Skip to content
Store API logo

Store API MCP server

Which MCP servers are Store API's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-25

← Back to Store API

Whose server it is
  • Registry namecom.store-api/store-apiverified in the MCP registry

The registry name sits under store-api.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-25
  • Stateanswerschecked 2026-10-25
  • Tools6
  • Server calls itselfstore-api
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 166 ms.

Should an agent connect itNot proven either way yet
  • Its tools do call several AI model APIs with one key, but not point the OpenAI SDK at a custom base URL.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • For "call several AI model APIs with one key", the likely first call is compare_models.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-10-25
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it1 of 2 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer706 ms
  • Space in an agent's context≈ 705 tokensthe definitions of all its tools (6), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results6 of 6 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · call several AI model APIs with one key
  • not sure · connect Cursor or Cline to model APIs
  • cannot · point the OpenAI SDK at a custom base URL

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers6 tools · read 2026-10-25
  • list_models

    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.

  • ask_model

    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…

  • generate_image

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

  • get_balance

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

  • get_usage

    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.

  • compare_models

    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.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

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

Add it

Claude Code, in a terminal

claude mcp add --transport http store-api https://store-api.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://store-api.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.