Skip to main content

mcp-client-console

MCP client that connects to a remote MCP server, LLM backend (API key or local model) and preset configuration files.

Intended for use within private network for Cybersecurity purposes.

System:  {user} <--> mcp-client-console <--> network <--> {box} <--> mcp-server-remote <--> tools
Client:  {user} <--> cli.py <--> client.py <--> mcp SDK <--> * <--> mcp-server-remote

User Guide | LLM Backend Setup

Skip this section if using an API LLM connection. For a local model, set up Ollama before installing the client:

curl -fsSL https://ollama.com/install.sh | sh   # Linux. macOS: brew install ollama. Windows: winget install Ollama.Ollama
ollama pull qwen2.5:14b                         # default model in config_default.toml
ollama list                                     # confirm Ollama is running and the model is pulled

To use a different model, pull it the same way and update model under [llm.local] in your config.toml to match the tag exactly. host under [llm.local] must include the full scheme: http://127.0.0.1:11434... not 127.0.0.1:11434.

User Guide | Installation

Users:

pipx install mcp-client-console
mcp-client-console

Developers:

git clone https://github.com/geomux/mcp-client-console.git
cd mcp-client-console
python3 -m venv .venv && source .venv/bin/activate
pip install -e .
mcp-client-console

User Guide | Configuration

First run creates a default config.toml and prints its filepath (the /config command in the terminal chat prints it too). Edit it... populate with server name, url, token:

[server]
name = "Box_1"
url = "http://127.0.0.1:9000/mcp"
OS Config filepath
Linux ~/.config/mcp-client-console/config.toml
macOS ~/Library/Application Support/mcp-client-console/config.toml
Windows %LOCALAPPDATA%\mcp-client-console\config.toml

User Guide | Operation

Start your MCP server first (see repos below) and confirm the client is configured to reach it. The client connects, performs the MCP handshake, and lists the server's tools. Use LLM natural language in the CLI to access tools on the remote box:

$ mcp-client-console
Connected to Box_1 @ http://127.0.0.1:9000/mcp

How may I help you today?

Related / Required Repos

Project Status

  • Create MCP client repo
  • Connect to MCP server locally
  • LLM backend (API / local Ollama) added to client
  • Connect to MCP server remotely (e.g. over the internet)
  • Add TLS + bearer auth as requirement

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_client_console-0.4.0.tar.gz (42.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_client_console-0.4.0-py3-none-any.whl (55.8 kB view details)

Uploaded Python 3

File details

Details for the file mcp_client_console-0.4.0.tar.gz.

File metadata

  • Download URL: mcp_client_console-0.4.0.tar.gz
  • Upload date:
  • Size: 42.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.5

File hashes

Hashes for mcp_client_console-0.4.0.tar.gz
Algorithm Hash digest
SHA256 1cb3a0b4439e528b5962434aca64e8c14a3b0e1a0260539395053d5478122823
MD5 8ce5f8fe3f249b6bf62d4cfbc5f1f511
BLAKE2b-256 430296595672c58788f4f28bc5922a5aea8b103334c75fc2f5e902e5006b3fa5

See more details on using hashes here.

File details

Details for the file mcp_client_console-0.4.0-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_client_console-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 8d81c470ddafc8152910c6f460e4b0881853acb14e583042568196de9e0b1c86
MD5 933d3f9479adbc694733e81fc372bfc0
BLAKE2b-256 321cbd34bdd8247f8ccaad74bf049b92974360743f02c86fd8644e247b5c6322

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page