tavily-proxy-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TAVILY_MCP_URL | No | Upstream Tavily MCP URL | https://mcp.tavily.com/mcp/ |
| TAVILY_API_KEYS | Yes | Comma-separated Tavily API Keys | |
| TAVILY_PROXY_LOG_LEVEL | No | Log level: error, warn, info, or debug | info |
| TAVILY_PROXY_STATE_PATH | No | Path for state cache file | |
| TAVILY_RESET_GRACE_SECONDS | No | Buffer seconds for estimated reset time at start of month | 900 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| tavily_searchA | Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs. |
| tavily_extractA | Extract content from URLs. Returns raw page content in markdown or text format. |
| tavily_crawlA | Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth. |
| tavily_mapA | Map a website's structure. Returns a list of URLs found starting from the base URL. |
| tavily_researchA | Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources, including web pages, documents, and other resources, to answer a question or complete a task. Returns a detailed response based on the research findings. Rate limit: 20 requests per minute. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Most tools have distinct purposes: search for quick web queries, extract for single-page content, crawl for site-wide extraction, map for site structure, and research for comprehensive synthesis. However, search and research could be confused since both involve gathering web information, though research is explicitly more thorough and multi-source.
All tool names follow the consistent pattern 'tavily_<single_verb>', using lowercase with underscores and no mixed conventions. The verbs (search, extract, crawl, map, research) are clear and predictable, making the naming highly consistent.
With 5 tools, the server is well-scoped for a web research proxy, covering common operations without excess. Each tool serves a meaningful function and the count aligns with the stated purpose.
The tool set provides a comprehensive lifecycle for web data retrieval: search, extract, crawl, map, and research cover both quick lookups and deep investigations. There are no obvious missing operations for the domain of web research.