MCP Cli Host MCP Server

A CLI host application that enables Large Language Models (LLMs) to interact with external tools through the Model Context Protocol (MCP). Currently

Local serverstdio

What is the MCP Cli Host MCP server?

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. Exposed over MCP by the mcp cli host mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

  • 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

Adding it to your client

mcp-cli-host on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Its toolset

Everything the assistant can do here goes through one of these:

  • Examples — The Examples tool exposed by this server
  • Flags — The Flags tool exposed by this server

Configuration

You will need 6 environment variables: OPENAI_API_KEY, AZURE_OPENAI_DEPLOYMENT, AZURE_OPENAI_API_KEY, AZURE_OPENAI_API_VERSION, AZURE_OPENAI_ENDPOINT, GEMINI_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp cli host mcp server does with a few real requests.

When to reach for it

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. MCP Cli Host's toolset — Examples, Flags — is a fair guide to whether it matches your workflow. It is maintained by vincent-pli; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
ExamplesThe Examples tool exposed by this server.
FlagsThe Flags tool exposed by this server.

How to install the MCP Cli Host MCP server

{
  "mcpServers": {
    "cli-host": {
      "command": "uvx",
      "args": ["mcp-cli-host"],
      "env": {
        "OPENAI_API_KEY": "your-value",
        "AZURE_OPENAI_DEPLOYMENT": "your-value",
        "AZURE_OPENAI_API_KEY": "your-value",
        "AZURE_OPENAI_API_VERSION": "your-value",
        "AZURE_OPENAI_ENDPOINT": "your-value",
        "GEMINI_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
OPENAI_API_KEYCredential the server authenticates with.Yes
AZURE_OPENAI_DEPLOYMENTConfiguration value read at startup.Optional
AZURE_OPENAI_API_KEYCredential the server authenticates with.Yes
AZURE_OPENAI_API_VERSIONConfiguration value read at startup.Optional
AZURE_OPENAI_ENDPOINTConfiguration value read at startup.Optional
GEMINI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use MCP Cli Host to Examples.
  • Use MCP Cli Host to Flags.

Frequently asked questions

It connects MCP Cli Host to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (Examples, Flags) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Cli Host directly.