Giving a LangChain Agent Real-World Facility-Management Tools via MCP
Most "give your agent tools" tutorials hand it a calculator or a weather API. Useful for learning the mechanics, but it doesn't tell you what happens when an agent gets access to a real operational system — one with access control, multi-tenancy, and objects that map to actual physical things (buildings, vehicles, machines). This post walks through connecting a LangChain agent to Telesherpa , an…
This article describes how to connect a LangChain agent to Telesherpa, an ontology-based facility, fleet, and field-service management platform, using the Model Context Protocol (MCP). The article highlights the tool surface's size and role-gating, which makes the example useful beyond a marketing demo. The onboarding process is zero human intervention, with public MCP tools for registration, activation, and login.
The integration uses LangChain's langchain-mcp-adapters package, which connects to the server's live tool catalog directly, with no manual schema mapping or wrapper maintenance. Token authentication can be obtained programmatically through MCP tools, and the token's validity and roles can be checked before use. Once authenticated, a LangChain agent can reason over real ontology objects and perform various operations, such as querying and modifying objects or executing defined actions.
This setup allows agents to interact with real operational systems, providing a more practical application than toy data scenarios. The same MCP server works with various agent frameworks, making it a versatile solution for enterprise software.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
