
petro-mcp
io.github.petroptPublished by GitHub account petroptv1.1.2Updated Oct 24, 2026
MCP server for petroleum engineering: LAS logs, decline curves, PVT, petrophysics, volumetrics.
Overview
Local MCP server for petroleum engineering work: LAS well logs, decline curves, PVT calculations, petrophysics and volumetrics.
- What you can do
- Work with LAS well-log files, presumably reading and interpreting log data.
- Run decline-curve analysis on production data.
- Perform PVT calculations for reservoir fluids.
- Carry out petrophysical and volumetric computations.
- The manifest lists no individual tools, so the exact operations are not documented here.
- When to use it
- Worth adding when an assistant is helping with reservoir or production engineering tasks such as log interpretation, decline analysis, PVT estimates or volumetric calculations, and you want those computations done locally rather than by hand.
- Requirements
- Runs as a local process on the user's machine, installed from the PyPI package petro-mcp and started with uvx, so a Python environment with uv/uvx is needed. No authentication, environment variables or headers are declared. Desktop only; not available as a web endpoint.
Installation
In SourceWeft
- Open petro-mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
This repository has no README.
Tools
0Version history
1- v1.1.2LatestSep 16, 2026
Score
25% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
- License10 pts
Declare a license in the repository or the registry entry.