📄️ Introduction to tools
Understand tools at Portia and add your own.
📄️ Integrating tools
Learn how to integrate tools that your agent can use to answer a user query.
📄️ Remote MCP and cloud tools
When your agents are connected to Portia Cloud, they gain access to an extensive tool registry with powerful integrations. The registry includes by default popular services like Gmail, Google Calendar, Slack, GitHub, Zendesk, and is extensible to many more by integrating remote MCP servers. You can check out and configure the integrations you want access to in the dashboard (↗). This will update update the tools available to your DefaultToolRegistry (see here if you need a recap on how tool registries work).
📄️ Integrating an MCP server with the SDK
The Model Context Protocol (MCP) makes it very easy to integrate third-party tools into your Portia AI project.
📄️ Add custom tools
Let's build two custom tools that allow an LLM to write / read content to / from a local file. We're going to create our custom tools in a separate folder called mycustomtools at the root of the project directory and create a filewritertool.py and filereadertool.py file within it, with the following:
📄️ Use clarifications in custom tools
You can raise a Clarification in any custom tool definition to prompt a plan run to interrupt itself and solicit input (SDK reference ↗).
📄️ Using browser tools
Browser tools (SDK ↗) can deploy an agent to browse the internet and retrieve data or enact actions on your behalf. Portia will use Browser tools when it recognises there is a web-based task to be performed. We use the Browser Use (↗) library to offer a multi-modal web agent that will visually and textually analyse a website in order to navigate it and carry out a task.