Endor provides instant, private, sandboxed environments for your favorite services anywhere Node is available. Run MariaDB, PostgreSQL and many more servers securely and in just a few seconds. Perfect for AI agents and humans in a hurry.
- • Basic MCP protocol features implemented (12/40)
- • Room for improvement in GitHub community
- • Optimal dependency management (20/20)
- • Room for improvement in deployment maturity
- • Documentation (8/8)
- • Archestra MCP Trust score badge is missing
{
"endorhq-cli-mcp": {
"command": "npx",
"args": [
"-y",
"@endorhq/cli",
"mcp"
],
"env": {}
}
}Endor
Endor provides instant, private, sandboxed environments for your favorite services anywhere Node is available. Run MariaDB, PostgreSQL and many more servers securely and in just a few seconds. Nothing extra to install, everything runs locally. Perfect for AI agents and humans in a hurry.
Each service will run in an ephemeral, isolated VM that only exposes the application ports. When you are done, you can exit Endor with CTRL+C and everything is gone without leaving a trace in your system.
MCP mode allows the services to be launched and used from AI tools like agents and IDEs. Your agents can now securely and safely launch database servers or KV stores as part of their capabilities!
An experimental full-networking mode can be optionally enabled, allowing you to run a fully-featured Alpine Linux machine.
Need a MariaDB database? Just type endor run mariadb. Claude Code wants to run a Valkey instance? Just run endor mcp.
Learn more in the official documentation.
Get started
Install Endor:
npm install -g @endorhq/cli
Run your first service:
endor run mariadb
You can also run the service without installing the CLI with npx:
npx -y @endorhq/cli run mariadb
Supported applications
- Alpine
- MariaDB
- Memcached
- Redis
- Postgres
- RabbitMQ
- Valkey
Connect to your AI agents
Endor connects to your AI agents using the Model Context Protocol (MCP). You can run it directly using npx:
npx -y @endorhq/cli mcp
Follow these guides to configure your favorite agent tools:
License
By using Endor, you accept our End-User License Agreement (EULA).
[](https://archestra.ai/mcp-catalog/endorhq__cli)Endor
Endor provides instant, private, sandboxed environments for your favorite services anywhere Node is available. Run MariaDB, PostgreSQL and many more servers securely and in just a few seconds. Nothing extra to install, everything runs locally. Perfect for AI agents and humans in a hurry.
Each service will run in an ephemeral, isolated VM that only exposes the application ports. When you are done, you can exit Endor with CTRL+C and everything is gone without leaving a trace in your system.
MCP mode allows the services to be launched and used from AI tools like agents and IDEs. Your agents can now securely and safely launch database servers or KV stores as part of their capabilities!
An experimental full-networking mode can be optionally enabled, allowing you to run a fully-featured Alpine Linux machine.
Need a MariaDB database? Just type endor run mariadb. Claude Code wants to run a Valkey instance? Just run endor mcp.
Learn more in the official documentation.
Get started
Install Endor:
npm install -g @endorhq/cli
Run your first service:
endor run mariadb
You can also run the service without installing the CLI with npx:
npx -y @endorhq/cli run mariadb
Supported applications
- Alpine
- MariaDB
- Memcached
- Redis
- Postgres
- RabbitMQ
- Valkey
Connect to your AI agents
Endor connects to your AI agents using the Model Context Protocol (MCP). You can run it directly using npx:
npx -y @endorhq/cli mcp
Follow these guides to configure your favorite agent tools:
License
By using Endor, you accept our End-User License Agreement (EULA).
Related MCP Servers
mcp-shrimp-task-manager
88/100Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.
cognee-mcp
86/100Memory for AI Agents in 5 lines of code
shadcn-ui-mcp-server
82/100A mcp server to allow LLMS gain context about shadcn ui component structure,usage and installation,compaitable with react,svelte 5,and vue
mobile-mcp
81/100Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)
HuggingFace
80/100Remote MCP server for HuggingFace services - access models, datasets, and spaces
markitdown-mcp
80/100Python tool for converting files and office documents to Markdown.