LABSCO SUMMARY

The first install is the hard part; after that it is three tools.

Everything here is asynchronous by design — start a test, come back for the verdict — which is the right shape for browser runs that take minutes. The thing that catches people is the Playwright download on first launch: the project itself recommends pre-installing the browsers, because clients tend to give up before the download finishes.

What it is

A Node server that fronts Factifai, a browser-based test runner. Tests start asynchronously, so the agent gets a session back immediately and fetches the result when the run has finished.

What you get

A test started against Factifai from a plain-language description — testWithFactifai
The result of a run fetched by session — getFactifaiSessionResult
The tests started so far, listed — listFactifaiSessions

Requirements

Node.js >= 16.0.0 and a model provider: set MODEL_PROVIDER to bedrock or openai, then OPENAI_API_KEY for OpenAI, or AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY and AWS_DEFAULT_REGION for Bedrock. Launch with npx --yes @presidio-dev/factifai-mcp-server@latest. The first run downloads Playwright's browser binaries, which can exceed an MCP client's startup timeout — run npx playwright install --with-deps beforehand to avoid it.

Setup effort

One command plus a key — npx --yes @presidio-dev/factifai-mcp-server@latest, then supply credentials

See installation options

USE CASES

01

Testing a flow you just changed

Describe the journey in a sentence and let the run start in the background while you carry on working.

testWithFactifai

02

Checking a run that started ten minutes ago

Fetch the result by session id instead of watching a terminal.

getFactifaiSessionResult

03

Finding the session whose id you lost

List what has been started from this workspace and pick the run you meant.

listFactifaiSessions

3 tools

Listed in project docs. Your client may show a different list.

testWithFactifai

getFactifaiSessionResult

listFactifaiSessions

BEFORE YOU INSTALL

What to know first

Tools you get

3 tools named in the project's documentation.

Requires

npx on PATH
Node.js >= 16.0.0
MODEL_PROVIDER in your environment
For MODEL_PROVIDER=openai, OPENAI_API_KEY; for MODEL_PROVIDER=bedrock, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY and AWS_DEFAULT_REGION — in your environment

Where it runs

Both documented clients run the server on your machine.

INSTALLATION

Connect your client

Server setup

TERMINAL

npx --yes @presidio-dev/factifai-mcp-server@latest

MCP Clients

Hai Build

HAI BUILD · JSON

{
  "mcpServers": {
    "factifai": {
      "command": "npx",
      "args": [
        "-y",
        "@presidio-dev/factifai-mcp-server@latest"
      ],
      "env": {
        "MODEL_PROVIDER": "bedrock|openai",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "AWS_ACCESS_KEY_ID": "<YOUR_AWS_ACCESS_KEY_ID>",
        "AWS_SECRET_ACCESS_KEY": "<YOUR_AWS_SECRET_ACCESS_KEY>",
        "AWS_DEFAULT_REGION": "<YOUR_AWS_DEFAULT_REGION>"
      }
    }
  }
}

VS Code

VS CODE · JSON

{
  "servers": {
    "factifai": {
      "command": "npx",
      "args": [
        "-y",
        "@presidio-dev/factifai-mcp-server@latest"
      ],
      "env": {
        "MODEL_PROVIDER": "bedrock|openai",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "AWS_ACCESS_KEY_ID": "<YOUR_AWS_ACCESS_KEY_ID>",
        "AWS_SECRET_ACCESS_KEY": "<YOUR_AWS_SECRET_ACCESS_KEY>",
        "AWS_DEFAULT_REGION": "<YOUR_AWS_DEFAULT_REGION>"
      }
    }
  }
}

Factifai MCP Server