Schema | Web Search MCP

Web Search MCP

Describes the environment variables required to run the server.

Name	Required	Description	Default
`EXA_API_KEY`	No	Enables Exa provider
`SEARXNG_URL`	No	SearXNG base URL	http://localhost:18443
`TAVILY_API_KEY`	No	Enables Tavily provider
`WSM_TIMEOUT_MS`	No	Global search timeout in milliseconds	25000
`WSM_MAX_RESULTS`	No	Default max results	10
`WSM_LLM_PROVIDER`	No	LLM provider for quality mode: 'haiku', 'local', or 'none'	none
`ANTHROPIC_API_KEY`	No	Required when WSM_LLM_PROVIDER=haiku
`FIRECRAWL_API_KEY`	No	Enables Firecrawl in extract pipeline
`WSM_LOCAL_LLM_URL`	No	Required when WSM_LLM_PROVIDER=local

Features and capabilities supported by this server

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
searchA	Multi-source web search with RRF fusion. Providers tried in parallel: SearXNG/ddgr/Tavily/Exa/opencli-zh. Results deduplicated by URL and reranked by reciprocal rank fusion. Snippets cleaned.
vertical_searchA	Vertical-domain structured search via AnySearch. Use for finance (real-time quotes, fundamentals), academic (papers), security (CVE), ip (patents), legal, health. Returns structured payload (field-level data, not flattened).
vertical_sub_domainsA	Discover sub-domains and required parameters for a given vertical domain. Call before vertical_search when sub_domain schema is unknown.
vertical_batchC	Up to 5 vertical queries in parallel via AnySearch.
extractA	Extract clean markdown from a URL. Tries defuddle → opencli adapter → Firecrawl → opencli browser in order.
doctorC	Diagnose provider availability and health.

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/thehappyboy/web-search-mcp'

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