mcp-registry/mcp-cli

    ==================
      
       /// MCP ///
      /// MCP ///
        
    ==================
        
    [server:online]
    [protocol:ready]

mcp-cli

by chrishayuk

Python-based command-line interface for interacting with Model Context Protocol (MCP) servers; offers chat, interactive shell, and automation modes with built-in LLM provider & tool management.

1.6k
270
Open Source
GitHub

01

list_tables

List all tables in the connected SQLite database

02

describe_table

Return the schema/details of a specified database table

03

read_query

Execute an SQL query against the database and return the results

04

write_file

Write provided data to a specified file (e.g., export query results to CSV)

05

analyze_data

Perform analysis on a given data file and output the results

Installation

1. Prerequisites
• Python >= 3.8
• Git
2. Clone the repository
git clone https://github.com/chrishayuk/mcp-cli.git cd mcp-cli
3. (Recommended) Create and activate a virtual environment
python -m venv .venv source .venv/bin/activate # Windows: .venv\Scripts\activate
4. Install the package and its dependencies
pip install --upgrade pip wheel pip install .
5. Verify the CLI is available
mcp --help
6. Configuration (typical)
• Export or place your MCP access token in the environment, e.g.
• Point the CLI at your MCP server if it is not the default:
export MCP_TOKEN="<your-token>" export MCP_ENDPOINT="https://your-mcp-server.example.com" The exact environment variables and authentication method may vary—see the project documentation when available.

Documentation

License: Other (GitHub reports SPDX: NOASSERTION)
Updated 7/30/2025