extract_channelsLABSCO SUMMARY
Two reads over a DLIS file, no log-viewer needed.
It answers the two questions you have when a .dlis lands on your disk: what channels are in here, and what does the metadata look like. What comes back is a folder of channels and a metadata structure to work from — there is no plotting or curve analysis on top.
What it is
A Python server that reads DLIS (Digital Log Interchange Standard) well-log files from a path on disk and writes out what is inside them: the channel data, and the file's metadata as a hierarchy.
What you get
- Every channel extracted from a DLIS file into a folder structure, with the output path returned
- The file's metadata read out as a hierarchy rather than a flat dump
- Both operations take a local file path, so the binary never has to be uploaded anywhere
- Questions like 'what channels are in this file' answered without opening a log-viewer application
Requirements
Python, and pip install mcp_server_dlis; the server then runs as python -m mcp_server_dlis. The README's Claude config sample launches mcp_server_time; the config on this page launches mcp_server_dlis, the module the package installs. Files are read from a local path, so the DLIS file has to sit on the same machine.
Setup effort
Follow the published steps — pip install mcp_server_dlis
USE CASES
01
Getting the channels out of a well log for analysis
Hand over the path to the .dlis file and the server writes every channel into a folder structure, returning the output path.
02
Seeing a file's structure before you extract anything
Read the metadata as a hierarchy, so you know which channels exist and how they nest.
03
Working through a stack of legacy log files
Each call takes one file path, so an archive folder of .dlis files can be walked one at a time in the same session.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation. A second tool is documented as get Metadata, which is not a valid tool identifier, and no working invocation name for it is shown.
Requires
pip on PATH
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install mcp_server_dlis
python -m mcp_server_dlisMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"dlis": {
"command": "python",
"args": [
"-m",
"mcp_server_dlis"
]
}
}
}The README's sample launches mcp_server_time, which is a different server; the module this package installs is mcp_server_dlis.
