Skip to main content
Glama
smart-search MCP

smart-search MCP

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
EXA_API_KEYNoExa API key. At least one search engine key is required (TAVILY_API_KEY, EXA_API_KEY, or ZHIHU_ACCESS_SECRET).
TAVILY_API_KEYNoTavily API key. At least one search engine key is required (TAVILY_API_KEY, EXA_API_KEY, or ZHIHU_ACCESS_SECRET).
ZHIHU_ACCESS_SECRETNoZhihu open platform access secret. At least one search engine key is required (TAVILY_API_KEY, EXA_API_KEY, or ZHIHU_ACCESS_SECRET). On non-Windows platforms only the environment variable is supported.
SMART_SEARCH_LLM_MODELNoLLM model name.deepseek-chat
SMART_SEARCH_RERANK_URLNoRerank service URL using the llama.cpp /v1/rerank protocol.http://127.0.0.1:19002/v1/rerank
SMART_SEARCH_LLM_API_KEYNoLLM API key. Leave empty to skip LLM summarization and return a JSON list instead.
SMART_SEARCH_LLM_API_URLNoOpenAI-compatible chat completions endpoint for LLM summarization.https://api.deepseek.com/chat/completions
SMART_SEARCH_LLM_THINKINGNoSet to 1 to enable thinking for reasoning models; not needed for summarization and increases latency.0
SMART_SEARCH_RERANK_MODELNoRerank model name.bge-reranker-v2-m3
SMART_SEARCH_RERANK_REQUIREDNoSet to 1 to error when the rerank service is unavailable instead of degrading.0

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

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