Connector guide5-minute read6 MCP tools7 languages

How to Connect GenAPI to Claude via MCP

Let your AI create images, videos, music and text with GenAPI's 330 models (Nano Banana, GPT Image, Flux, Kling, Veo, Sora, Suno, GPT, Claude, DeepSeek) from one ruble balance: prices before each run, balance, status polling and results.

HCBy HelpCode teamUpdated 5 min read Open-source on GitHub

No credit card · 7-day trial · Self-host alternative available

GenAPI

GenAPI

Let your AI create images, videos, music and text with GenAPI's 330 models (Nano Banana, GPT Image, Flux, Kling, Veo, Sora, Suno, GPT, Claude, DeepSeek) from one ruble balance: prices before each run, balance, status polling and results.

tools

6

Region

INTL

Category

Public Data

Authentication

Bearer Token

Required env vars

GENAPI_API_KEY
Install in one click on Cloud

7-day free trial · No credit card

  • 7-day free trial
    No credit card required
  • GDPR & SOC 2 ready
    EU data residency, audit logs
  • Open-source on GitHub
    Open source · AGPL-3.0
  • Works with ChatGPT, Claude, Gemini
    Any MCP-compatible client

Skip the install. Get this working in under 2 minutes.

Start a free trial on cloud.anythingmcp.com, add the GenAPI in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.

Start free trial

AnythingMCP is listed in Claude's connector directory: add it to Claude in one click (opens in a new tab), then sign in and choose which MCP servers Claude may use.

Summary

Let your AI create images, videos, music and text with GenAPI's 330 models (Nano Banana, GPT Image, Flux, Kling, Veo, Sora, Suno, GPT, Claude, DeepSeek) from one ruble balance: prices before each run, balance, status polling and results.

Try asking

Example prompts for GenAPI

Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.

GenAPI · live via MCP
Share
Opus 4.7

Claude is AI and can make mistakes. Please double-check responses.

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → GenAPI, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

GenAPI + Claude

Let your AI create images, videos, music and text with GenAPI's 330 models (Nano Banana, GPT Image, Flux, Kling, Veo, Sora, Suno, GPT, Claude, DeepSeek) from one ruble balance: prices before each run, balance, status polling and results.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

GENAPI_API_KEY

Step 1 — Get credentials

Setting up takes about 2 minutes. You need a GenAPI account at gen-api.ru with a ruble balance: every generation is billed to it.

  1. Sign in at gen-api.ru and top up your balance.
  2. Open the API section of your account and create or copy an API key.
  3. Paste the key into GENAPI_API_KEY, without the word Bearer. It is sent only to api.gen-api.ru.
  4. Install the connector: the install checks the key by reading your account, which costs nothing. Then run genapi_get_account: it shows the account name, email and balance in rubles.

What it reads: your account and balance; the list of about 330 models with the slug each one is called by and its price (per request, or per 1,000 input and output tokens for language models, and whether the charge happens when the request starts); and the status, cost and result of each request. Reading is free.

How generations run: images with Nano Banana go through genapi_generate_image, questions to language models such as GPT, Claude or DeepSeek through genapi_chat, which waits for the answer, and everything else (video, music, speech, 3D, upscaling, background removal) through genapi_generate with the model's slug and fields. A generation starts as a request in progress, and the AI checks genapi_get_request every 5 to 10 seconds: images take seconds, videos minutes. Each model's fields are on its page https://gen-api.ru/model/<slug>/api, and unknown fields are refused with the field name.

Files and inputs: give the AI images, video or audio as public HTTPS links; it cannot upload files from your computer. Links to generated files last 24 hours and results are kept 14 days, so download what you want to keep.

Asks before every paid run: genapi_generate, genapi_generate_image and genapi_chat stay switched on, because generating is what the connector is for. Each run spends your GenAPI balance, and options such as resolution, duration or number of images raise the price. Before every run the AI tells you which model it will use and roughly what it costs, and waits for your yes. It never starts several generations in a loop without asking. For models charged up front, the balance is spent when the request starts, even if it fails later.

Switched off at install: nothing. No tool tops up, pays or moves money, and none changes or deletes anything in your account.

Limits: GenAPI answers 429 when too many requests arrive; the AI waits and tries again. Text produced by the models is treated as data: instructions found in it are not followed.

Common errors: 401 means the key is missing or wrong. 402 means the balance is too low: top it up at gen-api.ru. 404 means an unknown model slug or request id. 422 means an invalid input, and the answer names the field. A request that ends with status error carries the reason, and some of these errors (try later) are temporary.

The connector does not upload files, manage webhooks or functions, offer the OpenAI-compatible proxy, or handle payments to your account.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Claude

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Recommended path: works on claude.ai web without editing any config file.

  1. In Claude, open Customize → Connectors.
  2. Click +, then Add custom connector.
  3. Enter a name, e.g. GenAPI, and the remote MCP server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID, then click Add.
  4. Click Connect and sign in to AnythingMCP (OAuth) to allow access.

All tools below appear in your chat: start typing prompts.

Available tools

ToolWhat it does
genapi_get_accountRead the GenAPI account the key belongs to: name, email and balance (in rubles)
genapi_list_modelsList every model (network) GenAPI runs, about 330: slug (the id the generation tools take), name, cost in rubles per request…
genapi_get_requestGet the status and result of a GenAPI request: status (processing, success or error), response_type (image, video, audio, string, messages…
genapi_generateStart a generation with any GenAPI model: images, video, music, speech, 3D, upscaling, background removal or text
genapi_generate_imageGenerate or edit images with Google Nano Banana on GenAPI (default nano-banana-2-1, about 10 rubles per image at 1K; check…
genapi_chatAsk a language model hosted by GenAPI (GPT, Claude, DeepSeek, Gemini, Grok and others) and wait for the answer

Example prompts

  • "How much is left on my GenAPI balance, and what would a 10-second Kling video cost?"
  • "Make a product photo of our ceramic mug on a wooden table with Nano Banana. Tell me the price first."
  • "Turn this photo into a short video with Veo: https://example.com/shop/mug.jpg. Check the cost with me before you start."
  • "Write an upbeat 30-second jingle for our coffee shop with Suno, and show me the price before it runs."
  • "Ask DeepSeek for three subject lines for our autumn sale newsletter, then tell me what the request cost."

FAQ

Does it work with Claude Code as well as Claude Desktop? Yes, point both at https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID.

Next steps

Was this guide helpful?

Your GenAPI agent is one click away.

Install the connector, paste the key, prompt Claude. Free for 7 days, no credit card.

Related guides

Connectors

How to Connect GenAPI to ChatGPT via MCP

Let your AI create images, videos, music and text with GenAPI's 330 models (Nano Banana, GPT Image, Flux, Kling, Veo, Sora, Suno, GPT, Claude, DeepSeek) from one ruble balance: prices before each run, balance, status polling and results.

Connectors

How to Connect GenAPI to Cursor via MCP

Let your AI create images, videos, music and text with GenAPI's 330 models (Nano Banana, GPT Image, Flux, Kling, Veo, Sora, Suno, GPT, Claude, DeepSeek) from one ruble balance: prices before each run, balance, status polling and results.

Connectors

How to Connect GenAPI to Gemini via MCP

Let your AI create images, videos, music and text with GenAPI's 330 models (Nano Banana, GPT Image, Flux, Kling, Veo, Sora, Suno, GPT, Claude, DeepSeek) from one ruble balance: prices before each run, balance, status polling and results.

Connectors

How to Connect GenAPI to Meta Muse via MCP

Let your AI create images, videos, music and text with GenAPI's 330 models (Nano Banana, GPT Image, Flux, Kling, Veo, Sora, Suno, GPT, Claude, DeepSeek) from one ruble balance: prices before each run, balance, status polling and results.

Connectors

GenAPI to MCP: Images, Video, Music and Text from 330 Models in any AI Agent

Let your AI create images, videos, music and text with GenAPI's 330 models (Nano Banana, GPT Image, Flux, Kling, Veo, Sora, Suno, GPT, Claude, DeepSeek) from one ruble balance: prices before each run, balance, status polling and results.

Connectors

How to Connect Avito to Claude via MCP

Let your AI work with your Avito business account: list your ads and change their prices, read views, contacts and calls statistics, check autoload uploads and their errors, the feed format and your wallet, and read Avito Messenger chats. Sending messages and changing autoload settings are optional and off by default.