← Registry

AI & Machine Learning

sovagpt.ru

Provides access to multiple AI models for chat, image generation, and balance checking.

1 endpoint3 known toolsFirst detected August 1, 2026Last detected August 1, 2026

ENDPOINT 1

https://sovagpt.ru/mcp

No auth detected

MCP server metadata

Name
sovagpt
Version
2.0.0
Capabilities
tools

Known tools 3

get_balance

Текущий баланс токенов SOVAGPT

Inferred read-only
chat

Задать вопрос любой нейросети SOVAGPT (ChatGPT, Claude, Gemini, DeepSeek, Perplexity)

Inferred read-only
generate_image

Сгенерировать изображение (nanobanana2, gpt-image-2 и др.)

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.sovagpt]
url = "https://sovagpt.ru/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "sovagpt": {
      "type": "http",
      "url": "https://sovagpt.ru/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: sovagpt
Remote MCP URL: https://sovagpt.ru/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "sovagpt": {
      "url": "https://sovagpt.ru/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "sovagpt": {
      "type": "http",
      "url": "https://sovagpt.ru/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "sovagpt",
  "transport": "streamable-http",
  "url": "https://sovagpt.ru/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for sovagpt.ru was fetched 2026-08-04T20:43:05.107Z.

Trust status Neutral

sovagpt.ru is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.