Glossary
Model Context Protocol (MCP)
MCP is an open standard for connecting AI models and agents to external tools, data sources, and services.
Why it matters
Without MCP, every agent needs custom integrations for every tool. MCP makes tool connections more portable.
How it works
An AI agent connects to MCP servers that expose tools. The agent discovers those tools, calls them when needed, and receives results in a standard format.
How OpenClaw uses this
Because OpenClaw supports MCP servers, you can extend it with any MCP-compatible tool without waiting for a bespoke integration.
Why managed hosting
MCP servers connected and managed for you
- Add MCP-compatible tools from a dashboard. Persistent connections and process lifecycle managed for you.
- Health monitoring reconnects disconnected tools automatically. Protocol updates adopted without manual intervention.
Related terms
AI Agent
An AI agent is software that can interpret a goal, decide what to do, and take actions with tools or external systems.
Agentic AI
Agentic AI describes systems that can take actions on a user's behalf. Instead of only answering questions, they can use tools, handle multi-step work, and adapt as they go.
Large Language Model (LLM)
A large language model (LLM) is a model trained on huge amounts of text so it can understand language, follow instructions, and generate responses.
Learn more
Your OpenClaw, live in minutes.
Go live in minutes from $29/month. No credit card required.
No credit card required. Go live in minutes.