tavily-search-mcp
A cost-aware stdio MCP server for the Tavily Search API, supporting basic, fast, ultra fast, and advanced searches with credit tracking and automatic API key rotation.
README
Tavily Search MCP
A cost-aware stdio MCP server for the official Tavily Search API.
Tool
tavily_search supports:
- Basic, Fast, and Ultra Fast Search at 1 API credit.
- Advanced Search at 2 API credits, only when explicitly selected.
- General, news, and finance topics.
- Domain and date filters.
- Up to 20 ranked results with source URLs and relevance scores.
- Reported credit usage, response time, and request ID.
The server always sends auto_parameters: false, include_usage: true, and excludes generated answers, raw pages, and images. This keeps cost and response size predictable while leaving synthesis to the MCP client.
Configuration
Required at call time:
TAVILY_API_KEY
On Windows, run npm run setup for the first-install configuration window. Enter multiple API keys separated by semicolons. It saves the API URL as a non-secret setting and stores the key array as a current-user DPAPI ciphertext under %APPDATA%\tavily-search-mcp\api-key.dpapi. Environment variables (TAVILY_API_KEYS or TAVILY_API_KEY) still take precedence for CI or temporary sessions.
Requests rotate across configured keys. Authentication, rate-limit, and quota responses (401, 429, 432, 433) can switch to the next distinct key, with a hard maximum of three attempts per MCP call. Server failures and ambiguous errors are not retried.
Optional:
TAVILY_API_URL=https://api.tavily.com/search
The server starts and lists tools without a key, then fails closed with a clear error if a search is attempted before TAVILY_API_KEY is configured. Secrets are never accepted as tool arguments or printed.
Each installation must use its own Tavily credentials. Do not share .env files, DPAPI ciphertext, setup screenshots, or API keys with other users.
Development
npm install
npm run check
Codex configuration
After building, register the compiled entry point and forward only the required environment variable:
[mcp_servers.tavily_search]
command = "node"
args = ["D:/path/to/tavily-search-mcp/dist/index.js"]
env_vars = ["TAVILY_API_KEYS", "TAVILY_API_KEY", "TAVILY_API_URL"]
startup_timeout_sec = 20
tool_timeout_sec = 60
No request is retried automatically. HTTP redirects are rejected so the API key cannot be forwarded to another origin.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.