API Hubs MCP Server

by apihubsru Your server? Claim it

answering

API Hubs is answering right now. Last checked 12 min ago. It exposes 8 tools.

Generate AI video, images and music. Browse models and prices; OAuth and one prepaid balance.

Uptime history 5 days of history

5 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

195 ms

Response time

average over 24h

open, no key

Access

streamable-http

Nothing serious here today

Today is the operative word: we check API Hubs every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add apihubs --transport http https://api.apihubs.ru/mcp

Settings → Connectors → Add custom connector, then paste this address

https://api.apihubs.ru/mcp

~/.codex/config.toml

[mcp_servers.apihubs]
url = "https://api.apihubs.ru/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "apihubs": {
      "url": "https://api.apihubs.ru/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "apihubs": {
      "type": "http",
      "url": "https://api.apihubs.ru/mcp"
    }
  }
}

Available tools 8

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

account

get_account

The prepaid balance generations are charged from, and where to top it up.

estimate

estimate_cost

The exact amount create_generation would charge for this request. Nothing is created or charged.

generation

create_generation

Start a generation. Charges the user's balance and returns a taskId at once; the result arrives later — poll get_task. A failed generation is refunded.

generations

list_generations

The user's generations, newest first.

model

get_model

The full parameter list, price table and an example request for one model. Call this before create_generation: parameters differ between models.

models

list_models

List the video, image and music models available, with the starting price of each. Call this first to pick a model.

task

get_task

Status of a generation and, once finished, the URLs of its files. Pass waitSeconds to wait for it to finish instead of polling in a loop.

upload

create_upload_url

Get a signed URL to PUT one local image, video or audio file (up to 25 MiB). Upload is free, but requires a positive balance. After PUT succeeds, use publicUrl as a generation input. The upload URL expires in 10 minutes; at most 20 URLs per minute per user.

Endpoints

URL	Transport	State	Latency	Checked
https://api.apihubs.ru/mcp	streamable-http	answering	170 ms	12 min ago

Alternatives to API Hubs

same job, measured the same way

API Hubs

by apistock

Generate AI video, images and music. Browse models and prices; OAuth and one prepaid balance.

8 tools answering

API Hubs

by sergiyiva

Generate AI video, images and music. Browse models and prices; OAuth and one prepaid balance.

8 tools answering

API Stock

by apistock

Generate AI video, images and music. Browse models and prices; OAuth and one prepaid balance.

8 tools answering

API Stock

by sergiyiva

Generate AI video, images and music. Browse models and prices; OAuth and one prepaid balance.

8 tools answering

Pixfaro

by pixfaro

Generate images with any major model — one API key, one prepaid balance, one MCP.

59 installs/wk 8 tools answering

HiAPI

by hiapi

Generate images, video, speech, music and text with HiAPI's AI models. OAuth or API key.

answering

FOTOhub Creative AI

by fotohub

Generate images, video, music, voice and 3D through one API. 30 tools, 200+ models.

answering

Imaginode

by imaginode

Generate AI images and videos from 89 models on one credit balance, refunds on failure.

4 tools answering

API Hubs — questions

Answers built from our own checks of this server.

What can API Hubs do?

It exposes 8 tools, read directly from the server on our last check. Among them: create_generation, create_upload_url, estimate_cost, get_account, get_model, get_task and 2 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is API Hubs working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 195 ms. The bar chart above shows every period we have measured.

How do I connect API Hubs?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does API Hubs need an API key?

No. API Hubs completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 8 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is API Hubs?

It answers our handshake in 195 ms on average, which is faster than 68% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.