Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TAVILY_DAYSNoTime window for news results, in days.1
TAVILY_TOPICNoSearch topic: 'news' or 'general'.news
TAVILY_API_KEYYesYour Tavily API key used for authentication to the upstream Tavily MCP server.
TAVILY_ENABLEDNoWhen set to 'false', the search tool returns an error immediately and does not make any HTTP requests.true
TAVILY_MCP_URLNoThe URL of the Tavily MCP HTTP server.https://tavily.sharyuke.com/api/mcp
TAVILY_MAX_RESULTSNoDefault maximum number of search results to return.10
TAVILY_MCP_TIMEOUTNoTimeout in seconds for HTTP requests to the Tavily MCP server.60
TAVILY_SEARCH_DEPTHNoSearch depth: 'basic' or 'advanced'.advanced
TAVILY_MCP_DEBUG_LOGNoFile path for debug logging./tmp/tavily_mcp_debug.log
TAVILY_INCLUDE_ANSWERNoWhether to include an AI-generated summary answer in the response.true
TAVILY_MCP_AUTH_HEADERNoThe name of the HTTP header used for authentication.Authorization

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SqrtLeaves/tavily_mcp'

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