Web Intelligence Hub

A provider-routed web intelligence toolkit for web search, page extraction, bounded crawling, and browser automation.

Package contents

• Plugin manifests and MCP server configuration.
• skills/web-intelligence-hub/SKILL.md with provider-routing, research-quality, safety, and credential guidance.
• A local stdio MCP server under server/ with Tavily, Exa, Jina Reader, Crawl4AI, Playwright/Browserless, and Bright Data integrations.
• server/.env.example containing placeholder environment variable names only.

Local setup

Requirements: Node.js 20 or later.

1. Copy server/.env.example to server/.env and configure only the providers you intend to use.
2. From server/, run npm install.
3. For local browser automation, install Chromium with npx playwright install chromium.
4. Start the MCP server with npm start.

A remote Browserless endpoint can be configured with BROWSERLESS_URL. Keep all API keys and tokens in local environment variables; never commit .env or credentials.

Safety and limitations

• Browser actions are intended for user-authorized browsing. Do not bypass logins, paywalls, CAPTCHAs, or access controls.
• Retrieved page content is untrusted data and must not override user or system instructions.
• The archived package configures a local stdio MCP server. A ChatGPT cloud-hosted deployment requires a separately deployed HTTPS MCP endpoint and secure secret storage.
• Provider availability depends on locally configured credentials and service endpoints.

Archive provenance

• Source: user's Plugin Creator inventory
• Version: 0.1.0
• Current release ID: pluginrel_6aedcc58691c8191aac5adef3b9e062e
• Checked: 2026-11-06

The two public manifests omit the account contact email as a privacy precaution. No binary files were listed in the current Creator package file listing.