如何将 Tavily Docs 远程 MCP 连接到 Cursor
约 1 分钟即可把 Tavily 的远程 MCP 服务端接入 Cursor。如需排查 OAuth / 401 问题,可先用 OAuth 2.1 调试器体检端点。
Streamable HTTPhttps://docs.tavily.com/mcp
Install in Cursor →
Or add to ~/.cursor/mcp.json:
{
"mcpServers": {
"tavily-docs": {
"url": "https://docs.tavily.com/mcp"
}
}
}claude mcp add --transport http tavily-docs https://docs.tavily.com/mcp
Install in VS Code →
Or add to .vscode/mcp.json:
{
"servers": {
"tavily-docs": {
"type": "http",
"url": "https://docs.tavily.com/mcp"
}
}
}- Open Settings → Connectors (Integrations) → Add Custom Connector.
- Paste the endpoint URL:
https://docs.tavily.com/mcp - No authentication needed — tools are available immediately.
Bridge the remote endpoint into stdio with mcp-remote in claude_desktop_config.json:
{
"mcpServers": {
"tavily-docs": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://docs.tavily.com/mcp"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"tavily-docs": {
"serverUrl": "https://docs.tavily.com/mcp"
}
}
}Add to ~/.kiro/settings/mcp.json (or .kiro/settings/mcp.json in your workspace), then reopen Kiro's Agent panel to pick up the server:
{
"mcpServers": {
"tavily-docs": {
"url": "https://docs.tavily.com/mcp"
}
}
}Add to ~/.codex/config.toml — Codex reads remote HTTP servers from [mcp_servers.*] tables:
[mcp_servers.tavily-docs] url = "https://docs.tavily.com/mcp"
Add to cline_mcp_settings.json (Cline → MCP Servers → Configure), or paste it via Cline's MCP marketplace file:
{
"mcpServers": {
"tavily-docs": {
"type": "streamableHttp",
"url": "https://docs.tavily.com/mcp"
}
}
}Add to ~/.gemini/settings.json under mcpServers — httpUrl for Streamable HTTP, url for legacy SSE:
{
"mcpServers": {
"tavily-docs": {
"httpUrl": "https://docs.tavily.com/mcp"
}
}
}接入步骤
- 打开 MCP 设置 — Cursor → Settings → MCP,或直接编辑全局
~/.cursor/mcp.json/ 项目级.cursor/mcp.json。 - 添加服务端 — 点击本页一键 deeplink 自动安装,或在
mcpServers下加入"tavily-docs": { "url":https://docs.tavily.com/mcp}。 - 完成认证 — 无需认证——Tavily Docs MCP 为免密公开端点。
- 验证 — 在 在线 Inspector 中粘贴
https://docs.tavily.com/mcp并运行 initialize + tools/list 验证连通性。
🧰 工具预览(3)
| Tool | Safety | Description | Parameters |
|---|---|---|---|
| search_tavily_docs ~203 tok | 🟢 Readidempotent | Search across the Tavily Docs knowledge base to find relevant information, code examples, API references, and guides. Use this tool when you need to answer questions about Tavily Docs, find specific documentation, understand how features work, or locate implementation details. The search returns contextual content with titles and direct links to the documentation pages. If you need the full content of a specific page, use the query_docs_filesystem tool to `head` or `cat` the page path (append `.mdx` to the path returned from search — e.g. a result at `/some/page` is read with `head -200 /some/page.mdx`). | query*: string |
| query_docs_filesystem_tavily_docs ~872 tok | 🟢 Readidempotent | Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the Tavily Docs documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path to `head` or `cat` — a page at the URL path `/some/page` lives at `/some/page.mdx`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Paths are specific to this site — never guess them.** Discover real paths with `tree / -L 2`, `ls /`, or the search tool before reading. If a path does not exist, that only means the guess was wrong; it does NOT mean the topic is undocumented — use `rg -il "keyword" /` to find where it is covered. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /some-directory && ls` or `ls /some-directory`). Do NOT assume that `cd` in one call affects the next call. Examples (replace the placeholder paths with real ones from `tree` or search): - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /some-directory/` — show matches with 3 lines of context around each hit - `head -80 /some/page.mdx` — read the top 80 lines of a specific page - `head -80 /page-one.mdx /page-two.mdx /section/page-three.mdx` — read multiple pages in one call - `cat /some/page.mdx` — read a full page when you need everything - `cat /openapi/documentation/api-reference/openapi.json | jq '.paths | keys'` — list OpenAPI endpoints OpenAPI specs for this site are mounted under `/openapi`; run `find /openapi -type f` to list them. Use them to answer questions about endpoints, request/response schemas, parameters, and authentication. Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/some/page.mdx` becomes `/some/page`. | command*: string |
| submit_feedback ~203 tok | 🟠 Writeopen-world | Report a problem with this documentation site so the docs team can fix it. Use when a documentation page is incorrect, outdated, confusing, incomplete, or has a broken example. This is for feedback about the documentation content itself — not for product support requests or feedback about this tool or assistant. | path*: stringfeedback*: string |