Stealthee MCP Tools Server

Provides MCP tooling to run Stealthee signals pipeline locally, including web search, extraction, scoring, and alerting.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "rainbowgore-stealthee-mcp-tools": {
      "command": "python",
      "args": [
        "mcp_server_stdio.py"
      ],
      "env": {
        "NIMBLE_API_KEY": "YOUR_NIMBLE_KEY",
        "OPENAI_API_KEY": "YOUR_OPENAI_KEY",
        "TAVILY_API_KEY": "YOUR_TAVILY_KEY",
        "SLACK_WEBHOOK_URL": "YOUR_SLACK_WEBHOOK"
      }
    }
  }
}

Stealthee MCP is a dev‑first toolkit that surfaces pre‑public product signals by connecting search, extraction, scoring, and alerting into a plug‑and‑play pipeline. Use it to monitor stealth launches, track emerging tech trends, and feed fresh product intel into your AI stack or dashboards.

How to use

You run the MCP servers locally and connect to them from your MCP client or agent workflows. Start by preparing your environment, then launch the three MCP endpoints, and finally run your pipelines from your agents or Smithery workflows. The tools include end‑to‑end capabilities like web search, URL extraction, field parsing, AI scoring, and data storage plus Slack alerts for high‑confidence signals.

How to install

Prerequisites you need to prepare before starting are Python 3.x, a virtual environment tool, and Git. You also require API keys for Tavily, OpenAI, and Nimble, plus an optional Slack webhook for alerts.

git clone https://github.com/rainbowgore/stealthee-MCP-tools
cd stealthee-MCP-tools
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

# Create environment values file or export keys in your shell as needed
# Required
# TAVILY_API_KEY=your_tavily_key_here
# OPENAI_API_KEY=your_openai_key_here
# NIMBLE_API_KEY=your_nimble_key_here

# Optional
# SLACK_WEBHOOK_URL=your_slack_webhook_here

# Start the MCP components (three variants shown below)"} ,{

Additional content

Starting the MCP servers uses stdio configurations so you can run them locally without a remote endpoint. The following commands are shown to start each server directly from your shell. Ensure your environment variables are set before starting.

python mcp_server_stdio.py

smithery dev

python start_fastapi.py

Available tools

web_search

Search the web for stealth launches and emerging signals using Tavily data sources.

url_extract

Extract and clean content from any URL to obtain readable text.

score_signal

Apply AI‑driven scoring to a single signal to estimate stealthiness.

batch_score_signals

Score multiple signals in one batch for rapid triage.

search_tech_sites

Query trusted tech news and sites to focus on credible sources.

parse_fields

Extract structured fields like pricing and changelogs from HTML content.

run_pipeline

Execute the end‑to‑end sequence: search → extract → parse → score → store.

Built by

VeilStrat

AI signals for GTM teams