OpenAgent

Tools & Automation

Give your assistant the ability to act - browse the web, call APIs, or run automations.

Tools & Automation

A standard LLM is limited to text generation. By adding Tools, you give your agent the ability to interact with the world: search the internet, browse live websites, execute code, or call external APIs.

OpenAgent supports two primary ways to extend an agent's capabilities.

Built-in Tools (Fastest)

The fastest way to add capabilities. These tools are pre-packaged with OpenAgent and require zero configuration.

Edit your Store.
Go to the Builtin Tools field.
Add tools like Web Search, Browser, or Shell.
Save and test in Chat.

Example: "Search the latest news about OpenAgent and summarize it."

Security Note: Tools like Shell or Browser can perform actions on your host machine. Only enable them in trusted, sandboxed environments.

MCP (Model Context Protocol)

OpenAgent supports MCP, an open standard for connecting AI models to external data and tools. This is the recommended way to connect your own databases or APIs.

Go to Servers → Add Server and enter your MCP server's URL (and optional Bearer token).
Click Sync to discover available tools, then allow/deny as needed.
Edit the Store and set MCP Server to this server.

Which one should I choose?

MethodBest forSetup Effort
Built-inGeneral web search, simple browsing, or shell tasksLow
MCPConnecting your own proprietary APIs or databasesMedium

Next Steps

Built-in Tools Reference

See the full list of available tools.

Understanding MCP

Deep dive into the Model Context Protocol.

Agent Providers

Technical details for MCP setup.

Add a Knowledge Base

Enable RAG so your assistant answers from your own documents.

Chat

How conversation works in OpenAgent — request lifecycle, Message records, feedback, and suggestions.

On this page

Tools & AutomationBuilt-in Tools (Fastest)MCP (Model Context Protocol)Which one should I choose?Next Steps