Store API

com.store-apiPublished by store-api.comOfficial publisherv1.0.0Updated Oct 24, 2026

GPT, Claude, Gemini, DeepSeek, Grok, Qwen and GLM through one API key. Pay per token.

VerifiedStreamable HTTPWeb executableMedia & DesignAI & ML

Overview

AI-generated overview

Remote MCP endpoint that lets an assistant query many third-party LLMs (GPT, Claude, Gemini, DeepSeek, Grok, Qwen, GLM) through one paid Store API key.

What you can do
List the model catalog with prices in rubles per 1M tokens, optionally filtered by provider, and compare 2 to 4 models on the same question side by side with token counts. Ask any catalog model a question and get the answer as text, so the assistant can consult a second model from inside the current chat. Generate an image from a text prompt and get a link back. Check the remaining balance on the key and review spending history per model over the last N days with request counts.
When to use it
Useful when you want a second opinion from another model without leaving Cursor, Claude Desktop or Claude Code, when comparing answers from several models on one question, or when you need image generation and per-model spending tracking under a single prepaid key.
Requirements
Remote Streamable HTTP endpoint; no local runtime. A Store API account and key (sk-shop-…) sent as an Authorization Bearer header, or as a key query parameter for clients that cannot send headers. Network access to the provider's endpoint; payment is per token in rubles.
Before you install
Every ask_model, compare_models and generate_image call spends money on the key, and compare_models bills each model separately. The key is a paid credential; passing it in the URL query string is less safe than a header because URLs can end up in client logs. Prompts and questions are sent to the third-party provider and to the selected model vendors.

Installation

In SourceWeft

  1. Open Store API in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.store-api%2Fstore-api/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "store-api": {
      "type": "http",
      "url": "https://store-api.com/mcp"
    }
  }
}

README

Store API — MCP server

One MCP endpoint that gives your AI client access to GPT, Claude, Gemini, DeepSeek, Grok, Qwen and GLM through a single API key. Ask another model from inside your current chat, generate images, check your balance — without leaving Cursor, Claude Desktop or Claude Code.

Built for developers in Russia: payment with locally issued cards, no VPN required, prices in rubles, pay per token with no subscription.

  • Endpoint: https://store-api.com/mcp (Streamable HTTP)
  • Auth: Authorization: Bearer sk-shop-…, or ?key=sk-shop-… in the URL for clients that cannot send headers
  • Get a key: https://store-api.com/login — free account, pay only for what you use
  • Setup guide (Russian): https://store-api.com/mcp-guide

Tools

ToolWhat it does
ask_modelAsk any model from the catalog and get the answer back as text. Sitting in Claude, ask GPT-6 or Gemini — and the other way around.
list_modelsCatalog with prices in rubles per 1M tokens, optionally filtered by provider.
generate_imageGenerate an image from a prompt, returns a link.
balanceRemaining funds on your key.

Setup

Cursor

~/.cursor/mcp.json:

json
{  "mcpServers": {    "store-api": {      "url": "https://store-api.com/mcp",      "headers": {        "Authorization": "Bearer sk-shop-YOUR_KEY"      }    }  }}

Claude Desktop and other clients without header support

Pass the key in the URL:

json
{  "mcpServers": {    "store-api": {      "url": "https://store-api.com/mcp?key=sk-shop-YOUR_KEY"    }  }}

A header is safer than a query string — a URL may end up in client logs. Keys can be revoked and reissued at any time in the dashboard.

Claude Code

bash
claude mcp add --transport http store-api "https://store-api.com/mcp?key=sk-shop-YOUR_KEY"

Check that it works

Ask your assistant: "show my Store API balance". If it answers with an amount, you are connected. Then try "ask GPT-6 Sol what it thinks about this code".

Pricing

Same as regular API calls: you pay for the tokens of the model you invoked, at the catalog price. There is no extra charge for the MCP server itself and no subscription. Current prices: https://store-api.com/#plans

Models

OpenAI (GPT-6, GPT-5 family, GPT-4o), Anthropic (Claude Opus, Fable, Sonnet, Haiku), Google (Gemini), DeepSeek, xAI (Grok), Qwen, Z.ai (GLM), plus image models. The full list with prices is returned by list_models.

По-русски

MCP-сервер сервиса Store API: доступ к GPT, Claude, Gemini, DeepSeek, Grok, Qwen и GLM по одному ключу, оплата картой российского банка, без VPN и подписок.

Подключается к Cursor, Claude Desktop, Claude Code и другим клиентам с поддержкой MCP — примеры настроек выше. Ключ берётся в личном кабинете, списание идёт по факту за токены.

Подробная инструкция на русском: https://store-api.com/mcp-guide

License

MIT

Source: README.md at commit 95d9bbb

Tools

6

list_models

Каталог моделей

List available Store API models with prices in rubles per 1M tokens. Use it before ask_model to pick a model. — Список моделей Store API с ценами в рублях за 1 млн токенов.

Parametersprovider

ask_model

Спросить модель

Ask any model from the Store API catalog — GPT, Claude, Gemini, DeepSeek, Grok, Qwen, GLM — and get the answer as text. Lets you consult a second model from inside the current chat. — Задать вопрос любой модели каталога и получить ответ текстом.

Parametersmodelrequiredpromptrequiredsystemmax_tokens

generate_image

Нарисовать картинку

Generate an image from a text prompt and return a link to it. — Сгенерировать изображение по описанию, возвращает ссылку.

Parameterssizemodelpromptrequired

get_balance

Остаток на ключе

Remaining balance on your Store API key, in rubles. — Остаток средств на ключе в рублях.

Takes no parameters.

get_usage

История трат

Spending history for this key: how much went to each model over the last N days, with request counts. — История трат по ключу: сколько ушло на каждую модель за последние N дней.

Parametersdays

compare_models

Сравнить модели

Ask 2 to 4 models the same question at once and get their answers side by side with token counts. Every model is billed separately. — Задать один вопрос нескольким моделям сразу и сравнить ответы.

Parametersmodelsrequiredpromptrequiredsystemmax_tokens

Version history

1
  1. v1.0.0LatestSep 24, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts