Atlas / MCP servers / debugg-ai / Debugg AI

Debugg AIBLOCK

Name: Debugg AI
Author: debugg-ai

mcp/debugg-ai/debugg-ai

MCP server by debugg-ai · automation · browser · end to end testing · Audited 2026-10-07

⚑ Report / re-scan Source ↗

Zero-Config, Fully AI-Managed End-to-End Testing for all code gen platforms.

Verdict

BLOCK

Grade

Trust score

69 /100

Exposed tools

10 10r · 0w · 0d

Transport

stdio · streamable-http

License

Apache-2.0

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

AI-powered browser testing via the Model Context Protocol. Point it at any URL (or localhost) and describe what to test — an AI agent browses your app and returns pass/fail with screenshots.

Setup

Requires Node.js 20.20.0 or later (transitive requirement from posthog-node@^5.26.0).

Testing `http://localhost:...` URLs requires the `caddy` binary — check_app_in_browser, probe_page, and trigger_crawl tunnel localhost targets through a local Caddy reverse proxy. This installs automatically: the @radically-straightforward/caddy npm dependency downloads a pinned Caddy release for your platform during npm install/npx — nothing to install yourself in the normal case. It is now the only binary this package downloads; the tunnel client itself is pure TypeScript — it replaced the ngrok package, which fetched the ngrok agent. If that download never ran (npm install --ignore-scripts, an offline/air-gapped install), point CADDY_BIN at your own install (brew install caddy / apt install caddy / see caddyserver.com/docs/install) — missing it surfaces as a clear error on the first localhost-URL call, not a silent hang. Public-URL calls, every non-browser tool, and test_suite {action:"run"} (which uses its own dedicated tunnel and bypasses Caddy entirely) don't need it either way.

Get an API key at debugg.ai, then add to your MCP client config:

{
"mcpServers": {
"debugg-ai": {
"command": "npx",
"args": ["-y", "@debugg-ai/debugg-ai-mcp"],
"env": {
"DEBUGGAI_API_KEY": "your_api_key_here"
}
}
}
}

Or with Docker:

docker run -i --rm --init -e DEBUGGAI_API_KEY=your_

Read from source at commit 5eb6e615cb10OBSERVED · 2026-10-07

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add debugg-ai-mcp --env DEBUGGAI_API_KEY=${DEBUGGAI_API_KEY} --env DEBUGGAI_API_TOKEN=${DEBUGGAI_API_TOKEN} --env DEBUGGAI_JWT_TOKEN=${DEBUGGAI_JWT_TOKEN} --env DEBUGGAI_LIVE_TUNNEL_API_KEY=${DEBUGGAI_LIVE_TUNNEL_API_KEY} -- npx -y @debugg-ai/[email protected]

claude-desktop

{
  "mcpServers": {
    "debugg-ai-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@debugg-ai/[email protected]"
      ],
      "env": {
        "DEBUGGAI_API_KEY": "${DEBUGGAI_API_KEY}",
        "DEBUGGAI_API_TOKEN": "${DEBUGGAI_API_TOKEN}",
        "DEBUGGAI_JWT_TOKEN": "${DEBUGGAI_JWT_TOKEN}",
        "DEBUGGAI_LIVE_TUNNEL_API_KEY": "${DEBUGGAI_LIVE_TUNNEL_API_KEY}"
      }
    }
  }
}

Exposed tools (10)

10 read · 0 write · 0 destructive.

Tool	Risk	Description
`S`	read	d
`Updated`	read	Updated desc
`environment`	read	A single environment by UUID, with credentials inline (passwords redacted).
`environments`	read	Environments for the auto-detected project (credentials redacted).
`execution`	read	A single execution by UUID, with full node detail + artifact links.
`executions`	read	Recent workflow executions (first page).
`n`	read	d
`new-name`	read	updated
`project`	read	A single project by UUID, with full detail.
`projects`	read	All projects visible to this API key (first page).

Trust audit

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	FAIL
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	PASS
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: none-observed
Network: declared (2 observation(s))
Shell: declared (2 observation(s))
Dependencies: not all pinned
Secrets in source: found

Findings (25)

HIGHNetwork egress · net.tls_off · CWE-200, CWE-319

services/tunnel/debuggTransport.ts:429

? tls.connect({ host, port, servername: host, rejectUnauthorized: false })

Why it matters. certificate verification is disabled

Fix. leave verification on

MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319

.beads/issues.jsonl:162

{"_type":"issue","id":"debugg_ai_mcp-k6yq","title":"probeTunnelHealth returns a FALSE NETWORK_ERROR ~1 in 5 runs (DNS race ~286ms after tunnel creation) — spurious TunnelTrafficBlocked on a healthy se

MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321

__tests__/handlers/triggerCrawlHandler.test.ts:271

password: 'super-secret-password-9876',