Flow-Registration

Provides programmatic access to Flow-Registration motion correction for 2-photon microscopy data via the MCP interface.

python

0

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "flowregsuite-mcp-flowreg": {
      "command": "python",
      "args": [
        "-m",
        "flowreg_mcp"
      ]
    }
  }
}

You can run the Flow-Registration MCP server to expose motion correction capabilities for 2-photon microscopy data via the Model Context Protocol. This enables AI assistants and other MCP clients to programmatically access Flow-Registration functionality for denoising and stabilizing imaging data.

How to use

Once the MCP server is running, you can connect an MCP client to it and issue motion correction requests against your microscopy datasets. The server exposes Flow-Registration capabilities through the standard MCP interface, allowing you to feed in raw 2-photon movie or volumetric data and receive motion-corrected results. Use your client’s typical workflow to load data, select a motion-correction workflow, run the correction, and retrieve the aligned output for further analysis or visualization.

How to install

Prerequisites: You need Python 3.10 or higher and the FastMCP framework installed in your environment.

Step 1: Clone the project and install dependencies.

git clone https://github.com/FlowRegSuite/flowreg-mcp.git
cd flowreg-mcp
pip install -r requirements.txt

Step 2: Install the MCP server in editable mode so you can run it and develop against it.

pip install -e .

Additional setup and configuration

To run the MCP server from your environment, configure your MCP client to connect as shown below. This example uses a local command to start the server via Python.

{
  "mcpServers": {
    "flowreg": {
      "command": "python",
      "args": ["-m", "flowreg_mcp"],
      "cwd": "/path/to/flowreg-mcp"
    }
  }
}

Troubleshooting and notes

If you encounter issues starting the server, ensure your Python environment is using Python 3.10+ and that all dependencies in requirements.txt are installed. Verify that the path in cwd points to your local flowreg-mcp checkout and that you can import flowreg_mcp without errors in a Python shell.

Security and access

Limit access to the MCP server to trusted clients and networks. If you plan to expose the server beyond a secure internal network, consider adding authentication or network-level protections as appropriate for your environment.

Notes

This MCP server is in alpha development. Expect rapid changes and incomplete features as the project progresses.

Available tools

MotionCorrection

Performs motion correction on 2-photon microscopy data using Flow-Registration algorithms, exposed through the MCP interface.