Skip to main content
Glama

@vibeleading/mcp-real-time-scout

The Real-Time Scout — the Web & API Connector. Conditions change constantly; this server keeps the Pilot updated on market shifts and competitor moves, piping intelligence into the HUD for course corrections before competitors see the turn coming.

Implements the "Real-Time Scout" server from Vibe Leading The AI — one of the "3 Must-Have MCP Servers".

What it does

  • Fetches live web pages from anywhere over HTTP(S).

  • Runs web searches (Brave Search API or Tavily) to scan the competitive landscape.

  • Parses RSS/Atom feeds with zero dependencies and friendly in-memory caching.

  • Tracks competitor mentions across curated or custom feeds.

Related MCP server: The Web MCP

Install

npm install -g @vibeleading/mcp-real-time-scout

Or run on demand with npx:

npx -y @vibeleading/mcp-real-time-scout
# or run straight from the GitHub source (builds automatically):
npx -y github:VibeLeading/mcp-real-time-scout

Requirements

  • Node.js >= 22 — required. The server uses the global fetch API and AbortSignal.timeout; on older Node versions the process fails to start, which MCP clients report generically as "connection closed".

  • Optional — web search keys. The search_web tool needs MCP_SEARCH_PROVIDER (brave | tavily) and MCP_SEARCH_API_KEY set. Without them it returns a clear error; all other tools work unconfigured.

  • No other runtime dependencies.

Quick Start (Agent Setup)

Give your agent the full VibeLeading methodology in one paste:

Give me the Vibe Leading methodology: install the 5 agent skills so I can lead AI agents by intent + real-time telemetry, and add the 4 MCP servers so I get hands in the corporate engine.

SKILLS (npx skills add): npx skills add VibeLeading/mission-script VibeLeading/ira-prompting VibeLeading/hud-setup VibeLeading/pit-stop-audit VibeLeading/org-geometry

MCP SERVERS (@vibeleading scope, add to YOUR agent's MCP config): @vibeleading/mcp-hybrid-data-engine @vibeleading/mcp-document-architect @vibeleading/mcp-real-time-scout @vibeleading/mcp-privacy-shield

ENV VARS: MCP_STONE_PATH=data/stone.db MCP_LIGHT_PATH=data/light.json MCP_FLOW_PATH=data/flow.json MCP_DOCS_ROOT=~/.vlb-docs MCP_SHIELD_NAMES=1

NOTE: MCP installation method varies by agent. Examples:

  • OpenCode: opencode mcp add real-time-scout -- npx -y @vibeleading/mcp-real-time-scout

  • Claude Code / Cursor: add to .mcp.json / claude_desktop_config.json with command=npx, args=[-y, @vibeleading/mcp-real-time-scout]

  • Codex: configure via its MCP settings UI Use the method appropriate for your agent.

Paste the block above into your AI agent (OpenCode, Claude Code, Cursor, Codex, etc.). It will install the skills, write the MCP config, and you're ready to lead.

Client configuration

Add to your MCP client config (e.g. Claude Desktop, Cursor, or opencode):

{
  "mcpServers": {
    "real-time-scout": {
      "command": "npx",
      "args": ["-y", "@vibeleading/mcp-real-time-scout"]
    }
  }
}

Tools

Tool

Arguments

Description

fetch_url

url: string

Fetch a web page; returns HTTP status, title, and text content (capped at ~100k chars, 15s timeout).

search_web

query: string, num_results?: number

Web search; returns normalized {title, url, snippet} results.

monitor_feed

feed_url: string, limit?: number

Parse an RSS/Atom feed and return latest items (cached in-memory 5 min).

track_competitor

company: string, feeds?: string[], recent_days?: number

Aggregate feed items mentioning a company, newest first.

Environment variables

Variable

Required

Description

MCP_SEARCH_PROVIDER

For search_web

brave or tavily.

MCP_SEARCH_API_KEY

For search_web

API key for the configured provider.

The server never calls a search engine without a key. If these variables are unset, search_web returns an instructive configuration error.

Production notes

  • fetch_url rejects non-http(s) URLs and enforces a 15-second timeout so it cannot hang.

  • search_web: get a Brave Search API key (free tier) or a Tavily key and set the two env vars before starting the server.

  • monitor_feed caches parsed items in an in-memory LRU (max ~200 feeds) with a 5-minute TTL to avoid hammering publishers.

  • track_competitor defaults to a curated set of well-known tech-news feeds; pass your own feeds to watch specific sources, and recent_days to bound the time window.

  • Runs over stdio via StdioServerTransport, so it drops cleanly into any MCP-compatible client.

Publishing

Published to the npm registry via OIDC trusted publishing — no npm tokens stored anywhere. Pushing a version tag triggers the .github/workflows/publish.yml workflow:

npm version patch -m "release: v%s"
git push origin main --follow-tags
  • One-time bootstrap. The very first published version cannot use trusted publishing (the trust relationship attaches to an existing package). Publish 0.1.1 once manually (npm publish after npm login, or a short-lived publish-scoped token), then configure Trusted Publisher on npmjs.com → the package → Settings → Trusted publishing → GitHub Actions → owner VibeLeading, repo mcp-real-time-scout, workflow publish.yml, action allow npm publish (requires 2FA once per package).

  • Requires Node.js >= 22 and npm >= 11.5.1 on the runner (handled by the workflow).

License & Attribution

MIT — Copyright (c) 2026 Jean Machuca (see LICENSE).

This server implements concepts from the book Vibe Leading The AI: The Corporate Race Against Machines by Jean Machuca (ISBN 9798252505008, © 2026 Jean Machuca). The book is copyrighted commercial material; this repository does not republish its text. Buy the book at https://vibeleading.org or https://a.co/d/04L5YatK. Author website: jeanmachuca.com · Support on GitHub Sponsors: github.com/sponsors/jeanmachuca. See NOTICE.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

No tool schema history has been recorded yet.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables comprehensive web research through multi-engine search, intelligent website crawling, content analysis, trends data exploration, and automated research workflows with anti-detection measures and rich snippet detection.
    127
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Enables AI assistants to access real-time web data through search, markdown scraping, and browser automation while bypassing anti-bot protections. It provides tools for web research, e-commerce monitoring, and data extraction from across the globe.
    4
    7,869
    5
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI assistants to perform real-time business intelligence tasks including competitive analysis, website scoring, review analysis, and market research.
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/VibeLeading/mcp-real-time-scout'

If you have feedback or need assistance with the MCP directory API, please join our Discord server