Who it is forAn engineer who wants an AI agent to run repeatable structural checks on a part and report whether the result matches beam theory.
The problemRunning a full mesh, material, load and solve sequence by hand for each variant of a part is slow and easy to get wrong.
The outcomeThe agent drives FieldCraft through its MCP server and returns a tip deflection that the user can compare with the beam theory value.
What you need first
- A computer running macOS, Windows or Linux, or a web browser for the no-install option
- The FieldCraft app from the latest release, or Rust 1.95 or later to build from source
- For the agent workflow: an MCP-capable AI agent such as Claude Code and the fieldcraft-cli binary
Steps
- Build or unpack the fieldcraft-cli binary, then note its full path.
- Register the server with Claude Code using
claude mcp add fieldcraft -- /path/to/fieldcraft-cli mcp. - Read docs/mcp.md in the repo to see which tools the server exposes and how they are called.
- Ask the agent to open the part, hex mesh it, define the material, clamp and load, solve, and report the tip deflection.
- Compare the reported deflection with the beam theory value the agent computes, and check the difference is small.
Prompt for your agent
Using the FieldCraft repo at tangency-labs/fieldcraft, connect to its MCP server with `fieldcraft-cli mcp`, open the I-beam part at <part-path>, hex mesh it, apply a clamp and a 1000 N tip load, and solve. Report the tip deflection in mm and the beam theory value with shear, and verify the two values agree within a small tolerance before answering.
Caveat. The MCP walkthrough in the README is a demo session with shortened waits, so a real run may take longer and the part path must be supplied by the user.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page