Tavily MCP — wraps the Tavily API (tavily.com)
Run one of the commands below, then pick your client in the next section.
Streamable HTTP
https://gateway.pipeworx.io/tavily/mcp
Pick your client — the config below is generated for this server (hosted endpoint).
Remote (hosted) endpoint
https://gateway.pipeworx.io/tavily/mcp
Claude Desktop: Settings → Connectors → Add custom connector, paste this URL.
Format verified against the official Claude Desktop docs ↗.
terminal
claude mcp add --transport http tavily-pipeworx-io https://gateway.pipeworx.io/tavily/mcp
Format verified against the official Claude Code docs ↗.
.cursor/mcp.json (hosted endpoint)
{
"mcpServers": {
"tavily-pipeworx-io": {
"url": "https://gateway.pipeworx.io/tavily/mcp"
}
}
}Format verified against the official Cursor docs ↗.
.vscode/mcp.json (hosted endpoint)
{
"servers": {
"tavily-pipeworx-io": {
"type": "http",
"url": "https://gateway.pipeworx.io/tavily/mcp"
}
}
}Format verified against the official VS Code docs ↗.
mcp_config.json (hosted endpoint)
{
"mcpServers": {
"tavily-pipeworx-io": {
"serverUrl": "https://gateway.pipeworx.io/tavily/mcp"
}
}
}Format verified against the official Windsurf docs ↗.
最近更新于 18 天前 · MIT license
mcp-tavily Tavily MCP — wraps the Tavily API (tavily.com) Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources. Tools Tool Description ------ ------------- search AI/LLM-optimized web search built for RAG: returns a synthesized natural-language answer plus a ranked list of sourced results (title, url, content snippet, relevance score). Prefer this over scraping a generic search engine when you need grounded, citable web context. Example: search({ query: "latest SpaceX Starship test result" }) tavily news Recent NEWS coverage with FULL ARTICLE TEXT — "latest news about /person/topic>", "news coverage of X this week", "what are people reporting about X", "recent headlines on X". Returns a synthesized answer plus ranked articles each carrying title, url, publication content, and a relevance score — the full text, not just a headline, so the calling agent can quote and cite. Freshness-windowed via days (default 7). This is the premium news path (Tavily, funded key, no per-IP throttle, no shared free-tier quota); prefer it when the question asks what is being REPORTED about a specific entity or topic. extract Extract clean article text from one or more URLs via Tavily: strips boilerplate/navigation and returns up to 20,000 chars of readable content per page. Accepts a single URL string or an array. Ideal for feeding source pages into an LLM. Quick Start Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.): What this endpoint actually serves tools/list at returns the tools in the table above plus the shared Pipeworx meta-tools — ask pipeworx , discover tools , search within , remember / recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day. This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask pipeworx , which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints. Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's: Both URLs reach the same gateway and the same 1683+ data sources. The only difference is which pack's tools are listed directly ; ask pipeworx reaches all of them from either one. No MCP client? Call it over HTTP Our tavily key is reserved for paid accounts, so an anonymous call to POST needs your own key passed as apiKey alongside the arguments. Inspect any tool: GET Find one: POST with {"query":"..."} . Standalone (no gateway account) This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip: Or run it directly to confirm it starts: It speaks MCP over stdin/stdout and answers initialize / tools/list / tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask pipeworx routing. Using with ask pipeworx Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway: The gateway picks the right tool and fills the arguments automatically. More Docs and guides pipeworx.io License MIT…
Summary from the project README — github.com/pipeworx-io/mcp-tavily
Distributed as Streamable HTTP, listed under Search. Review our MCP security guide before granting access to real data.
mcp-tavily Tavily MCP — wraps the Tavily API (tavily.com) Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources. Tools Tool Description ------ ------------- search AI/LLM-optimized web search built for RAG: returns a synthesized natural-language answer plus a ranked list of sourced results (title, url, content snippet, relevance score). Prefer this over scraping a generic search engine when you need grounded, citable web context. Example: search({ query: "latest SpaceX Starship test result" }) tavily news Recent NEWS coverage with FULL ARTICLE TEXT — "latest news about /person/topic>", "news coverage of X this week", "what are people reporting about X", "recent headlines on X". Returns a synthesized answer plus ranked articles each carrying title, url, publication content, and a relevance score — the full text, not just a headline, so the calling agent can quote and cite. Freshness-windowed via days (default 7). This is the premium news path (Tavily, funded key, no per-IP throttle, no shared free-tier quota); prefer it when the question asks what is being REPORTED about a specific entity or topic. extract Extract clean article text from one or more URLs via Tavily: strips boilerplate/navigation and returns up to 20,000 chars of readable content per page. Accepts a single URL string or an array. Ideal for feeding source pages into an LLM. Quick Start Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.): What this endpoint actually serves tools/list at returns the tools in the table above plus the shared Pipeworx meta-tools — ask pipeworx , discover tools , search within , remember / recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day. This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask pipeworx , which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints. Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's: Both URLs reach the same gateway and the same 1683+ data sources. The only difference is which pack's tools are listed directly ; ask pipeworx reaches all of them from either one. No MCP client? Call it over HTTP Our tavily key is reserved for paid accounts, so an anonymous call to POST needs your own key passed as apiKey alongside the arguments. Inspect any tool: GET Find one: POST with {"query":"..."} . Standalone (no gateway account) This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip: Or run it directly to confirm it starts: It speaks MCP over stdin/stdout and answers initialize / tools/list / tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask pipeworx routing. Using with ask pipeworx Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway: The gateway picks the right tool and fills the arguments automatically. More Docs and guides pipeworx.io License MIT
Run the install command shown above, then paste the config for your client (Claude Desktop, Claude Code, Cursor, VS Code or Windsurf) into its MCP settings and restart the client.
The MCP server itself is free to install. The source is public on https://github.com/pipeworx-io/mcp-tavily. Any third-party service it calls may require its own API key and account.
Any MCP-compatible client can use it, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and custom agents.
Publish this server? Link back with a badge on your README or site — copy either snippet.
Markdown
[](https://mcpnav.net/server/tavily-pipeworx-io/)
HTML
<a href="https://mcpnav.net/server/tavily-pipeworx-io/"><img src="https://mcpnav.net/badge/tavily-pipeworx-io.svg" alt="Listed on MCPNav" height="20"></a>