GhostQA

Name: GhostQA
Author: synctek-llc

by synctek-llccommunityv0.2.2

SpecterQA automates end-to-end testing by using AI personas to interact with applications as real users would, eliminating the need for brittle test scripts and selectors.

From the registry: AI personas navigate your web app in real browsers, find bugs and UX issues. No scripts needed.

GitHub Repository

Install & configure

Prerequisites

required
Python 3.10+
Python 3.10 or newer
required
Install specterqa with MCP extra
Install via pip to get the specterqa-mcp entry point
```
$ pip install 'specterqa[mcp]' && specterqa install
```
https://pypi.org/project/specterqa/
required
Anthropic API key
Required for vision model decisions
https://console.anthropic.com

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `ghostqa` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Python 3.10+** — Python 3.10 or newer
- **Install specterqa with MCP extra** — Install via pip to get the specterqa-mcp entry point Run: `pip install 'specterqa[mcp]' && specterqa install` (https://pypi.org/project/specterqa/)
- **Anthropic API key** — Required for vision model decisions (https://console.anthropic.com)

Canonical MCP server config (stdio transport):
- command: `specterqa-mcp`
- args: []
- required environment variables:
  - `ANTHROPIC_API_KEY`: Anthropic API key used for Claude vision model calls (example: `<your-anthropic-api-key>`)
- optional environment variables:
  - `SPECTERQA_BUDGET`: Default per-run budget in USD (example: `5.00`)
  - `SPECTERQA_ALLOWED_DIRS`: Colon-separated allowlist of directories usable as the `directory` parameter (example: `/home/user/projects:/ci/workspaces`)

Note: Upstream project is now named SpecterQA (formerly GhostQA). Provides an MCP server via the specterqa-mcp entry point after `pip install specterqa[mcp]`.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Upstream project is now named SpecterQA (formerly GhostQA). Provides an MCP server via the specterqa-mcp entry point after `pip install specterqa[mcp]`.