PIPESIM MCP servers and AI agent skills

How AI connects to PIPESIM

An MCP server or skill can only do what PIPESIM lets programs do. PIPESIM exposes 2 automation interfaces:

• Pipesim Python Toolkit (Sixgill) (Python): The Python Toolkit is a set of SLB and open-source modules shipped with its own Python distribution. The sixgill package does the work, exchanging data with Pipesim as pandas DataFrames, while the lower-level manta module isn't meant for direct use. It runs separately from the Pipesim UI, but you can't edit the same model in the UI and the toolkit at once. SLB says it is included with the base simulator licences and isn't yet at parity with the UI. Documentation
• Excel integration (Other): The toolkit's documentation has a separate Excel integration section, and SLB's extensibility page describes building models from scratch, updating them, running simulations and sending results back to Excel or a dashboard from Python. Documentation

What SLB offers

SLB lists a Tela agentic-AI assistant for Pipesim (catalogue page dated 27 July 2026). It gives a natural-language interface to run simulations, generate plots, find production bottlenecks and automate reporting, and a PTK AI assistant that builds and runs Python Toolkit workflows. It works inside SLB's environment, not as an MCP server. The SLB Developer MCP server searches the toolkit documentation only.

Checked 4 Nov 2026. Sources: Tela agentic-AI assistant for Pipesim (SLB Tela catalogue), AI Assistant and MCP integration (SLB Developer)

What you can do with PIPESIM and AI

• Open a well or network model through sixgill, list its branches, wells and fluids, and report the boundary conditions set on each source and sink.
• Run a nodal analysis or network simulation for a set of wellhead pressures and return the operating points as a table.
• Sweep choke settings or gas-lift rates across a field network and rank the cases by total oil rate.
• Write a Python Toolkit script from a plain-language description of a study, using the documentation the SLB Developer MCP server returns.

Taken from the listings' own documentation. Check each listing for exactly what it supports.

Installing

The listings here document setup for ChatGPT, Claude, Codex, Cursor and VS Code. Install steps, copied from each project's own documentation, are on each listing's page. Most PIPESIM integrations run on your own computer next to PIPESIM, so you need PIPESIM installed and licensed on the same machine unless the listing says otherwise.