FERS MCP Server — structural calculations for AI agents

FERS Cloud exposes a real finite-element solver as a remote MCP server. Any MCP client — Claude, ChatGPT, Cursor, VS Code Copilot, Windsurf — can solve beams, frames and trusses, run Eurocode EN 1993-1-1 steel checks, and get a transparent hand-calc trace back. 100 free solves per week.

MCP endpoint (streamable HTTP)

https://ferscloud.com/api/mcp

Get an API key One-click install

What is the FERS MCP server?

The Model Context Protocol is an open standard that lets AI assistants discover and call external tools. FERS Cloud exposes its FEM solver as an MCP server so any compatible AI client can run structural calculations on your behalf.

Once configured, you can simply ask your AI assistant:

Use FERS to solve a cantilever beam with a 10 kN point load at the free end, 6 m span, IPE 300 steel section.

The AI will automatically call the FERS solver tools, get results, and explain the displacements, reactions, and internal forces to you.

Unlike a plain language model, FERS actually calculates: every result comes from a finite-element engine that is validated against closed-form solutions and returns the working, not a guess.

How to calculate a beam or frame with AI

Connect your AI client to the FERS MCP server, then describe the structure in plain language: span, section, supports and loads. The agent builds a solver-ready model, runs the FEM solver in the cloud, and reports deflections, reactions, internal forces and Eurocode utilization.

Check an IPE 400 in S275, 7.5 m simply supported span, 12 kN/m distributed load, to EN 1993-1-1 with FERS.

Use FERS to build a 2D portal frame — 8 m span, 4 m eaves height, HEA 240 columns, IPE 330 rafter — apply 5 kN/m snow load and report the governing utilization.

A member check returns the bending, shear, combined N+M and lateral-torsional buckling utilizations, clause by clause. A solve returns displacements, reaction forces and internal forces — every number traceable in the report.

See the full Eurocode 3 worked example Try it in the browser first — Ask FERS, no install needed

Quick start: connect in two minutes

One URL and one API key is all a client needs.

Create a FERS Cloud account at ferscloud.com
Generate an API key from your Profile page → API Keys section
Configure your AI client using one of the examples below

Using Claude or ChatGPT on the web? The one-click connector uses OAuth — no API key to paste at all.

One-click install

Add FERS to your editor or assistant with a single click, or copy one command.

Cursor

Add to Cursor

After installing, replace YOUR_API_KEY in ~/.cursor/mcp.json with your key.

VS Code / GitHub Copilot

Install in VS Code

After installing, replace YOUR_API_KEY in .vscode/mcp.json (or when prompted).

Claude Code

claude mcp add --transport http fers https://ferscloud.com/api/mcp --header "X-API-Key: YOUR_API_KEY"

One command in your terminal — then FERS is available in every Claude Code session.

Claude (web & desktop)

In Claude on the web or desktop: Settings → Connectors → Add custom connector, then paste the endpoint URL. OAuth signs you in — no key needed.

https://ferscloud.com/api/mcp

ChatGPT

ChatGPT connects through a Custom GPT Action or the connector directory — see the ChatGPT section below.

Configuration examples

The same endpoint and header work in every MCP-native client.

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "fers": {
      "url": "https://ferscloud.com/api/mcp",
      "headers": {
        "X-API-Key": "your-api-key-here"
      }
    }
  }
}

VS Code / GitHub Copilot (.vscode/mcp.json)

{
  "servers": {
    "fers": {
      "type": "http",
      "url": "https://ferscloud.com/api/mcp",
      "headers": {
        "X-API-Key": "your-api-key-here"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "fers": {
      "url": "https://ferscloud.com/api/mcp",
      "headers": {
        "X-API-Key": "your-api-key-here"
      }
    }
  }
}

Windsurf, Cline, Zed and any other streamable-HTTP MCP client use the same URL and X-API-Key header.

All 16 tools

Tool names are stable identifiers — your agent discovers them automatically. Solver calls (marked below) count toward your solve quota, and saving models to your account requires a Pro subscription; everything else is free.

solve_modelmetered solve

Run the FEM solver on a structural model JSON (displacements, forces, reactions)

validate_modelfree

Check model structure without running the solver

run_unity_checksmetered solve

Solve and return Eurocode code-check (unity) results and report

check_beammetered solve

Turnkey EN 1993-1-1 (EC3) steel member check — build, solve, and return the utilization (bending, shear, N+M, LTB)

create_beamfree

Generate a solver-ready beam model (span, section, supports, load)

create_framefree

Generate a solver-ready 2D portal-frame model

add_unity_checkfree

Author a code check against the solver's canonical schema

get_check_schemafree

Fetch the canonical schema for authoring code checks

save_modelPro

Store a model in your account (Pro subscription required — free accounts use local JSON export/import)

load_modelfree

Load a previously saved model

list_modelsfree

List the models stored in your account

list_templatesfree

Browse starter models

get_templatefree

Fetch a starter model

get_usagefree

Check this week's free solves

get_balancefree

Check your prepaid credit balance

buy_creditsfree

Get a Stripe checkout link to top up prepaid solve credits

Using ChatGPT? Custom GPT and connectors

The MCP config above works with MCP-native clients — Claude Desktop, Cursor, VS Code / Copilot, Windsurf, and custom agents. ChatGPT connects through a Custom GPT Action instead:

Create a Custom GPT and open Actions → Import from URL
Import https://ferscloud.com/api/openapi.json
Set authentication to API Key and send it as the X-API-Key header

One-click connectors (ChatGPT and Claude on the web, via OAuth) connect to the same server with no key to paste.

How much does it cost?

The first 100 successful solves every week are free — enough for daily engineering use. Beyond that, a solve costs €0.01 from a prepaid balance, or is included with Pro.

Tier	Free solves	Beyond the free tier
Free	100 / week	€0.01 / solve (prepaid credits)
Pro	Unlimited	Included with Pro subscription

Only successful solves are charged. Top up in €5 / €10 / €20 packs with buy_credits, or enable auto-reload.

Can you trust AI structural calculations?

Yes — when the AI does not do the arithmetic. FERS results come from a finite-element engine validated against closed-form analytical solutions, and every solve returns a transparent per-clause report you can check by hand. The LLM interprets; the solver calculates.

See the accuracy benchmarks Modeling conventions & units

Frequently asked questions

What is the FERS MCP server?

A remote Model Context Protocol server at https://ferscloud.com/api/mcp that lets AI assistants run real finite-element structural calculations — beams, frames and trusses, including Eurocode EN 1993-1-1 steel checks — and return the results with a hand-calc trace.

Which AI clients can use FERS?

Any MCP-compatible client: Claude (web, desktop and Claude Code), Cursor, VS Code with GitHub Copilot, Windsurf, Cline and custom agents. ChatGPT connects via a Custom GPT Action using the OpenAPI spec, or via connectors.

Do I need an API key?

For editor clients, yes — create a free account and generate a key on your Profile page. Claude and ChatGPT one-click connectors use OAuth instead, so there is no key to paste.

How much does the FERS MCP server cost?

The first 100 successful solves per week are free. After that a solve costs €0.01 from prepaid credits (€5 / €10 / €20 packs), or is included with a Pro subscription.

What can FERS calculate?

3D beams, frames and trusses with linear and nonlinear analysis: deflections, reaction forces, internal force diagrams, buckling, and Eurocode EN 1993-1-1 member checks including lateral-torsional buckling.

How accurate are the results?

The solver is validated against closed-form analytical solutions and published benchmark problems — the benchmarks page shows the comparisons. Every result includes a report you can verify line by line.

More ways to use FERS

REST API & OpenAPI spec Ask FERS — chat demo in the browser Getting started with FERS Cloud