MCP-CLI Adapter MCP Server | MCP Server List

Use command line tools in a secure fashion as MCP tools.

TheMCPShellis a tool that allows LLMs to safely executecommand-line toolsthrough theModel Context Protocol (MCP). It provides a secure bridge between LLMs and operating system commands.

- Flexible command execution: Run any shell commands as MCP tools, with parameter substitution through templates.
- Configuration-based tool definitions: Define tools in YAML with parameters, constraints, and output formatting.
- Security through constraints: Validate tool parameters using CEL expressions before execution, as well as optional sanboxed environmentsfor running commands.
- Quick proptotyping of MCP tools: just add some shell code and use it as a MCP tool in your LLM.
- Simple integration: Works with any LLM client supporting the MCP protocol (ie, Cursor, VSCode, Witsy...)

Imagine you want Cursor (or some other MCP client) help you with your space problems in your hard disk.
-

Create a configuration file/my/example.yamldefining your tools:

mcp: description: | Tool for analyzing disk usage to help identify what's consuming space. run: shell: bash tools: - name: "disk_usage" description: "Check disk usage for a directory" params: directory: type: string description: "Directory to analyze" required: true max_depth: type: number description: "Maximum depth to analyze (1-3)" default: 2 constraints: - "directory.startsWith('/')" # Must be absolute path - "!directory.contains('..')" # Prevent directory traversal - "max_depth >= 1 && max_depth <= 3" # Limit recursion depth - "directory.matches('^[\\w\\s./\\-_]+$')" # Only allow safe path characters, prevent command injection run: command: | du -h --max-depth={{ .max_depth }} {{ .directory }} | sort -hr | head -20 output: prefix: | Disk Usage Analysis (Top 20 largest directories):

Take a look at theexamples directoryfor more sophisticated and useful examples. Maybe you prefer to let the LLM know about your Kubernetes cluster with kubectl? Or let it run some AWS CLIcommands?

Configure the MCP server in Cursor (or in any other LLM client with support for MCP)

For example, for Cursor, create.cursor/mcp.json:

{ // you need the "go" command available "mcpServers": { "mcp-cli-examples": { "command": "go", "args": [ "run", "github.com/inercia/MCPShell@v0.1.8", "mcp", "--tools", "/my/example.yaml", "--logfile", "/some/path/mcpshell/example.log" ] } } }

You can also use relative paths and omit the.yamlextension:

{ "mcpServers": { "mcp-cli-examples": { "command": "go", "args": [ "run", "github.com/inercia/MCPShell@v0.1.8", "mcp", "--tools", "example", "--logfile", "/some/path/mcpshell/example.log" ] } } }

This will look forexample.yamlin the tools directory (~/.mcpshell/tools/by default).

See more details on how to configureCursoror Visual Studio Code. Other LLMs with support for MCPs should be configured in a similar way.

Make sure your MCP client is refreshed (Cursor should recognize it automatically the firt time, but any change in the config file will require a refresh).

Ask your LLM some questions it should be able to answer with the new tool. For example:"I'm running out of space in my hard disk. Could you help me finding the problem?".

Take a look at all the command in this document.

Configuration files use a YAML format defined here. See the this directoryfor some examples.

For deploying MCPShell in containers and Kubernetes, see the Container Deployment Guide.

For AI agent functionality that connects LLMs directly to tools, see the Donproject. Don provides:

- Direct LLM connectivity without requiring a separate MCP client
- RAG (Retrieval-Augmented Generation) support
- Multi-agent architecture
- Uses MCPShell's tool configuration format

So you will probably thing"this AI has helped me finding all those big files. What if I create another tool for removing files?".Don't do that!.

- Limit the scope of these tools toread-only actions, do not give the LLM the power to change things.
- Useconstraintsto limit command execution to safe parameters
- Consider using a sanboxed environmentfor running commands.
- Review all command templates for potential injection vulnerabilities
- Only expose tools that are safe for external use
- All of the above!

Please read the Security Considerationsdocument before using this software.

Contributions are welcome! Take a look at the development guide. Please open an issue or submit a pull request on GitHub.

This project is licensed under the MIT License - see the LICENSE file for details.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

A Model Context Protocol (MCP) server that enables AI assistants to integrate with Prometheus Alertmanager

A comprehensive MCP server for tooling interactions(40+) and resource accessibility(60+) plus many useful prompts to interact with Algorand Blockchain.

An MCP server that provides control over Android devices through ADB. Offers device screenshot capture, UI layout analysis, package management, and ADB command execution capabilities.

A Binary Ninja plugin, MCP server, and bridge that seamlessly integrates Binary Ninja with your favorite MCP client.

integration that connects BloodHound with AI through MCP, allowing security professionals to analyze Active Directory attack paths using natural language queries instead of Cypher.

A specialized MCP gateway for LLM enhancement prompts and jailbreaks with dynamic schema adaptation. Provides prompts for different LLMs using an enum-based approach.

Obtains latest dependency details for Clojure libraries.

A Model Context Protocol (MCP) server for CODESYS V3 programming environments.

Analyze large codebases and document collections using high-context models via OpenRouter, OpenAI, or Google AI -- very useful, e.g., with Claude Code

MCP-CLI Adapter

About

Details

Jump to

Setup

About

Details

Jump to

Setup

More like this

Sequential Thinking

Sentry

Github

Filesystem

EverArt

Google Drive