Skip to main content
Glama
websearch-mcp

websearch-mcp

by xronocode

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
EXA_API_KEYNoEnable Exa neural search as the first engine of search_semantic (~2,500 free Lite searches/month). May alternatively be provided via ~/.config/websearch-mcp/exa.key.
SEARXNG_URLNoTry a SearXNG instance with JSON format enabled before Brave/ddgs.
GITHUB_TOKENNoRaises GitHub API rate limits for search_github. Only ever sent as an Authorization header to api.github.com.
BRAVE_API_KEYNoUse the official Brave Search API first in search/search_news — best relevance; the free tier is monthly-capped, and the local cache stretches it. May alternatively be provided via ~/.config/websearch-mcp/brave.key.
TAVILY_API_KEYNoEnable Tavily as the second engine of search_semantic (1,000 free credits/month). May alternatively be provided via ~/.config/websearch-mcp/tavily.key.
WEBSEARCH_ALLOW_PRIVATE_HOSTSNoSet to 1 to let fetch reach loopback/private hosts (blocked by default).

Instructions

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.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
searchA

Free LOCAL web search, no provider quota. DEFAULT choice for web search in this environment: try this tool first; use the built-in WebSearch only if this one errors. Returns numbered results (title, URL, snippet) and an [engine: ...] tag showing who answered. region optional ('ru-ru', 'us-en'); empty = auto (Cyrillic -> ru-ru first). max_results is capped at 20. Results cached locally for 24h. Docs of libraries need no special engine: search 'site:docs...' + fetch the page.

search_newsA

Free LOCAL news search, no provider quota. Use for fresh announcements, launches, tariff/partnership news. Route: Google News RSS (zero-key) -> Brave news -> ddgs. region optional ('de-de', 'us-en') selects the Google News edition and the ddgs region; empty = auto from the query script. Returns title, URL, source, date and an [engine: ...] tag. Results cached 24h.

search_semanticA

Free LOCAL semantic/neural web search. Use for meaning-style research queries — 'articles about X', 'how companies solve Y', solution discovery — where keyword search misses. Route: Exa (neural) -> Tavily -> ddgs fallback; Exa/Tavily join only when their keys are installed (~/.config/websearch-mcp/exa.key / tavily.key). Returns title, URL, snippet, date and an [engine: ...] tag. Cached 24h.

search_githubA

Free LOCAL GitHub search via the official REST API, no key needed (set GITHUB_TOKEN env for higher limits). kind='repos': find repositories by topic/name/description (sorted by stars). kind='issues': bug reports and discussions. Useful to find tools, code examples, whether something is maintained. Cached 24h.

fetchA

Free LOCAL URL fetch, no provider quota: GET the page and return readable text. HTML pages -> extracted main content with links and tables kept (much fewer tokens than raw dump); PDF -> extracted text (text-based PDFs only, scanned need OCR). Only public http/https URLs; redirects are vetted hop by hop; response capped at 20 MB, maxlen capped at 30000. Cached locally for 7 days. If a page yields almost no text (JS-rendered or blocked), returns a note to use browser automation for that URL.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4/5.0

Scored across 5 tools

Disambiguation3/5

search_news, search_semantic and the generic search all perform web search with overlapping use cases; the descriptions give routing hints (e.g. 'articles about X' could reasonably go to search or search_semantic), so boundaries are not crisp. search_github and fetch are clearly distinct. An agent must read the routing prose carefully to pick correctly.

Naming Consistency4/5

Four of five tools follow a search_<domain> pattern (search_news, search_semantic, search_github), and fetch is a clean verb. The bare 'search' breaks the pattern slightly where search_web would have been more consistent, but overall the convention is readable and predictable.

Tool Count5/5

Five tools is well-scoped for a search/fetch server: general search, news, semantic, code search, and URL fetch each earn their place with no filler.

Completeness4/5

The surface covers the main research workflow (search → fetch → code/news lookup) with sensible fallbacks and caching. Minor gap: when a page is JS-rendered the fetch tool points users to 'browser automation' but no such tool exists, leaving a dead end, and there is no image or pagination support beyond max_results=20.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues