CLI
Command-line interface for InstrMCP utilities.
Main CLI Module
InstrMCP Command Line Interface
Main CLI entry point for InstrMCP utilities.
Commands
The instrmcp command provides the following subcommands:
version
Show InstrMCP version information.
instrmcp version
Output:
InstrMCP version 2.2.0
config
Show configuration information including installation path and optional extensions.
instrmcp config
Output:
InstrMCP Configuration:
Version: 2.2.0
Package path: /path/to/instrmcp
Optional Extensions:
✅ measureit: 1.0.0
Setup Utilities
InstrMCP setup utilities for post-installation configuration.
- instrmcp.setup_utils.setup_jupyter_config()[source]
Minimal setup - InstrMCP extensions are loaded manually.
- instrmcp.setup_utils.setup_all()[source]
Run all post-install setup tasks.
- Returns:
Exit code (0 for success, 1 for failure)
- Return type:
Key Functions
setup_all
Server CLI Modules
Jupyter QCodes CLI
Environment Variables
InstrMCP respects the following environment variables:
INSTRMCP_PATH
Installation path for InstrMCP.
export INSTRMCP_PATH=/path/to/instrmcp
Used by launcher scripts to locate InstrMCP installation.
MEASUREIT_HOME
Path to MeasureIt installation (if using MeasureIt integration).
export MEASUREIT_HOME=/path/to/measureit
Used to find default database location:
$MEASUREIT_HOME/Databases/Example_database.db
QCODES_DB_LOCATION
Default QCodes database path.
export QCODES_DB_LOCATION=/path/to/database.db
Or set in QCodes config:
import qcodes as qc
qc.config.core.db_location = "/path/to/database.db"
Exit Codes
The CLI uses standard exit codes:
0: Success1: General error2: Invalid usage/arguments130: Interrupted (Ctrl+C)
Example Usage
Typical Workflow
Start server in JupyterLab:
jupyter lab
Then in notebook:
%load_ext instrmcp.extensions
%mcp_start
Connect Claude Desktop using launcher:
python agentsetting/claudedesktopsetting/claude_launcher.py
metadata tokens
Count tokens used by tool/resource metadata descriptions. Useful for optimizing context budget. By default uses the Anthropic API for exact counts, with automatic fallback to tiktoken.
instrmcp metadata tokens # API (auto-fallback to tiktoken)
instrmcp metadata tokens --offline # Force tiktoken offline estimation
instrmcp metadata tokens --source merged # Include user overrides
instrmcp metadata tokens --format json # JSON output
The standalone script is also available: python tools/token_count.py
Development Workflow
# Install in development mode
pip install -e .[dev]
# Check version
instrmcp version
# View configuration
instrmcp config