OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

MCP Client CLI

MCP Client CLI is a Python command-line client for prompting LLM providers and connecting to MCP-compatible servers. It supports provider configuration for OpenAI, Groq and local models via llama.cpp, and lets users define MCP server commands and tool-call confirmation rules in a configuration file.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

MCP Client CLI — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an LLM prompt or MCP tool workflow belongs in a terminal, or when you want to pass shell output or files into a prompt. Configure the provider and MCP servers first.

Who it is for

  • Developers who want to prompt LLMs from a terminal.
  • People configuring MCP-compatible servers for command-line use.
  • Shell users who want to pass command output, files or images to an LLM.

Documented uses

  • Send a prompt to a configured LLM provider from the terminal.
  • Connect prompts to tools exposed by configured MCP servers.
  • Pipe text or images into a prompt.
  • Use documented prompt templates for Git review, commit-message drafting or YouTube summarization.
Before you choose

Requirements & limits

The repository identifies the project as open source under the MIT license.

  • It is a CLI workflow rather than a graphical client.
  • You configure the LLM provider and MCP servers yourself.
  • Tool calls can be set to require confirmation; the README also documents a flag to bypass confirmations.
  • Image input is documented for use with multimodal LLMs.
  • The README documents pip installation and Python-based project implementation.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and configure MCP Client CLI

Set up the CLI with an LLM provider and MCP server definitions.

Before you start

  • Python package installation with pip
  • An LLM provider configuration and API key, either in the config file or an environment variable
  • Configuration details for the MCP servers you want to use

Steps

  1. Install the package with the command below.

    Documented command
    pip install mcp-client-cli

  2. Create ~/.llm/config.json or $PWD/.llm/config.json with the LLM provider, model and API key, plus the MCP server definitions you intend to use.

  3. Run a prompt with the llm command, such as llm "What is the capital city of North Sumatra?".

Expected outcome

The CLI is configured to submit prompts to the selected LLM provider and use the specified MCP server configuration.

Guide limitations

  • The README points to CONFIG.md for the full configuration format.
  • Each configured MCP server and provider requires its own setup; the example configuration includes server-specific commands and, for Brave Search, an API key.
Documentation 1 ↗
Source-based practical guide

Send piped text or image input to a prompt

Provide command output, file content or an image as input to an LLM prompt.

Before you start

  • MCP Client CLI installed and configured with an LLM provider
  • Text on standard input or an image file; image analysis requires a multimodal LLM

Steps

  1. Pipe text into llm, optionally adding a prompt, for example echo "Given a location, tell me its capital city." | llm "West Java".

  2. For image input, pipe an image file to the CLI with a question, for example cat screenshot.png | llm "Is there any error in this screenshot?".

Expected outcome

The supplied text or image is included as input for the configured LLM to respond to or analyze.

Guide limitations

  • Image analysis is described for multimodal LLMs.
  • Shell characters such as &, | and ; may be interpreted by the shell when used in an unquoted prompt.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 November 2026
Original website title
adhikasp/mcp-client-cli · Official homepage title · retained in its source language
How we review sourcesSuggest a correction