This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
QAmcp
free MCP server tester, in your browser or terminal
QAmcp tests MCP servers the way AI apps use them. It reads every tool, safely runs the read-only ones and tells you in plain words what is broken: vague tools, missing safety labels, hidden instructions, leaked secrets. Free in your browser or terminal.
Hi Product Hunt! I'm Abhiram, the solo maker of QAmcp.
MCP servers are how AI apps like Claude, Cursor and Codex use outside tools. When I started building with them, I kept hitting the same loop: change a tool, restart the AI app, type prompts by hand, and hope it worked. So I built a tester that connects to a server exactly like an AI app does and checks everything in about a minute.
What it checks: whether it connects on the newest MCP version, whether every tool and input is described, whether tools carry honest safety labels, hidden instructions in descriptions, how tools handle wrong inputs, and whether error messages leak secrets.
By default it only runs tools the server labels read-only and never anything that sounds like it deletes. Every result is checked by code, never by an AI, and shows its evidence.
Then I ran it on every new server in the official MCP Registry. That became a public directory (390 servers so far, updated daily) and a monthly report. The most common bug: half the servers have tool inputs with no description, so the AI has to guess.
Ways to use it, all free: • In the browser, no signup: qamcp.dev (no server handy? one click tests Context7) • In the terminal: npx qamcp-cli • On every pull request (GitHub Action) or every commit • Before you install someone else's server: --before-install
I'd love your honest feedback, especially: what check is missing for your server?
About QAmcp on Product Hunt
“free MCP server tester, in your browser or terminal”
QAmcp was submitted on Product Hunt and earned 3 upvotes and 1 comments, placing #115 on the daily leaderboard. QAmcp tests MCP servers the way AI apps use them. It reads every tool, safely runs the read-only ones and tells you in plain words what is broken: vague tools, missing safety labels, hidden instructions, leaked secrets. Free in your browser or terminal.
On the analytics side, QAmcp competes within Open Source, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how QAmcp performed against the three products that launched closest to it on the same day.
Who hunted QAmcp?
QAmcp was hunted by Abhiram Reddy.K. 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.
For a complete overview of QAmcp including community comment highlights and product details, visit the product overview.
Abhiram Reddy.K
Hi Product Hunt! I'm Abhiram, the solo maker of QAmcp.
MCP servers are how AI apps like Claude, Cursor and Codex use outside tools. When I started building with them, I kept hitting the same loop: change a tool, restart the AI app, type prompts by hand, and hope it worked. So I built a tester that connects to a server exactly like an AI app does and checks everything in about a minute.
What it checks: whether it connects on the newest MCP version, whether every tool and input is described, whether tools carry honest safety labels, hidden instructions in descriptions, how tools handle wrong inputs, and whether error messages leak secrets.
By default it only runs tools the server labels read-only and never anything that sounds like it deletes. Every result is checked by code, never by an AI, and shows its evidence.
Then I ran it on every new server in the official MCP Registry. That became a public directory (390 servers so far, updated daily) and a monthly report. The most common bug: half the servers have tool inputs with no description, so the AI has to guess.
Ways to use it, all free: • In the browser, no signup: qamcp.dev (no server handy? one click tests Context7) • In the terminal: npx qamcp-cli • On every pull request (GitHub Action) or every commit • Before you install someone else's server: --before-install
I'd love your honest feedback, especially: what check is missing for your server?