About TeklaMCP
TeklaMCP is an MCP server published by osc-bouw in the Developer Tools category: c# Tekla MCP server.
The repository has 2 stars and 0 forks, with the last commit yesterday. Recent commit activity is the strongest signal that reported issues will get attention.
Install
git clone https://github.com/osc-bouw/TeklaMCPThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (10)
DeleteObjectDelete a single object by GUID
Parameters not published.
DeleteObjectsDelete multiple objects by GUID in one call
Parameters not published.
FilterModelQuery model objects by type, name, profile, material, class, or user-defined attributes
Parameters not published.
GetUserSelectionRead the objects currently selected by the user in Tekla
Parameters not published.
ModifyBeamModify profile, material, position, or endpoints of an existing beam
Parameters not published.
OverlappingNumberingFind parts with duplicate cast-unit or assembly numbers
Parameters not published.
PlaceBeamPlace a beam between two 3D coordinates
Parameters not published.
PlaceBeamsPlace multiple beams in a single call
Parameters not published.
PlaceColumnPlace a column at a base point with a given height
Parameters not published.
UserSelectedBeamPrompt the user to pick a beam and return its properties
Parameters not published.
Ask AI
Ask AI about TeklaMCP
Powered by Claude · Grounded in docs
Security checks
- ✓README presentThe repository ships documentation.
5 checks have not been run yet.
README
TeklaMCP
A Model Context Protocol (MCP) server for Tekla Structures, enabling AI assistants (Claude, Cursor, etc.) to read and modify your structural model through natural language.
What it does
TeklaMCP runs as a WPF desktop application alongside Tekla Structures. It exposes a local HTTP server (http://127.0.0.1:51234/) that speaks the MCP protocol — so any MCP-compatible AI client can place beams, query objects, delete elements, and more, all by calling into the live Tekla model.
MCP Tools
| Tool | Description |
|---|---|
PlaceBeam |
Place a beam between two 3D coordinates |
PlaceBeams |
Place multiple beams in a single call |
PlaceColumn |
Place a column at a base point with a given height |
ModifyBeam |
Modify profile, material, position, or endpoints of an existing beam |
FilterModel |
Query model objects by type, name, profile, material, class, or user-defined attributes |
GetUserSelection |
Read the objects currently selected by the user in Tekla |
UserSelectedBeam |
Prompt the user to pick a beam and return its properties |
DeleteObject |
Delete a single object by GUID |
DeleteObjects |
Delete multiple objects by GUID in one call |
OverlappingNumbering |
Find parts with duplicate cast-unit or assembly numbers |
MCP Resources
| Resource URI | Description |
|---|---|
tekla://model/object-names |
Distinct list of all part names in the model |
tekla://model/grids |
All grid objects with coordinates and axis labels |
Requirements
- Windows (WPF desktop app)
- Tekla Structures 2023 or later, with a model open
- .NET Framework 4.8
- An MCP-compatible AI client (Claude Desktop, Cursor, etc.)
Usage
- Open a model in Tekla Structures.
- Launch TeklaMCP (
TeklaMcp.Server.exe). - Click Start — the server starts at
http://127.0.0.1:51234/. - Configure your MCP client to connect to that URL.
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"tekla": {
"url": "http://127.0.0.1:51234/"
}
}
}
Health check
GET http://127.0.0.1:51234/health
Returns {"status":"ok"} when the server is running.
Audit log
Every tool call is appended to:
%APPDATA%\Develoh\Tekla\mcp-audit.log
Each line is a JSON object with timestamp, tool, args, success, and message.
Project structure
TeklaMcp.Contracts/ - Shared DTOs (args and result types)
TeklaMcp.Plugin/ - WPF app + MCP server host
McpHostedServer.cs - HTTP listener, JSON-RPC 2.0 dispatcher
Tekla/ - TeklaModelFacade wrapping the Tekla Open API
Tools/ - One class per MCP tool
Logging/ - Audit log
License
About
TeklaMCP is created by Develoh.
Need a custom AI implementation in Tekla Structures or Revit? We build tailored solutions for structural engineering workflows. Get in touch at develoh.com.
README copy captured when this server was indexed; it may lag the repository. The original is authoritative.