Tekla Structures MCP
A Tekla Structures MCP server designed to accelerate modeling workflows through tool-based automation and natural-language interaction
What is Tekla Structures MCP?
Tekla Structures MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to tekla structures mcp server designed to accelerate modeling workflows through tool-based automation and natural-language interaction
A Tekla Structures MCP server designed to accelerate modeling workflows through tool-based automation and natural-language interaction
This server falls under the APIs and Cloud Services categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Tekla Structures MCP server designed to accelerate modelin
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx teklaConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Tekla Structures MCP
Tekla MCP Server is a Python-based MCP server that bridges AI assistants with Tekla Structures, the industry-leading 3D structural BIM software. It exposes modular toolsets for selection, view management, component insertion, property queries, modeling operations, and drawing management — all accessible through natural language. Structural engineers can describe what they need in plain text and have the AI translate it directly into Tekla operations, dramatically reducing repetitive modeling work.
Prerequisites
- Python 3.11, 3.12, or 3.13 installed
- Tekla Structures 2022 or later installed and running with an open model
- uv package manager installed (https://astral.sh/uv)
- An MCP-compatible client such as Claude Desktop or Cursor
- Read access to the Tekla Structures installation directory
Clone the repository
Download the Tekla MCP Server source code to your local machine.
git clone https://github.com/teknovizier/tekla_mcp_server.git
cd tekla_mcp_serverInstall Python dependencies
Install all required packages using uv, the fast Python package manager used by this project.
uv pip install -r requirements.txtCreate configuration files
Copy all sample configuration files to their active names. These files control Tekla path, component catalog, element types, semantic attribute overrides, and report properties.
copy config\settings.sample.json config\settings.json
copy config\element_types.sample.json config\element_types.json
copy config\semantic_overrides.sample.json config\semantic_overrides.json
copy config\base_components.sample.json config\base_components.json
copy config\report_properties.sample.json config\report_properties.jsonEdit settings.json with your Tekla path
Open config/settings.json and set the `tekla_path` property to your actual Tekla Structures binary directory. For example: C:\Program Files\Tekla Structures\2022.0\bin
{
"tekla_path": "C:\\Program Files\\Tekla Structures\\2022.0\\bin",
"read_only": false,
"excluded_tags": [],
"embeddings": {
"enabled": true,
"embedding_model": "teknovizier/minilm-tekla-attr-embed-v1"
}
}Configure your MCP client
Add the server entry to your MCP client's config file. Replace the placeholder paths with the actual absolute paths on your Windows machine. The server is launched by pointing directly at mcp_server.py.
{
"mcpServers": {
"tekla-mcp": {
"command": "python",
"args": ["C:\\path\\to\\tekla_mcp_server\\src\\tekla_mcp_server\\mcp_server.py"],
"env": {
"TEKLA_MCP_LOG_LEVEL": "INFO",
"TEKLA_MCP_LOG_FILE_PATH": "C:\\path\\to\\mcp_server.log",
"TEKLA_MCP_CONFIG_DIR": "C:\\path\\to\\tekla_mcp_server\\config"
}
}
}
}Open Tekla Structures before connecting
Ensure Tekla Structures is running and a structural model is open before starting or connecting your MCP client. The server communicates with a live Tekla instance and will fail if Tekla is not running.
Tekla Structures MCP Examples
Client configuration (Claude Desktop)
Full configuration block for claude_desktop_config.json showing required env vars for the Tekla MCP Server.
{
"mcpServers": {
"tekla-mcp": {
"command": "python",
"args": ["C:\\Users\\you\\tekla_mcp_server\\src\\tekla_mcp_server\\mcp_server.py"],
"env": {
"TEKLA_MCP_LOG_LEVEL": "INFO",
"TEKLA_MCP_LOG_FILE_PATH": "C:\\Users\\you\\mcp_server.log",
"TEKLA_MCP_CONFIG_DIR": "C:\\Users\\you\\tekla_mcp_server\\config"
}
}
}
}Prompts to try
Natural language prompts to send to your AI assistant once Tekla MCP Server is connected.
- "Select all steel beams on grid line A and report their properties."
- "Insert a Lifting Anchor component on the selected concrete slab element."
- "List all available rebar catalog entries for 16mm diameter bars."
- "Change the phase of the currently selected elements to Phase 2."
- "What macros are available in the current Tekla model?"Troubleshooting Tekla Structures MCP
Server fails to connect to Tekla with a clr or .NET error
There may be a naming conflict with a Python package called `clr`. Rename or delete `C:\Users\<User>\AppData\Local\Programs\Python\Python313\Lib\site-packages\clr` to resolve the conflict, then restart the MCP server.
Tekla is running but the MCP server reports it cannot find the model or connect
Ensure `tekla_path` in config/settings.json points to the correct bin directory for your Tekla version (e.g., C:\Program Files\Tekla Structures\2022.0\bin). For Tekla 2026, verify that `<tekla_path>\Net48Runtime` exists. Restart the MCP server after any settings change — config is read only at startup.
Semantic attribute mapping returns wrong properties
If the MiniLM embedding model fails to download or produces poor matches, set `"embeddings": {"enabled": false}` in settings.json to fall back to LLM-only attribute resolution. The model (~120 MB) downloads automatically on first use from HuggingFace.
Frequently Asked Questions about Tekla Structures MCP
What is Tekla Structures MCP?
Tekla Structures MCP is a Model Context Protocol (MCP) server that tekla structures mcp server designed to accelerate modeling workflows through tool-based automation and natural-language interaction It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Tekla Structures MCP?
Follow the installation instructions on the Tekla Structures MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Tekla Structures MCP?
Tekla Structures MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Tekla Structures MCP free to use?
Yes, Tekla Structures MCP is open source and available under the GPL-3.0 license. You can use it freely in both personal and commercial projects.
Tekla Structures MCP Alternatives — Similar APIs Servers
Looking for alternatives to Tekla Structures MCP? Here are other popular apis servers you can use with Claude, Cursor, and VS Code.
Kong
★ 43.4k🦍 The API and AI Gateway
API Mega List
★ 5.4kThis GitHub repo is a powerhouse collection of APIs you can start using immediately to build everything from simple automations to full-scale applications. One of the most valuable API lists on GitHub—period. 💪
Fetch
★ 5.4kFetch web content and convert to markdown for AI consumption
Fusio
★ 2.1kSelf-Hosted API Management for Builders
Korean Law
★ 1.8k국가법령정보MCP v4.0 | 법제처 41개 API → 17개 MCP 도구. 법령·판례·조례 검색 + LLM 환각 방지 인용검증 + 조문 영향 그래프(impact_map) + 시점 비교 자동 diff(time_travel) + 시민 5단계 실행 가이드(action_plan) | 41 Korean legal APIs → 17 MCP tools
RuleGo
★ 1.5k⛓️RuleGo is a lightweight, high-performance, embedded, next-generation component orchestration rule engine framework for Go.
Browse More APIs MCP Servers
Explore all apis servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Tekla Structures MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Tekla Structures MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.