Schema | Scout MCP Server

Scout MCP Server

Official

Describes the environment variables required to run the server.

Name	Required	Description
`PORT`	No	Listen port for HTTP transport. Default: 3000
`SCOUT_API_KEY`	Yes	Your Scout API key (required).
`SCOUT_BASE_URL`	No	Override the API origin. Default: https://core.usescout.sh
`SCOUT_MCP_PATH`	No	Endpoint path for HTTP transport. Default: /mcp
`SCOUT_MCP_TOKEN`	No	If set, clients must send Authorization: Bearer <token>.

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": false }

Functions exposed to the LLM to take actions

Name	Description
scout_searchA	Search the live web and return ranked results as JSON. Set depth="deep" for an agentic multi-step search; it reports progress as it runs.
scout_scrapeC	Fetch a web page and return clean, LLM-ready Markdown. Handles JS rendering and bot defenses.
scout_extractB	Extract structured data from one or more URLs. Provide an objective describing what to pull.
scout_crawlC	Crawl a website from a start URL and return its pages. Bound it with max_pages.
scout_screenshotB	Capture a screenshot of a web page. Returns a URL (or data URI) to the image.
scout_companyA	Look up a company profile from its domain: name, description, industry, socials, logo, and more.
scout_answerA	Answer a natural-language question by reading a page and the pages it links to.
scout_find_allA	Build a list of entities matching a natural-language query (e.g. "Series A fintech companies in Europe").

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Scout-AI-Labs/scout-mcp'

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