MoySklad MCP (RU) runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 14 Sep 2026.
MoySklad JSON API 1.2 in your AI assistant — schema-driven, safety-gated document writes.
We read the source, 22 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
subprocess.run(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add moysklad-mcp-ru -- uvx moysklad-mcp-ru
{
"mcpServers": {
"moysklad-mcp-ru": {
"args": [
"moysklad-mcp-ru"
],
"command": "uvx"
}
}
}
[mcp_servers.moysklad-mcp-ru]
command = "uvx"
args = ["moysklad-mcp-ru"]
{
"mcpServers": {
"moysklad-mcp-ru": {
"args": [
"moysklad-mcp-ru"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"moysklad-mcp-ru": {
"args": [
"moysklad-mcp-ru"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
MOYSKLAD_TOKEN (MoySklad personal access token (Настройки → Пользователи → Токены доступа). Optional if credentials are stored in ~/.moysklad-mcp/cabinets.json.), MOYSKLAD_ALLOW_WRITE (Set to 1 to allow document writes (create/post/delete). Off by default. Point only at a TEST cabinet.).
The author declared them in the registry entry; get the values from the project itself.
Wildberries, Ozon, Yandex Market & Avito seller APIs for AI assistants: schema-driven, safety-gated.
Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.
Record your screen and export studio-styled demo videos on macOS, driven by your AI assistant.
Run AI-driven web-app and API security scans (DAST) from Claude or any MCP agent. Windows.
AI-driven penetration testing - 22 security tools behind safety-hardened MCP endpoints
Agent-First CRUD store MCP server — 1 daemon per table, schema.yaml driven, SQLite backend
Decixa MCP Server — intent-driven API discovery and selection for AI agents.
MCP server for AI assistants: read, write, edit, and manage files securely on local filesystem.
Answers built from our own checks of this server.