
MCP-CLI
OfficialFreeCommand line interface for MCP server interactions.
Free · Opens the source repo
What MCP-CLI does
MCP-CLI is a command line interface designed to facilitate interactions with Model Context Protocol (MCP) servers. This tool is particularly useful for developers and system integrators who need to communicate with various external systems, such as APIs, databases, and filesystems, directly from the command line. By providing a straightforward set of commands, MCP-CLI allows users to discover available MCP servers and their associated tools, explore tool parameters, and execute commands with specified arguments.
The workflow of MCP-CLI is intuitive and follows a clear sequence: users can start by listing all available servers and tools with the mcp-cli command. Once they have identified the server they want to work with, they can delve deeper into the specific tools available on that server. This exploration includes viewing tool parameters and obtaining the full JSON schema for each tool, which is essential for understanding the expected input format. After gathering the necessary information, users can execute commands by passing JSON arguments, making it easy to integrate with other systems or automate tasks.
MCP-CLI is ideal for developers looking to streamline their workflow when interacting with multiple external resources. It is particularly beneficial in environments where automation and quick access to various tools are crucial. With features like searching for tools by name and obtaining JSON output for scripting, MCP-CLI enhances productivity and allows for efficient command execution without the need for complex setups.
Overall, MCP-CLI serves as a powerful utility for anyone needing to interact with MCP servers through a command line, offering a structured approach to manage and utilize external tools effectively.
When to use it
Use MCP-CLI when you need to quickly access and manage tools on MCP servers from the command line, especially in development or automation scenarios.
When not to use it
This tool may not be suitable for users who prefer graphical interfaces or those who do not require command line access to MCP servers.
What you can build with it
Automating API Calls
Use MCP-CLI to automate API calls to various external services, streamlining your development process.
Exploring Tool Parameters
Quickly explore and understand the parameters required for different tools on MCP servers using the command line.
Integrating with External Systems
Easily integrate with external systems by executing commands directly from the terminal, enhancing productivity.
How to install MCP-CLI
View source1. Install with the skills CLI
npx skills add github/awesome-copilot/mcp-cli --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by githubMCP-CLI
Access MCP servers through the command line. MCP enables interaction with external systems like GitHub, filesystems, databases, and APIs.
Commands
| Command | Output |
|---|---|
mcp-cli | List all servers and tool names |
mcp-cli <server> | Show tools with parameters |
mcp-cli <server>/<tool> | Get tool JSON schema |
mcp-cli <server>/<tool> '<json>' | Call tool with arguments |
mcp-cli grep "<glob>" | Search tools by name |
Add -d to include descriptions (e.g., mcp-cli filesystem -d)
Workflow
- Discover:
mcp-cli→ see available servers and tools - Explore:
mcp-cli <server>→ see tools with parameters - Inspect:
mcp-cli <server>/<tool>→ get full JSON input schema - Execute:
mcp-cli <server>/<tool> '<json>'→ run with arguments
Examples
# List all servers and tool names
mcp-cli
# See all tools with parameters
mcp-cli filesystem
# With descriptions (more verbose)
mcp-cli filesystem -d
# Get JSON schema for specific tool
mcp-cli filesystem/read_file
# Call the tool
mcp-cli filesystem/read_file '{"path": "./README.md"}'
# Search for tools
mcp-cli grep "*file*"
# JSON output for parsing
mcp-cli filesystem/read_file '{"path": "./README.md"}' --json
# Complex JSON with quotes (use heredoc or stdin)
mcp-cli server/tool <<EOF
{"content": "Text with 'quotes' inside"}
EOF
# Or pipe from a file/command
cat args.json | mcp-cli server/tool
# Find all TypeScript files and read the first one
mcp-cli filesystem/search_files '{"path": "src/", "pattern": "*.ts"}' --json | jq -r '.content[0].text' | head -1 | xargs -I {} sh -c 'mcp-cli filesystem/read_file "{\"path\": \"{}\"}"'
Options
| Flag | Purpose |
|---|---|
-j, --json | JSON output for scripting |
-r, --raw | Raw text content |
-d | Include descriptions |
Exit Codes
0: Success1: Client error (bad args, missing config)2: Server error (tool failed)3: Network error
Frequently asked questions about MCP-CLI
Similar skills
WinMD API Search
Easily find and explore Windows desktop APIs.
WebMCPify
Transform any web app into an agent-ready platform.
Phoenix Tracing
Instrument LLM applications with OpenInference tracing.
Foundry Hosted Agent CopilotKit
Guidance for developing agentic web apps on Azure.
Power Automate Foundation
Connect AI agents to Power Automate seamlessly.
Power Automate Flow Builder
Efficiently build and deploy Power Automate flows programmatically.
