We use cookies on our website to analyze website usage and to help secure the website against misuse. Advertising and functional cookies are not used in our site or our web application products.
By clicking “Accept Essential Cookies Only”, you consent to us placing these cookies.
The Model Context Protocol (MCP) is an open standard that allows AI assistants to connect to external tools and data sources. The xAssets MCP Server is a free, open-source bridge between your xAssets instance and any MCP-compatible AI assistant — including Microsoft Copilot, Claude, ChatGPT, and others.
Instead of navigating menus and building queries manually, your team can ask questions in plain English and get answers directly from your asset data. The MCP server handles authentication, permissions, and data access through the xAssets API — your AI assistant never connects to the database directly.
The MCP server exposes seven tools that cover the full range of day-to-day asset management operations:
The MCP server connects to xAssets through the REST API using API key authentication. All data access is mediated by the same user permissions model that applies to the web interface — the AI assistant can only see and do what the API key's user group allows. No direct database access is possible.
Administrators control exactly which user group and permission level each API key operates under.
The MCP server is a standalone .NET application that runs alongside your AI assistant. Setup takes a few minutes:
appsettings.json with your instance URL, API key, and database nameThe server communicates via the standard MCP JSON-RPC protocol over stdin/stdout, so it works with any MCP-compatible client without additional configuration.
The xAssets MCP Server is open source. Customers can inspect the code, extend it with additional tools, or adapt it to their specific workflows. It requires .NET 9.0 and network access to your xAssets instance.
Use metadata to explore your categories and saved queries, then query_run to
execute a report. The AI assistant can interpret the results and answer follow-up questions about your data.
Use record_read to retrieve an asset, ask the AI to make changes, then record_save
to write the update back. The AI assistant can look up field names using metadata to ensure
the correct XML tags are used.
Use metadata to list available transformations, then save_special to execute one.
This is useful for scheduled imports, data cleansing, and bulk updates.