03) encrypts its cookie store so no other program can read it, and holds the
Cookies file open exclusively while it runs, so it cannot even be copied. So
mostai-login opens its own Chrome profile (~/.mostai-mcp/pw-profile/) where you sign in to
MostAI once — by whatever method your account uses (Google, VK, email, …). The profile persists — later refreshes need no re-login,
and your everyday Chrome can stay open.
The cookie is read from, in order: the MOSTAI_COOKIE environment variable (for
headless/CI use), the system keyring (Windows Credential Manager / macOS Keychain /
Linux SecretService, service mostai-mcp) — the normal case — and ~/.mostai-mcp/.env,
a plain-text fallback for environments with no working keyring. Check status without
opening a browser with mostai-login --check.
If a tool returns 401 / session expired, run mostai-login again. The running server
re-reads the cookie from the keyring on an auth error and retries once, so no server
restart is needed — which matters for long-lived processes like Claude Desktop.
24 tools. Their docstrings in the server are the authoritative reference — that is what your MCP client actually reads.
| Tool | What it does |
|---|---|
| Catalogue | |
list_models(type?, sort_by_price?, include_deprecated?) | Live catalogue with price, free_left, capabilities (image:edit, video:first_last_frame, low_moderation, …), accepted inputs, no_prompt, credits_per_message. Retired models hidden by default |
describe_model(model_id) | One model's exact parameters and options, attachment slots, voices, dance presets, price and a copyable example_call |
| Account | |
get_balance() | Balance in ₽, low-balance alert, and free generations per model |
spending_status() | Balance plus the configured spend guards |
whoami() | Email, message credits, permissions |
list_free_generations() | Remaining free runs per model (-1 = unlimited) |
estimate_price(model, prompt?, aspect_ratio?, duration?, quality?, parameters?) | Price a job in ₽ without running it; invalid values are refused here |
topup(amount_rub?) | The MostAI top-up page link (pay_url) — the user pays there, choosing country and payment method themselves; this server cannot take or confirm a payment |
| Text | |
chat(prompt, model?, system?, session?) | Text reply. Spends message credits, not ₽. Default chatgpt-free is free and unlimited |
ask_second_opinion(question, files?, model?, session?, confirm?) | An independent take from a different model — optionally on files it reads (documents, spreadsheets, images-as-OCR, audio/video). Default chatgpt-free is free; a paid model quotes the price and asks first |
| Images | |
generate_image(prompt, model?, aspect_ratio?, quality?, images?, …) | Text-to-image; images = references. Default google/nano-banana-2 |
edit_image(prompt, source, model?, …) | Image-to-image: transform an existing picture (URL or local path, or a list) |
| Video | |
generate_video(prompt, model?, duration?, quality?, mode?, images?, videos?, audios?, …) | Text-to-video. Default xai/grok-imagine-video. mode: model-specific — reference/frames on seedance-2.x/2.5, wan-3.0, minimax-h3, veo-3.1; tone (normal/fun/spicy) on grok — see describe_model |
animate_image(prompt, source, model?, mode?, …) | Animate a still photo; prompt describes the motion. On the reference/frames models, mode defaults to frames HERE (a still photo is the point of this tool) — pass mode="reference" to opt out; two pictures then become the first and last frame |
| Audio | |
generate_audio(text, model?, voice?, style?, dialogue?, …) | Speech (elevenlabs/v3, google/gemini-3.1-flash-tts), multi-speaker dialogue, or music (suno: text = lyrics, style = genre) |
| Any model | |
generate_media(model, prompt?, images?, videos?, audios?, named_images?, preset?, parameters?, …) | Call any model in the catalogue, including the prompt-less apps |
| Files & gallery | |
media_status(public_id) | Poll an async generation |
download_media(url, dest_path?) | Save the binary to disk (default ~/.mostai-mcp/downloads) |
preview_media(url_or_public_id) | Show the image inline so Claude can judge it (video: its thumbnail) |
list_gallery(limit?, success_only?, tag?, public?) | Your gallery, or the public explore feed |
| Lifecycle | |
share_link(public_id) | Public share URL — https://most-ai.com/s/{public_id} |
publish_media(item_id, published?) | Publish or unpublish to the public gallery |
like_media(item_id) | Like a generation |
delete_media(item_id) | Permanently delete one of your generations (irreversible) |
Every generator also accepts save_path, max_price, confirm and wait; all of them
except generate_audio also accept free_mode (audio has no free tier).
| Say this | What runs |
|---|---|
| "Generate an image of a red bicycle on a beach" | generate_image → google/nano-banana-2 (free quota) |
| "Make this photo look like a watercolour painting" | edit_image(source=…) |
| "Turn this photo into a 5-second video" | animate_image → xai/grok-imagine-video |
| "Cut out the background of this picture" | generate_media("background-remover-v1", images=[…]) |
| "Put my face on this portrait" | generate_media("faceswap", named_images={"swap_image": …, "input_image": …}) |
| "Upscale this photo 4×" | generate_media("prunaai/p-image-upscale", images=[photo], parameters={"factor": "x4"}) |
| "Make this portrait say this line" | generate_media("kling/ai-avatar", images=[photo], audios=[voice]) |
| "Make a dancing video from this photo" | generate_media("kwaivgi/kling-v2.6-motion-control", images=[photo], preset="…") |
| "Read this text in a warm female voice" | generate_audio → elevenlabs/v3 |
| "Write me a song about autumn in Yekaterinburg" | generate_audio → suno (text = lyrics, style = genre) |
| "How much would a 10-second clip on Kling 3.0 cost?" | estimate_price — no money spent |
| "Get a second opinion on this plan from another model" | ask_second_opinion(question, files?) — free on chatgpt-free |
free_mode=None (the default) runs for free whenever the model still
has free quota and you did not pin a paid quality/duration; the result reports
free_mode, free_locked and free_left_after. True forces free, False always pays.MOSTAI_WARN_PRICE (default
50₽) returns needs_confirmation with the price and charges nothing; it runs only when
the call is repeated with confirm=True. Set MOSTAI_WARN_PRICE=0 to turn the gate off.MOSTAI_MAX_PRICE is an optional absolute hard cap (unset by default) — anything
above it is refused outright; MOSTAI_MIN_BALANCE (default 50₽) drives the low-balance
alert; per-call max_price= caps a single generation.chat spends message credits
(whoami().message_credits, credits_per_message in list_models(type='text')) — a
text model showing price_rub: 0 is not free.save_path / dest_path write wherever the agent asks —
the server does not restrict paths, so keep untrusted content out of the prompt.estimate_price(model, …) with the parameters you actually
intend to use, or list_models. price_from: true means the listed price is the
cheapest tier ("from") — longer or higher-quality jobs cost more.Orientation only, from the 2026-09-03 catalogue snapshot: images ≈ 3–26₽ (the popular ones ≈ 3–10₽), the prompt-less AI apps ≈ 3–26₽, TTS ≈ 4₽, a song ≈ 20₽, prompted video ≈ 14–66₽ plus a per-second charge. Always check the live price before spending.
Questions, or a stuck sign-in? Reach the MostAI team:
uv tool upgrade mostai-mcp
Close Claude Code before updating — while it runs it locks the installed executable
and the reinstall fails. Restart it afterwards. get_balance() and whoami() add an
update_available line when a newer release is out (checked at most once a day).
Everything lives in ~/.mostai-mcp (override with the MOSTAI_HOME env var): .env
(spend limits, and the cookie only as a keyring fallback), pw-profile/ (the dedicated
Chrome profile used for sign-in), downloads/ (default destination of download_media
and save_path), version_check.json (cache of the daily update check). The session
cookie itself lives in the system keyring under the service name mostai-mcp.
mostai-login. No server
restart needed.chat on a paid text model with no credits left.
Check whoami().message_credits, top up, or switch to chatgpt-free.failed: true with alternatives — the model refused or errored (moderation is the
usual cause). Rephrase, or try one of the listed alternative models.needs_confirmation in the result — the job costs ≥ MOSTAI_WARN_PRICE. Nothing
was charged; repeat the call with confirm=True to proceed.list_models() for current ids; include_deprecated=True shows retired ones.uv tool update-shell and restart it.claude CLI not found — setup prints the manual step; once the CLI is installed run
claude mcp add mostai -s user -- /full/path/to/mostai-mcp yourself.mostai-mcp is an unofficial connector to the private app API behind
chatbot.most-ai.com. It authenticates with your browser session cookie and speaks to:
| Endpoint | Used for |
|---|---|
GET /api/v1/models-v2 | The live model catalogue (readable without auth) |
POST /api/v1/attachments | Upload input files up front (free); the body then references them by uuid |
POST /api/v1/images/price | Price a job (pure JSON body) |
POST /api/v1/images/generate | Start a generation (multipart with a json field) |
GET /api/v1/images/shared/{public_id} | Poll the result |
POST /api/v1/chat | Text, streamed over SSE |
The catalogue is the source of truth: parameters, attachment slots, prompt-vs-app
expectations and prices are normalized from models-v2 and validated against it before a
request is sent, so there is no hardcoded model list to go stale.
Source access and contributions are handled by the MostAI team — reach us through the
Support channels above. Licensed under the MIT License, © 2026 MostAI.
MCP registry name: io.github.most-ai-com/mostai-mcp.
Disclaimer. This is an unofficial connector to a private API that is not a public, versioned contract — endpoints and fields can change without notice if MostAI updates the app. Model names and descriptions come from the MostAI catalogue and are in Russian, the way the site itself presents them.
FAQs
MCP server for MostAI (most-ai.com): generate images, video, music, speech and text with 60+ models from Claude Code, Claude Desktop or any MCP client
We found that mostai-mcp demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Research
/Security News
The compromise affects MemTensor's MemOS, an open source memory framework for large language models (LLMs) and AI agents. Both npm package @memtensor/memos-cloud-openclaw-plugin and the PyPI package MemoryOS are compromised. They drop cross-platform Go binaries that exfiltrate developer secrets.
Security News
Lovable’s OJ rewrites Vite’s dev server in Rust, reducing memory use and preview times as AI lowers the cost of open source reimplementation.
Security News
It has been one year since Shai-Hulud made its first appearance on npm.