tavily-fastmcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TAVILY_API_KEY | Yes | Your Tavily API key |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| tavily.healthA | Return package and server health metadata. |
| tavily.catalogA | Return the structured server catalog that describes tools, resources, and prompts. |
| tavily.searchB | Search the web when relevant URLs are not yet known. |
| tavily.extractA | Extract content from specific known URLs. |
| tavily.mapA | Discover site structure and candidate URLs on a single domain. |
| tavily.crawlA | Traverse a site and retrieve multi-page content. |
| tavily.researchB | Create a deep multi-source Tavily research task. |
| tavily.get_researchA | Retrieve the status or result of an existing Tavily research task. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| tavily-router | General routing prompt that chooses the smallest correct Tavily workflow. |
| tavily-profile | Render a packaged profile and bind it to a concrete user request. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| ServerCatalog | Structured catalog of tools, prompts, profiles, and example resources. |
| ProfileCatalog | List of packaged workflow profiles exposed by the server. |
| ClaudeDesktopConfig | Example stdio configuration snippet for Claude Desktop. |
| CursorConfig | Example stdio configuration snippet for Cursor or similar MCP clients. |
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose: catalog and health are meta; crawl, extract, map, search, research, and get_research each target different research stages. No overlap.
All tools follow a consistent 'tavily.<verb>' or 'tavily.get_research' pattern with snake_case, making the naming predictable.
8 tools is well within the ideal 3-15 range, and each tool serves a necessary function in the research workflow.
The tool set covers the full lifecycle: search for unknown URLs, map/extract/crawl for content, research for deep analysis, and get_research for results, plus health and catalog for metadata. No obvious gaps.