Schema | beacon

beacon

Describes the environment variables required to run the server.

Name	Required	Description	Default
`BEACON_TIMEOUT`	No	HTTP timeout (seconds) for fetch	15
`BEACON_LOG_LEVEL`	No	Logging verbosity	INFO
`BEACON_USER_AGENT`	No	User-Agent for outbound requests	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
beacon_searchA	Search the web (DuckDuckGo) and return ranked results. Use this to discover URLs for a topic. Then call beacon_fetch on the most relevant URL to read its content. Args: query: Search terms. max_results: Max hits to return (1..20, default 5). Returns: List of {"title", "url", "snippet"} objects.
beacon_fetchA	Fetch a URL and return its main readable text content. Extracts the article/page body (drops navigation, ads, boilerplate). Returns plain text, not HTML. Args: url: An http(s) URL. max_chars: Truncate content to protect context budget (default 8000). Returns: {"url", "title", "content"} or None if the URL cannot be fetched.

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/mason99-stack/beacon-mcp'

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