Scout MCP Server
Enables web search, scraping, extraction, and crawling through an MCP interface, allowing coding agents to access real-time web data.
README
Scout CLI
Run Scout from the terminal, and wire the Scout MCP server into your coding agent with one command.
npm install -g @scout-ai/cli
# or run without installing: npx @scout-ai/cli search "..."
Set your key once (get one at platform.usescout.sh/settings):
export SCOUT_API_KEY=sk_your_key
Commands
scout search "best climate tech startups 2026" --limit 5 --country us
scout scrape https://example.com
scout extract https://example.com/pricing --objective "plan names and prices"
scout crawl https://example.com --max-pages 50
scout screenshot https://example.com --full-page
scout company stripe.com
scout answer https://example.com "what does this company sell?"
scout find-all "Series A fintech companies in Europe" --limit 25
Output is JSON on stdout, so it pipes into jq and friends:
scout search "serp api" --limit 3 | jq '.results[].url'
Wire it into your coding agent
One command adds the Scout MCP server (web search, scraping, extraction) to your agent's config:
scout mcp install --client claude-code
scout mcp install --client codex
scout mcp install --client gemini-cli
scout mcp install --client antigravity
scout mcp install --client cursor
scout mcp install --client windsurf
It writes the config file each client expects (e.g. .mcp.json for Claude Code, ~/.codex/config.toml for Codex, ~/.gemini/settings.json for Gemini CLI). Pass --api-key to bake the key in, or set SCOUT_API_KEY first.
To see the raw config block without writing anything:
scout mcp print
Flags
| Flag | Use |
|---|---|
--api-key <key> |
Override SCOUT_API_KEY |
--limit <n> |
Max results (search, find-all) |
--country <cc> |
Two-letter country code (search) |
--depth <d> |
shallow | standard | deep (search) |
--version, --help |
Version / usage |
License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.