A developer-focused guide on creating a new capability for the Goose AI agent. Learn to write a simple Python script, wrap it into a reusable Model Context Protocol (MCP) for sending emails, and integrate it into a larger workflow.
with Claire Vo
Open-source AI agent by Block for automating tasks
Before building the full tool, ask Goose to write a basic script to perform the core task. This validates the logic in a simple environment.
I have a scaffolded Python package here using uv... I have a .env file... can you make a python script in this directory that sends a test email?Provide Goose with the necessary context by pasting the example code from the MCP Python SDK's README file directly into the chat. Then, ask it to merge your script from Step 1 with the example to create a functional MCP server file.
Here's reference code... can you use that example to make an MCP with a send email tool?If the generated code has an error, don't debug it manually. Instead, copy and paste the full error message back into Goose and ask it to fix the problem. The agent can often identify and correct its own mistakes.
Once the MCP is working, add it as a new custom extension in the Goose settings. This makes the send_email function available as a tool that the agent can use in any conversation.
Return to a previous conversation where you completed a task (like creating a payment link). Enable your new email extension for that session and give a final command to use the new capability.
I just enabled email tool. Can you send that payment link to my demo email address?
Follow Sahil Lavingia's method for delegating small but impactful maintenance tasks, like fixing an internal Slack report, to the AI agent Devin. This workflow shows how to use simple, clear prompts to fix code and update system prompts without distracting your engineering team.
Learn Gumroad CEO Sahil Lavingia's process for rapidly prototyping a UI with v0, then using the AI agent Devin to autonomously code, implement, and submit the feature for review, turning a multi-day task into a one-hour workflow.
Improve your writing in real-time by using ChatGPT as a first reader. Get instant feedback on structure, clarity, and flow as you write, allowing you to polish your work section by section.
We've made ChatPRD affordable so everyone from engineers to founders to Chief Product Officers can benefit from an AI PM.