Skip to main content
Glama
Sign In
beacon

beacon

by mason99-stack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

beacon

A zero-config web search MCP server for any MCP client (opencode, Claude Desktop, Cursor, etc.).

Gives your local models the ability to search the web and read page content — no API keys, no Docker, no setup beyond pip install.

What it gives you

Two MCP tools:

Tool

Description

beacon_search(query, max_results=5)

Web search via DuckDuckGo. Returns {title, url, snippet} hits.

beacon_fetch(url, max_chars=8000)

Fetches a URL and returns its main readable text (HTML-stripped, boilerplate removed).

Related MCP server: mcp-ddg-research

Install

git clone <your-fork-url> beacon
cd beacon
python3 -m venv .venv
.venv/bin/pip install -e .

Register with an MCP client

opencode

Add to your opencode.json:

{
  "mcp": {
    "beacon": {
      "type": "local",
      "command": ["/absolute/path/to/beacon/.venv/bin/beacon-mcp"]
    }
  }
}

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "beacon": {
      "command": "/absolute/path/to/beacon/.venv/bin/beacon-mcp"
    }
  }
}

Manual testing (CLI)

.venv/bin/beacon search "python async patterns"
.venv/bin/beacon fetch https://example.org

Configuration (optional, via env vars)

Variable

Default

Purpose

BEACON_TIMEOUT

15

HTTP timeout (seconds) for fetch

BEACON_USER_AGENT

Firefox-like string

User-Agent for outbound requests

BEACON_LOG_LEVEL

INFO

Logging verbosity

No state is written to disk. No database. No API keys required.

Development

.venv/bin/pip install -e ".[dev]"
.venv/bin/python -m pytest -v

License

MIT.

Available Tools

2 tools
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.

Inputs: url (required), max_chars. Returns: result

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.

Inputs: query (required), max_results.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.7/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: one searches the web for URLs and the other fetches a specific URL's content. There is no overlap or confusion between them.

    Naming Consistency5/5

    Both tools use a consistent 'beacon_' prefix followed by a simple verb ('search' and 'fetch'), forming a predictable and coherent naming pattern.

    Tool Count3/5

    With only two tools, the server feels minimally scoped for a web search/fetch utility. While each tool is essential, the count is borderline and may leave users wanting additional capabilities like URL validation or cached results.

    Completeness5/5

    The server provides a complete workflow: search for URLs, then fetch and read content. It covers the core domain of web searching and extraction without obvious gaps or dead ends.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    • DuckDuckGo Search MCP

      OEvortex
      A
      license
      A
      quality
      C
      maintenance
      A privacy-friendly MCP server that enables web searches and URL content extraction using DuckDuckGo, allowing AI assistants to access real-time web information without API keys.
      1
      709 npm
      45
      Apache 2.0

    • local-websearch-mcp

      dr34dl10n
      A
      license
      Not graded
      quality
      D
      maintenance
      Small Python MCP server that provides web search and page fetching tools via DuckDuckGo, requiring no API key.
      Apache 2.0

    • EZ Web Search MCP Server

      Gnarus-G
      A
      license
      A
      quality
      D
      maintenance
      A simple MCP server that provides web search functionality via DuckDuckGo, returning titles, URLs, and descriptions for results. Configurable result limit.
      1
      ISC