Enable your code gen agents to create & run 0-config end-to-end tests against new code changes in remote browsers via the Debugg AI testing platform.
Enable your code gen agents to create & run 0-config end-to-end tests against new code changes in remote browsers via the Debugg AI testing platform. Exposed over MCP by the debugg ai mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
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.
Everything the assistant can do here goes through one of these:
Removed — Replacementsearch_projects — project {action:"get"} / project {action:"list"}create_project — project {action:"create"}search_environments — environment {action:"get"} / {action:"list"}search_executions — executions {action:"get"\Browser — The Browser tool exposed by this servercheck_app_in_browser — Runs an AI browser agent against your app. The agent navigates, interacts, and reports back with screenshots. Localhost URLs are auto-tunneled viatrigger_crawl — Fires a server-side browser-agent crawl to populate the project's knowledge graph. Localhost URLs tunnel automatically. Returns {executionId, statusprobe_page — All targets in a batch share one session tunnel, but only same-port (or all-public) batches share a single backend execution — 5 URLs on one portproject — Team and repo resolve by either uuid or name (case-insensitive exact match; NotFound if none, AmbiguousMatch if multiple). There is noenvironment — projectUuid auto-resolves from the git repo when omitted. Per-cred failures surface in credentialWarnings[] without blocking the env optest_suite — The test_suite tool exposed by this serverBeing a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
You will need 6 environment variables: DEBUGGAI_API_KEY, DEBUGGAI_API_TOKEN, DEBUGGAI_JWT_TOKEN, DEBUGGAI_API_URL, POSTHOG_API_KEY, DEBUGGAI_MCP_PUBLIC_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Among the browser automation options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Debugg AI's toolset — Removed, search_projects, create_project and 11 more — is a fair guide to whether it matches your workflow.
This entry was verified against Debugg AI's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Removed | Replacement |
| search_projects | project {action:"get"} / project {action:"list"} |
| create_project | project {action:"create"} |
| search_environments | environment {action:"get"} / {action:"list"} |
| search_executions | executions {action:"get"\ |
| Browser | The Browser tool exposed by this server. |
| check_app_in_browser | Runs an AI browser agent against your app. The agent navigates, interacts, and reports back with screenshots. Localhost URLs are auto-tunneled via ngrok. |
| trigger_crawl | Fires a server-side browser-agent crawl to populate the project's knowledge graph. Localhost URLs tunnel automatically. Returns {executionId, status, targetUrl, durationMs, outcome?, crawlSummary?, knowledgeGraph?, brows |
| probe_page | All targets in a batch share one session tunnel, but only same-port (or all-public) batches share a **single** backend execution — 5 URLs on one port in one call is dramatically faster than 5 parallel single-URL calls. A |
| project | Team and repo resolve by **either** uuid **or** name (case-insensitive exact match; NotFound if none, AmbiguousMatch if multiple). There is **no** update/delete — rename or delete a project from the DebuggAI web app. |
| environment | projectUuid auto-resolves from the git repo when omitted. Per-cred failures surface in credentialWarnings[] without blocking the env op. |
| test_suite | The test_suite tool exposed by this server. |
| test_case | The test_case tool exposed by this server. |
| executions | 404 from the backend surfaces as isError: true with {error: 'NotFound', message, uuid}. Credentials are **always** returned without passwords. |
{
"mcpServers": {
"debugg-ai": {
"command": "npx",
"args": ["-y", "@debugg-ai/debugg-ai-mcp"],
"env": {
"DEBUGGAI_API_KEY": "your_api_key_here"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| DEBUGGAI_API_KEY | Credential the server authenticates with. | Yes |
| DEBUGGAI_API_TOKEN | Credential the server authenticates with. | Yes |
| DEBUGGAI_JWT_TOKEN | Credential the server authenticates with. | Yes |
| DEBUGGAI_API_URL | Endpoint or connection string the server talks to. | Yes |
| POSTHOG_API_KEY | Credential the server authenticates with. | Yes |
| DEBUGGAI_MCP_PUBLIC_URL | Endpoint or connection string the server talks to. | Yes |
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.