logic-analyzer-ai-mcp
Enables remote control and automation of Saleae logic analyzers for capture, export, and protocol decoding.
README
Logic analyzer MCP
This project provides an MCP (Message Control Protocol) server and automation interface for Saleae logic analyzers. It enables remote control, automation, and integration of Saleae Logic devices and captures, making it easy to script, manage, and analyze logic analyzer data programmatically.
Features
- Device configuration management
- Capture configuration and execution
- Data export in various formats
- Logic file analysis and processing
- Protocol decoding and visualization
- Diagram generation and analysis
- MCP (Message Control Protocol) server integration
- Support for Logic 16 and other Logic 2 devices
- Capture file parsing and analysis using python-saleae
Requirements
- Python 3.10 or higher
- Saleae Logic 2 software installed
- Python-saleae module
- Logic 2 device (Logic 16, Logic Pro 8, etc.)
Installation
-
Clone the repository
-
Create and activate a virtual environment using uv:
# Create virtual environment
uv venv
# Activate virtual environment
# On Windows:
.venv\Scripts\activate
# On Unix/MacOS:
source .venv/bin/activate
- Install dependencies using uv:
# Install all dependencies
uv pip install -e .
If you encounter any issues with dependencies, you can try installing them directly:
# Install logic2-automation from GitHub
uv pip install git+https://github.com/saleae/logic2-automation/#subdirectory=python
# Install other dependencies
uv pip install grpcio protobuf grpcio-tools saleae mcp[cli] pytest
Note: This project requires Python 3.10 or higher due to dependency requirements.
Usage
Running the MCP Server
To start the MCP server for remote control:
# Using uv (recommended)
uv --directory <project_path> run -m logic_analyzer_mcp
Note: When using uv, make sure you have it installed and in your PATH. The --directory argument should point to the root directory of the project.
Current compatibility & Tested Version
This project is tested with Saleae Logic 1.2.40 for Windows.
- Please use this version for best compatibility.
- Other versions may work, but are not guaranteed or officially supported by this project.
Experimental note (alpha)
This is an experimental (alpha) version. The following MCP tool sequence has been tested and works for me:
- saleae_connect (for Saleae Logic 1.2.40)
- saleae_configure
- saleae_capture — save capture in .logicdata format
- parse_capture_file (optional)
- get_digital_data_mcp
- saleae_export (optional. use csv if needed)
Notes:
- Make sure the Saleae Logic application is running and the scripting socket server is enabled before using these tools.
- When calling saleae_capture, request the .logicdata format for best compatibility with the controller methods.
Troubleshooting & Important Notes
-
Logic Software Must Be Running:
- Before using this automation interface, ensure that the Saleae Logic software is already running on your system. The automation scripts will attempt to connect to the running instance.
- If the software is not running, the script may fail to connect, or may launch a new instance in simulation mode (which will not detect your real device).
-
Enable Scripting Socket Server:
- In the Logic software, go to
Options>Preferences(orEdit>Preferences), and ensure that the "Enable scripting socket server" option is checked. - The default port is usually 10429. If you change this, update your scripts accordingly.
- If the scripting server is not enabled, the Python API will not be able to communicate with Logic, and you will see connection errors.
- In the Logic software, go to
-
Device Not Detected:
- Make sure your Logic device is connected to your computer and recognized by the Logic software before running any scripts.
- If the device is not detected, check your USB connection and try restarting the Logic software.
-
Architecture Compatibility:
- Ensure that both the Logic software and your Python environment are either both 32-bit or both 64-bit. Mismatched architectures can cause connection failures.
-
Permissions:
- On some systems, you may need to run the Logic software and/or your Python script with administrator privileges to allow socket communication.
-
Supported Versions:
- This project is designed for Saleae Logic 1.x/2.x automation. Some features may only be available in Logic 2.x with the appropriate automation API installed.
Note on Capture File Formats
- .logicdata format is the recommended and best-supported file format for captures. All automation and parsing features are designed to work reliably with
.logicdatafiles. - .sal files (used by some older or alternative Saleae software) are currently known to have bugs and compatibility issues. Automated conversion or processing of
.salfiles may fail or require manual fixes. For best results, always use.logicdataformat for your captures.
API Reference
SaleaeController
The main controller class that provides high-level access to Logic 2 functionality.
Device Configuration Methods:
-
create_device_config(name: str, digital_channels: List[int], digital_sample_rate: int, analog_channels: Optional[List[int]] = None, analog_sample_rate: Optional[int] = None, digital_threshold_volts: Optional[float] = None) -> str- Creates a new device configuration with specified channels and sample rates
- Returns the configuration name
-
get_device_config(name: str) -> Optional[LogicDeviceConfiguration]- Retrieves a device configuration by name
- Returns None if not found
-
list_device_configs() -> List[str]- Lists all available device configuration names
-
remove_device_config(name: str) -> bool- Removes a device configuration
- Returns True if successful, False if not found
Capture Configuration Methods:
-
create_capture_config(name: str, duration_seconds: float, buffer_size_megabytes: Optional[int] = None) -> str- Creates a new capture configuration with specified duration
- Returns the configuration name
-
get_capture_config(name: str) -> Optional[CaptureConfiguration]- Retrieves a capture configuration by name
- Returns None if not found
-
list_capture_configs() -> List[str]- Lists all available capture configuration names
-
remove_capture_config(name: str) -> bool- Removes a capture configuration
- Returns True if successful, False if not found
Configurations:
Claude configuration (with uv run):
{
"mcpServers": {
"logic-analyzer-ai-mcp": {
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"<path to folder>",
"run",
"-m",
"logic_analyzer_mcp"
]
}
}
}
Claude configuration (direct usage):
{
"mcpServers": {
"logic-analyzer-ai-mcp": {
"type": "stdio",
"command": "python",
"args": [
"<path to folder>\\src\\logic_analyzer_mcp.py"
]
}
}
}
Claude configuration (with uv run):
{
"mcpServers": {
"logic-analyzer-ai-mcp": {
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"<path to folder>",
"run",
"-m",
"logic_analyzer_mcp"
]
}
}
}
Logic2 parameter description
This project includes an opt-in experimental path for Logic2 automation. It is disabled by default. You can enable it in one of three ways:
-
CLI flag (recommended for one-off runs)
- Example:
- python -m logic_analyzer_mcp --logic2
- Example:
-
Environment variable (convenient for CI / persistent shells)
- Example (Unix):
- LOGIC2=1 python -m logic_analyzer_mcp
- Example (Windows PowerShell):
- $env:LOGIC2='1'; python -m logic_analyzer_mcp
- Example (Unix):
-
Programmatic API (when embedding the library)
- Call the helper before registering tools:
- from mcp_tools import set_logic2_enabled, setup_mcp_tools
- set_logic2_enabled(True)
- setup_mcp_tools(mcp, controller)
- Or pass the explicit parameter to setup_mcp_tools:
- setup_mcp_tools(mcp, controller, enable_logic2=True)
- Call the helper before registering tools:
Notes
- Default behavior: Logic2 experimental features are OFF. When disabled the code prefers controller-based or offline fallbacks.
- Safety: Experimental features may change — enable intentionally and test with your environment before using in production.
- Troubleshooting: If enabling Logic2 fails, check that the logic2-automation / python-saleae packages are installed and that the Saleae app is running and reachable.
Claude configuration (example)
Below is a minimal Claude MCP server configuration example you can adapt. Place this under your Claude configuration file or tooling settings.
{
"mcpServers": {
"logic-analyzer-ai-mcp": {
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"<path to folder>",
"run",
"-m",
"logic_analyzer_mcp",
"--logic2"
]
}
}
}
Notes:
- Remove the
--logic2flag if you do not want experimental Logic2 tools enabled. - Adjust
<path to folder>and otheruvarguments to match your environment. - Use the
pythonbased configuration if you prefer to invoke the module directly instead of viauv.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.