1. Conduid
  2. Developer Tools
  3. CLI
MCP server · Developer Tools

CLI

MCP-CLI is a command-line tool for interacting with and testing Model Context Protocol (MCP) servers.

54Fair

Scored 3 months ago · breakdown

About CLI

CLI is an MCP server published by OpenSystemsLab in the Developer Tools category: mCP-CLI is a command-line tool for interacting with and testing Model Context Protocol (MCP) servers. It has been installed 0 times through Conduid.

The repository has 2 stars and 0 forks, with the last commit 6 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues (0) before depending on it in production.

Install

Install
npx mcp-cli

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about CLI

Powered by Claude · Grounded in docs

I know everything about CLI. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

MCP-CLI

MCP-CLI is a command-line tool for interacting with and testing Model Context Protocol (MCP) servers. It provides a user-friendly terminal user interface (TUI) for selecting and executing tools offered by an MCP server.

Features

  • Multiple Transports: Connect to MCP servers using stdio, sse (Server-Sent Events), or http (streamable HTTP).
  • Interactive TUI: A terminal user interface built with bubbletea that allows you to:
    • Select a tool from a list of available tools.
    • Browse and query MCP resources.
    • Enter arguments for the selected tool in a form.
    • View the results of the tool execution.
  • Resource Browser: A new tab in the TUI for listing and querying MCP resources.
  • Prompt Browser: A new tab in the TUI for listing MCP prompts.
  • Debug Panel: A scrollable debug panel on the right side of the TUI that shows:
    • Informational logs (key presses, state changes).
    • The arguments sent to the tool in a pretty-printed JSON format.
    • The results of tool calls.
  • Verbose Logging: Use the -v flag to enable verbose logging to a debug.log file for troubleshooting.

Installation

You can install mcp-cli using go install:

go install mcp-cli

Alternatively, you can build it from source.

Building from Source

  1. Clone the repository:
    git clone <repository-url>
    cd mcp-cli
    
  2. Build the executable:
    go build
    
    This will create an mcp-cli executable in the current directory.

Usage

The mcp-cli tool has three main commands, one for each transport protocol.

stdio

Connect to an MCP server that communicates over standard input/output.

mcp-cli stdio --env "VAR=value" --env "ANOTHER_VAR=another_value" "<command-to-start-server>"

The --env (or -e) flag can be used multiple times to pass environment variables to the server process.

Example:

mcp-cli stdio -e "API_KEY=12345" "python /path/to/mcp/server.py"

sse

Connect to an MCP server that uses Server-Sent Events (SSE).

mcp-cli sse --header "Header-Name: header-value" <server-url>

The --header (or -H) flag can be used multiple times to pass custom HTTP headers to the server.

Example:

mcp-cli sse -H "Authorization: Bearer my-token" http://localhost:8080/mcp

http

Connect to an MCP server that uses streamable HTTP.

mcp-cli http --header "Header-Name: header-value" <server-url>

The --header (or -H) flag can be used multiple times to pass custom HTTP headers to the server.

Example:

mcp-cli http -H "Authorization: Bearer my-token" http://localhost:8080/mcp

Global Flags

  • -v, --verbose: Enable verbose logging to debug.log.

TUI Guide

When you connect to an MCP server, you will be presented with a terminal user interface.

  • Tool Selection View: A list of available tools. Use the arrow keys to navigate and press Enter to select a tool. Press r to switch to the resource browser or p to switch to the prompt browser.
  • Resource Browser View: A list of available resources. Use the arrow keys to navigate and press Enter to view the resource details. Press t to switch back to the tool selection view or p to switch to the prompt browser.
  • Prompt Browser View: A list of available prompts. Use the arrow keys to navigate. Press t to switch back to the tool selection view or r to switch to the resource browser.
  • Argument Input View: A form for entering the arguments for the selected tool. Use Tab to switch between fields and Enter to submit the tool call.
  • Resource Detail View: Shows the content of the selected resource. Press Esc to return to the resource list.
  • Debug Panel: The right-hand panel shows a scrollable log of events, tool calls, and results. Use the up and down arrow keys to scroll through the log.
  • Navigation:
    • t: Switch to the tool selection view.
    • r: Switch to the resource browser view.
    • p: Switch to the prompt browser view.
    • Esc: Return to the previous view. - Ctrl+C: Exit the application.

README mirrored from the source repository 3 months ago. The original is authoritative.

Questions

About CLI

How do I install CLI?

Run npx mcp-cli, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is CLI safe to use with an AI agent?

Its trust score is 54 out of 100 (fair). It passes 0 of 1 static security checks; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is CLI still maintained?

The last commit was 6 months ago, with 0 open issues. That's long enough that you should check whether the maintainer is responding to issues before depending on it.