How to Connect GenAPI to Microsoft Copilot via MCP

💡 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 + Microsoft Copilot

Let your AI create images, videos, music and text with GenAPI's 330 models (Nano Banana, GPT Image, Flux, Kling, Veo, Sora, Suno, GPT, Copilot, 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, Copilot 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 Microsoft Copilot

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.

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the GenAPI tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

Available tools

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

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse