Schema | web-search-mcp

web-search-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`HOST`	No	Host to bind (default 127.0.0.1)	127.0.0.1
`PORT`	No	Port to listen (default 8080)	8080
`DEBUG`	No	Debug mode (0 or 1)
`CORS_ORIGIN`	No	CORS origin
`EXA_API_KEY`	No	API key for Exa search
`SQLITE_PATH`	No	Path to SQLite database file
`BRAVE_API_KEY`	No	API key for Brave search
`MCP_BASE_PATH`	No	Base path for MCP endpoint (e.g., /mcp)
`STATE_BACKEND`	No	State backend: memory, sqlite, redis
`MCP_AUTH_TOKEN`	No	Bearer token for MCP endpoint authentication
`SERPER_API_KEY`	No	API key for Serper search
`TAVILY_API_KEY`	No	API key for Tavily search
`SEARCH_PROVIDER`	No	Search provider: tavily, brave, exa, serper, duckduckgo, searxng
`DOMAIN_ALLOWLIST`	No	Comma-separated domain allowlist
`DOMAIN_BLOCKLIST`	No	Comma-separated domain blocklist
`HTTP_RATE_LIMIT_RPS`	No	Rate limit per second
`FETCH_MAX_BODY_BYTES`	No	Maximum fetch body size in bytes
`SEARCH_PROVIDER_FALLBACK`	No	Comma-separated fallback providers

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

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/charley-forey/web-search-mcp'

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