Browser-based MCP server testing with AI chat integration
Browser-based playground for MCP servers. Test any remote MCP server, debug tools, and chat with Claude/ChatGPT using your custom integrations. Fully MCP compatible, with built-in LLM chat.
Tobias here from Metorial. Super excited to share Starbase with you today!
We built Starbase because we were constantly testing MCP servers while working on Metorial (our main product; a dev tool that lets you add 600+ integrations to AI agents in just a couple lines of code, all powered by MCP).
We found ourselves wanting a faster and better way to test remote MCP servers and see how they actually behave in conversations with AI models. Anthropic's Inspector tries do this, but we wanted something that runs entirely in the browser and lets you chat with Claude or ChatGPT using your MCP tools.
So we built Starbase. Of course it's open source because we think the MCP ecosystem needs more accessible tooling.
What makes Starbase different:
Zero setup - just paste your MCP server URL and start testing
Chat with Claude/ChatGPT using your MCP tools to see them in action
Debug faster by testing in real conversations
Fully open source and self-hostable
We use it daily at Metorial while building our Python and TypeScript SDKs, and we hope it helps you build better MCP integrations too!
Would love to hear your feedback and answer any questions! 🚀
About Starbase by Metorial on Product Hunt
“Browser-based MCP server testing with AI chat integration”
Starbase by Metorial launched on Product Hunt on October 27th, 2025 and earned 298 upvotes and 17 comments, placing #4 on the daily leaderboard. Browser-based playground for MCP servers. Test any remote MCP server, debug tools, and chat with Claude/ChatGPT using your custom integrations. Fully MCP compatible, with built-in LLM chat.
On the analytics side, Starbase by Metorial competes within Developer Tools, Artificial Intelligence, GitHub and Tech — topics that collectively have 1.6M followers on Product Hunt. The dashboard above tracks how Starbase by Metorial performed against the three products that launched closest to it on the same day.
Who hunted Starbase by Metorial?
Starbase by Metorial was hunted by Tobias Herber. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Tobias Herber
Hey Product Hunt! 👋
Tobias here from Metorial. Super excited to share Starbase with you today!
We built Starbase because we were constantly testing MCP servers while working on Metorial (our main product; a dev tool that lets you add 600+ integrations to AI agents in just a couple lines of code, all powered by MCP).
We found ourselves wanting a faster and better way to test remote MCP servers and see how they actually behave in conversations with AI models. Anthropic's Inspector tries do this, but we wanted something that runs entirely in the browser and lets you chat with Claude or ChatGPT using your MCP tools.
So we built Starbase. Of course it's open source because we think the MCP ecosystem needs more accessible tooling.
What makes Starbase different:
Zero setup - just paste your MCP server URL and start testing
Chat with Claude/ChatGPT using your MCP tools to see them in action
Debug faster by testing in real conversations
Fully open source and self-hostable
We use it daily at Metorial while building our Python and TypeScript SDKs, and we hope it helps you build better MCP integrations too!
Try it: https://starbase.sh
GitHub: https://github.com/metorial/star...
Metorial: https://metorial.com
Follow us: https://x.com/metorialAi
Would love to hear your feedback and answer any questions! 🚀