AI agents
Set up Jot with your AI agent.
Your coding agent reads each report over MCP, with the screenshot, the selector and the replay summary, fixes the code and replies on the reviewer’s pin. Agents reply and resolve; who approves is your workspace's choice (by default, the person who reported it).
MCP agents are on every plan, Free included.
Set up in 30 seconds
/plugin marketplace add usejot/claude-plugins /plugin install jot@usejot
Then ask Claude to connect Jot (it opens your browser), or paste an agent token when Claude Code asks.
npx @usejot/cli login npx @usejot/cli init
login opens your browser to pick a workspace. init connects the repo. No token to paste.
Pick your agent
Jot for Claude Code
Connect Claude Code to Jot with the plugin: /jot lists the open feedback, reads the screenshot, selector and replay, fixes the code and replies on the pin.
Jot for Cursor
Connect Cursor to Jot over MCP: the agent reads each report's screenshot, selector and replay summary, fixes the code and replies on the reviewer's pin.
Jot for Codex
Connect OpenAI Codex to Jot over MCP: it reads each report's screenshot, selector and replay summary, fixes the code and replies on the reviewer's pin.
Jot for Windsurf
Connect Windsurf to Jot over MCP: the agent reads each report's screenshot, selector and replay summary, fixes the code and replies on the reviewer's pin.
Want it to run on its own? The Jot Loop fixes Jots as they arrive.
Hand your agent the queue.
Start free. Agents and reviewers are on every plan.