vincent-pli/mcp-cli-host

A CLI host application that enables Large Language Models (LLMs) to interact with external tools through the Model Context Protocol (MCP). Currently supports Openai, Azure Openai, Deepseek and Ollama models.
English | 简体中文
## What it looks like: 🤠
## Features ✨
Interactive conversations with multipe LLM models
Support for multiple concurrent MCP servers
Dynamic tool discovery and integration
Configurable MCP server locations and arguments
Configurable message history window for context management
Monitor/trace error from server side
Support Sampling, Roots, Elicitation, retrievling Resource, Prompts
Support runtime exclude specific tool
Show MCP server card when connected
display image from tool call output
## Latest Update 💌
[2025-11-26] Support display image from tool call output
[2025-07-18] Support Streamable HTTP mcp server, OAuth process not support yet
[2025-07-02] Support Elicitation
[2025-06-27] Deal with Prompts in MCP server: Link
[2025-06-20] Deal with Resources in MCP server: Link
## Environment Setup 🔧
1. For Openai and Deepseek:
bash
export OPENAI_API_KEY='your-api-key'
By default for Openai the base_url is "https://api.openai.com/v1"
For deepseek it's "https://api.deepseek.com", you can change it by --base-url
2. For Ollama, need setup firstly:
Install Ollama from https://ollama.ai
Pull your desired model:
bash
ollama pull mistral
Ensure Ollama is running:
bash
ollama serve
3. For Azure Openai:
bash
export AZURE_OPENAI_DEPLOYMENT='your-azure-deployment'
export AZURE_OPENAI_API_KEY='your-azure-openai-api-key'
export AZURE_OPENAI_API_VERSION='your-azure-openai-api-version'
export AZURE_OPENAI_ENDPOINT='your-azure-openai-endpoint'
4. For Google Gemini
bash
export GEMINI_API_KEY='your-gemini-api-token'
## Installation 📦
bash
pip install mcp-cli-host
## Configuration ⚙️
MCPCLIHost will automatically find configuration file at ~/.mcp.json. You can also specify a custom location using the --config flag:
### STDIO mcp server
json
"mcpServers": {
"sqlite": {
"command": "uvx",
"args": [
"mcp-server-sqlite",
"--db-path",
"/tmp/foo.db"
},
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/tmp"
Each MCP server entry requires:
command: The command to run (e.g., uvx, npx)
args: Array of arguments for the command:
For SQLite server: mcp-server-sqlite with database path
For filesystem server: @modelcontextprotocol/server-filesystem with directory path
### Remote mcp server(only support Streamable HTTP)
json
"mcpServers": {
"github": {
"url": "https://api.githubcopilot.com/mcp/",
"headers": {"Authorization": "Bearer "}
## Usage 🚀
MCPCLIHost is a CLI tool that allows you to interact with various AI models through a unified interface. It supports various tools through MCP servers.
### Available Models
Models can be specified using the --model (-m) flag:
Deepseek: deepseek:deepseek-chat
OpenAI: openai:gpt-4
Ollama models: ollama:modelname
Azure Openai: azure:gpt-4-0613
Gemini: gemini:gemini-2.5-flash
### Examples