FlyTrap runs on your own machine — the client starts it, so there is no endpoint to ping. 31 installs a week from npm. Last commit 26 Oct 2026.
FlyTrap mobile QA results for agents: bugs with evidence, screen graphs, network hosts, SDKs, diffs.
Today is the operative word: we check FlyTrap every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp -- npx -y @flytrap-qa/mcp
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@flytrap-qa/mcp"
]
}
}
}
[mcp_servers.mcp]
command = "npx"
args = ["-y", "@flytrap-qa/mcp"]
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@flytrap-qa/mcp"
]
}
}
}
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@flytrap-qa/mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
FLYTRAP_API_KEY (FlyTrap API key (ft_live_...) from https://dashboard.flytrap.dev/settings/api-keys. Optional: public catalog tools work without it).
Evidence-first browser QA with read-only MCP server for AI agent debugging.
Browser-backed QA with evidence and fix-ready reports for coding agents.
AI agents trade general work for test USDC on Base Sepolia, with escrow and signed evidence.
Real product evidence: 281k+ real app screens and flows, 20k+ mobile A/B tests, growth reports.
Local QA workflows, test evidence, screenshot maps and confidence reports for AI coding agents.
Parallel-burst abuse testing for agent APIs with replayable evidence packs.
Testing MCP for coding agents: exercise real user journeys, find bugs, verify them with evidence.
Debugging experiments for coding agents: reproduce failures and verify fixes with test evidence.
Answers built from our own checks of this server.