1. Conduid
  2. AI
  3. Tc MCP
MCP server · AI

Tc MCP

SIEMENS Teamcenter Model Context Protocol (MCP) Server

Unclaimed last commit 7 months ago ai
34Low

Scored 7 days ago · breakdown

About Tc MCP

Tc MCP is an MCP server published by goenninger-b-t in the AI category: sIEMENS Teamcenter Model Context Protocol (MCP) Server.

The repository has 8 stars and 1 forks, with the last commit 7 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/goenninger-b-t/tc-mcp

This 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.

Ask AI

✦

Ask AI about Tc MCP

Powered by Claude · Grounded in docs

I know everything about Tc MCP. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 3 days ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • !License declaredNo license file. Legally you have no right to use it in a product.
  • ✓Tests presentA test suite exists in the repository.
  • !Dependencies pinnedNo lockfile. Installs can pull different code over time.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.

1 check has not been run yet.

Releases

A0100A0100

README

SIEMENS Teamcenter Model Context Protocol (MCP) Server

Welcome to tc-mcp! This project provides a robust, zero-crash-tolerant bridge between modern AI assistants (like Claude, Gemini, or any MCP-compatible agent) and Siemens Teamcenter (TC).

Written entirely in Unison, this MCP Server exposes the vast and complex capabilities of Teamcenter's RESTful API (JsonRestServices/SOA) as clean, well-documented, and highly resilient AI tools. By connecting this server to an AI client, you can command and query your Product Lifecycle Management (PLM) system using natural language.

🛡️ Cyber Resilience Act (CRA) Compliance: This project maintains strict supply chain security standards. An SPDX 3.0.1 conforming Software Bill of Materials (SBOM) is continuously updated and provided alongside all releases.


🚀 For Teamcenter Users & Administrators

If you use Siemens Teamcenter (version 2412 or higher) to manage digital twins, Bills of Materials (BOMs), datasets, and engineering change workflows, this server is your AI co-pilot's access key.

What it does

By installing this MCP server into your AI assistant, your AI can automatically perform complex PLM tasks on your behalf:

  • Search & Discovery: Query items by ID or use complex saved queries to find parts and documents.
  • Item & Data Management: Create new Item Revisions, revise objects, copy them, and manage custom properties.
  • Files & Datasets: Create datasets (PDFs, CAD models) and securely commit binary file uploads.
  • Structure Management (BOM): Open BOM windows, apply Revision Rules (e.g., "Latest Working"), add children to parent lines, and expand multi-level structures.
  • Change & Workflow Management: Start workflows, create ECR/ECO change items, relate problem/solution items, and create rule/action handlers.

Getting Started (Client Configuration)

To run the server, ensure you have UCM (Unison Codebase Manager) installed, then configure your AI client (like Claude Desktop) using the provided launcher scripts.

macOS/Linux:

{
  "mcpServers": {
    "tc-mcp": {
      "command": "/absolute/path/to/tc-mcp/tc-mcp-server.sh",
      "env": {
        "TC_USER": "infodba",
        "TC_PASSWD": "infodba",
        "TC_SERVER_URL": "http://your-teamcenter-server.com:8080"
      }
    }
  }
}

Windows:

{
  "mcpServers": {
    "tc-mcp": {
      "command": "C:\\absolute\\path\\to\\tc-mcp\\tc-mcp-server.bat",
      "env": {
        "TC_USER": "infodba",
        "TC_PASSWD": "infodba",
        "TC_SERVER_URL": "http://your-teamcenter-server.com:8080"
      }
    }
  }
}

💻 For Unison Programmers

This project serves as a premier example of utilizing Unison in enterprise environments, specifically designed to meet DO-178C and ISO 26262 ASIL D compliance standards for high-reliability systems.

Architecture Overview

The repository is split into distinct boundary layers to ensure the purity of the core logic while managing the inherently unsafe nature of network requests:

  • tc_mcp.core: Pure, side-effect-free data structures. Implements bounded types, localization, and a Syslog-standard Tracer to ensure deterministic behavior.

  • tc_mcp.network: The safe REST boundary. Wraps unison-http with exponential backoff and retry capabilities to handle TC 5xx/4xx errors gracefully. It also houses JsonParser, utilizing unison-json for strict contract validation.

  • tc_mcp.tc_api: Domain-specific Unison wrappers over Siemens SOA endpoints. It manages stateful X-XSRF-Token headers and transforms raw JSON maps into typed Unison values.

  • tc_mcp.mcp_server: The MCP transport layer. It maps the internal API into 30+ standardized AI tools and provides the stdio JSON-RPC event loop.

Working with the Codebase

The Unison source files (.u) mirror the namespace structure inside src/.

To explore the available tools and documentation directly within UCM:

.> pull <remote> tcmcp/main
.> run tc_mcp.mcp_server.help ()

To run the integration test suite (requires an active TC connection):

ucm -p tcmcp/main run.tests

Compiling the Server

If you modify the tools or the MCP JSON-RPC loop, you must recompile the runtime binary for the shell scripts:

echo "compile tc_mcp.mcp_server.server.main mcp_server.uc" | ucm -p tcmcp/main

Philosophy

  • Zero-Crash Tolerance: Exception abilities are caught at the outermost boundary and serialized into standard JSON-RPC error payloads.
  • Abilities for Effects: Interaction with HTTP and the File System is strictly mediated by custom Unison Abilities, allowing seamless mocking during Unit and Integration tests.

README fetched from the repository 3 days ago. The original is authoritative.

Questions

About Tc MCP

How do I install Tc MCP?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Tc MCP safe to use with an AI agent?

Its trust score is 34 out of 100 (low). It passes 3 of the 5 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Tc MCP still maintained?

The last commit was 7 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.