Enables LLMs to perform AI-powered web searches using the Tavily search API.
Tavily MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Enables LLMs to perform AI-powered web searches using the Tavily search API.
I built this MCP server back in early March of 2025 when the MCP protocol was brand new and there were no consistent ways to do search in chatbots, predating other implementations.
Installation goes through your MCP client rather than a global install: point it at npx on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Once Tavily is connected, these are the calls the assistant has available:
tavily_web_search — Performs comprehensive web searches with AI-powered content extractiontavily_answer_search — Performs web searches and generates direct answers with supporting evidencetavily_news_search — Searches recent news articles with publication datesPrompts — The server also provides prompt templates for each search type:You will need one environment variable: TAVILY_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
uv Python package manager (recommended)This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Tavily's toolset — tavily_web_search, tavily_answer_search, tavily_news_search and 1 more — is a fair guide to whether it matches your workflow. It is maintained by RamXX; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Tavily's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| tavily_web_search | Performs comprehensive web searches with AI-powered content extraction. |
| tavily_answer_search | Performs web searches and generates direct answers with supporting evidence. |
| tavily_news_search | Searches recent news articles with publication dates. |
| Prompts | The server also provides prompt templates for each search type: |
{
"mcpServers": {
"tavily-3": {
"command": "npx",
"args": ["-y", "npx"],
"env": {
"TAVILY_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
uv Python package manager (recommended)| Variable | Description | Required |
|---|---|---|
| TAVILY_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.