Build and run persistent AI agents with Claude. No code. No infrastructure. Just describe what you want and agents come to life. And keep living long after the conversation ends.
Step 1: Connect to the MCProspero MCP server.
Add MCProspero to Claude Desktop, claude.ai, or Claude mobile. One-time setup, takes 30 seconds. (Actually any MCP client, like ChatGPT, will work — we just really like Claude)
Step 2: Connect your tools.
Link your Gmail, Slack, Calendar, GitHub — whatever your agents will need. Standard OAuth, same as any app. Revoke access anytime.
Step 3: Tell Claude what you want.
"Check Hacker News every morning and email me a summary of the top AI stories." Claude and MCProspero build the agent, connect the right tools, and set the schedule. MCProspero runs it, and keeps it running.
Step 4: Monitor and modify.
Check on your agents anytime, from any device. Modify it with a follow-up conversation. "Forward my HN summary to my work email too."
Build agents by talking
Create agents from your desktop, web browser, and mobile phone.
You can't tell an LLM "be careful with my data." So MCProspero has your back.
During agent creation, MCProspero surfaces what tools and endpoints the agent wants to use. You approve the list. At runtime, anything not approved is blocked.
You can also opt in for PII security scanning. Data starts leaking? The agent automatically gets suspended (before you do).
Use any MCP client to manage your agents. Any OpenAI-compatible model can serve as your agent's brain — Claude, OpenAI, Llama, Mistral, or whatever comes next.
Open standards on both sides. No lock-in, ever.
In Shakespeare's The Tempest, Prospero is the sorcerer who commands the storm — and the forces working within it — to set things right.
Today's world is a tempest. You need a sorcerer.
MCProspero is your sorcerer.
Easy enough for your boss — safe enough for your kids (and your CISO).