Schema | Web Search MCP Server

Web Search MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`CACHE_TTL`	No	Cache time-to-live (seconds, 0 = disabled). Default: 300.	300
`LOG_LEVEL`	No	Logging verbosity. Default: INFO.	INFO
`LOG_FORMAT`	No	Log format: json or text. Default: json.	json
`MAX_RESULTS`	No	Default result count. Default: 10.	10
`BING_API_KEY`	No	API key for Bing (Azure Cognitive Services).
`BRAVE_API_KEY`	No	API key for Brave Search (2000/month free).
`GOOGLE_CSE_ID`	No	Custom Search Engine ID for Google CSE.
`CACHE_MAX_SIZE`	No	Max cache entries. Default: 256.	256
`RETRY_ATTEMPTS`	No	Max HTTP retry attempts. Default: 3.	3
`TAVILY_API_KEY`	No	API key for Tavily (recommended, 1000/month free).
`REQUEST_TIMEOUT`	No	HTTP timeout (seconds). Default: 30.	30
`SEARCH_PROVIDER`	No	Active search backend. Default: tavily.	tavily
`SERPAPI_API_KEY`	No	API key for SerpAPI (100/month free).
`CONCURRENCY_LIMIT`	No	Parallel page extractions. Default: 5.	5
`GOOGLE_CSE_API_KEY`	No	API key for Google Custom Search Engine.
`PLAYWRIGHT_TIMEOUT`	No	Browser nav timeout (ms). Default: 30000.	30000
`PLAYWRIGHT_HEADLESS`	No	Headless browser mode. Default: true.	true

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityInactive

ResponsivenessNo issues