MCPInstall

tavily

Tavily API integration with managed API key authentication. Perform AI-powered web search, extract content from URLs, crawl websites, map site structure, and run research tasks. Use this skill when users want to search the web, extract page content, crawl websites, discover URLs, or conduct in-depth research with citations. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Requires network access and valid Maton API key.

Installs
324
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://skills.volces.com --skill tavily
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads tavily automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Tavily

Access the Tavily API with managed API key authentication. Perform AI-powered web searches, extract content from URLs, crawl websites, map site structure, and run in-depth research tasks.

Quick Start

# Search the web
python <<'EOF'
import urllib.request, os, json
data = json.dumps({"query": "latest AI news", "max_results": 5}).encode()
req = urllib.request.Request('https://gateway.maton.ai/tavily/search', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Base URL

https://gateway.maton.ai/tavily/{endpoint}

Replace {endpoint} with the Tavily API endpoint (search, extract, crawl, map, research). The gateway proxies requests to api.tavily.com and automatically injects your API key.

Authentication

All requests require the Maton API key in the Authorization header:

Authorization: Bearer $MATON_API_KEY

Environment Variable: Set your API key as MATON_API_KEY:

export MATON_API_KEY="YOUR_API_KEY"

Getting Your API Key

  1. Sign in or create an account at maton.ai
  2. Go to maton.ai/settings
  3. Copy your API key

Connection Management

Manage your Tavily API key connections at https://ctrl.maton.ai.

List Connections

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections?app=tavily&status=ACTIVE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Create Connection

python <<'EOF'
import urllib.request, os, json
data = json.dumps({'app': 'tavily', 'method': 'API_KEY'}).encode()
req = urllib.request.Request('https://ctrl.maton.ai/connections', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Open the returned url in a browser to enter your Tavily API key.

Get Connection

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Delete Connection

python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}', method='DELETE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

Specifying Connection

If you have multiple Tavily connections, specify which one to use with the Maton-Connection header:

python <<'EOF'
import urllib.request, os, json
data = json.dumps({"query": "AI news"}).encode()
req = urllib.request.Request('https://gateway.maton.ai/tavily/search', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
req.add_header('Maton-Connection', '{connection_id}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF

If omitted, the gateway uses the default (oldest) active connection.

API Reference

Search

Perform AI-powered web search with optional answer generation.

POST /tavily/search
Content-Type: application/json

{
  "query": "What is artificial intelligence?",
  "max_results": 5
}

Request Parameters:

ParameterTypeRequiredDescription
querystringYesSearch query string
max_resultsintegerNoNumber of results (0-20, default 5)
search_depthstringNobasic, advanced, fast, ultra-fast (default: basic)
topicstringNogeneral or news (default: general)
include_answerboolean/stringNotrue, false, basic, advanced
include_raw_contentboolean/stringNotrue, false, markdown, text
include_imagesbooleanNoInclude image results
include_domainsarrayNoOnly search these domains (max 300)
exclude_domainsarrayNoExclude these domains (max 150)
time_rangestringNoday, week, month, year
start_datestringNoFilter by date (YYYY-MM-DD)
end_datestringNoFilter by date (YYYY-MM-DD)

Response:

{
  "query": "What is artificial intelligence?",
  "answer": "Artificial intelligence (AI) is...",
  "results": [
    {
      "title": "What is AI?",
      "url": "https://example.com/ai",
      "content": "AI is a branch of computer science...",
      "score": 0.95
    }
  ],
  "response_time": 0.55
}

Extract

Extract content from one or more URLs.

POST /tavily/extract
Content-Type: application/json

{
  "urls": ["https://example.com/article"],
  "format": "markdown"
}

Request Parameters:

ParameterTypeRequiredDescription
urlsstring/arrayYesURL or array of URLs to extract
querystringNoUser intent for reranking content
chunks_per_sourceintegerNoMax chunks per source (1-5, default 3)
extract_depthstringNobasic or advanced (default: basic)
formatstringNomarkdown or text (default: markdown)
include_imagesbooleanNoInclude extracted images
timeoutfloatNoMax wait time in seconds (1-60)

Response:

{
  "results": [
    {
      "url": "https://example.com/article",
      "raw_content": "# Article Title\n\nContent in markdown...",
      "images": [],
      "favicon": "https://example.com/favicon.ico"
    }
  ],
  "failed_results": [],
  "response_time": 0.01
}

Map

Discover URLs from a website without extracting content.

POST /tavily/map
Content-Type: application/json

{
  "url": "https://example.com",
  "limit": 20
}

Request Parameters:

ParameterTypeRequiredDescription
urlstringYesRoot URL to begin mapping
instructionsstringNoNatural language guidance for crawler
max_depthintegerNoExploration depth (1-5, default 1)
max_breadthintegerNoLinks per page level (1-500, default 20)
limitintegerNoTotal links to process (default 50)
select_pathsarrayNoRegex patterns for URL inclusion
exclude_pathsarrayNoRegex patterns for URL exclusion
allow_externalbooleanNoInclude external links (default true)
timeoutfloatNoMax wait time (10-150 seconds)

Response:

{
  "base_url": "https://example.com",
  "results": [
    "https://example.com/about",
    "https://example.com/products",
    "https://example.com/contact"
  ],
  "response_time": 0.1
}

Crawl

Crawl a website and extract content from discovered pages.

POST /tavily/crawl
Content-Type: application/json

{
  "url": "https://example.com",
  "limit": 10,
  "max_depth": 2
}

Request Parameters:

ParameterTypeRequiredDescription
urlstringYesRoot URL to begin crawl
instructionsstringNoNatural language guidance (2x cost)
chunks_per_sourceintegerNoMax snippets per source (1-5, default 3)
max_depthintegerNoExploration depth (1-5, default 1)
max_breadthintegerNoLinks per page level (1-500, default 20)
limitintegerNoTotal links to process (default 50)
select_pathsarrayNoRegex patterns for URL inclusion
exclude_pathsarrayNoRegex patterns for URL exclusion
allow_externalbooleanNoInclude external links (default true)
extract_depthstringNobasic or advanced (default: basic)
formatstringNomarkdown or text (default: markdown)
timeoutfloatNoMax wait time (10-150 seconds)

Response:

{
  "base_url": "https://example.com",
  "results": [
    {
      "url": "https://example.com/about",
      "raw_content": "# About Us\n\nContent...",
      "favicon": "https://example.com/favicon.ico"
    }
  ],
  "response_time": 0.09
}

Research Tasks

Run async research tasks that gather sources and synthesize findings.

Create Research Task

POST /tavily/research
Content-Type: application/json

{
  "input": "What are the latest developments in AI safety?",
  "model": "mini"
}

Request Parameters:

ParameterTypeRequiredDescription
inputstringYesResearch task or question
modelstringNomini, pro, or auto (default: auto)
streambooleanNoStream results via SSE (default: false)
output_schemaobjectNoJSON Schema for structured output
citation_formatstringNonumbered, mla, apa, chicago

Response:

{
  "request_id": "582a6eec-9a10-43ba-830f-d9a1aeb19f07",
  "status": "pending",
  "input": "What are the latest developments in AI safety?",
  "model": "mini",
  "created_at": "2026-03-08T11:36:12.674507+00:00",
  "response_time": 0.05
}

Get Research Task

GET /tavily/research/{request_id}

Response (completed):

{
  "request_id": "582a6eec-9a10-43ba-830f-d9a1aeb19f07",
  "status": "completed",
  "content": "## AI Safety Developments\n\nResearch findings...",
  "sources": [
    {
      "title": "Source Title",
      "url": "https://example.com/source",
      "favicon": "https://example.com/favicon.ico"
    }
  ],
  "created_at": "2026-03-08T11:36:12.674507+00:00",
  "response_time": 45
}

Status values: pending, in_progress, completed, failed

Code Examples

JavaScript

// Search with answer
const response = await fetch('https://gateway.maton.ai/tavily/search', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${process.env.MATON_API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    query: 'latest AI news',
    max_results: 5,
    include_answer: true
  })
});
const data = await response.json();

Python

import os
import requests

# Search with answer
response = requests.post(
    'https://gateway.maton.ai/tavily/search',
    headers={'Authorization': f'Bearer {os.environ["MATON_API_KEY"]}'},
    json={
        'query': 'latest AI news',
        'max_results': 5,
        'include_answer': True
    }
)
data = response.json()

Notes

  • Search endpoints return AI-generated answers when include_answer is enabled
  • Map returns URLs only; Crawl returns URLs with extracted content
  • Using instructions parameter in crawl/map doubles the credit cost
  • Research tasks are async - poll with GET to check status
  • Research models: mini (fast/efficient), pro (comprehensive)
  • IMPORTANT: When piping curl output to jq or other commands, environment variables like $MATON_API_KEY may not expand correctly in some shell environments

Error Handling

StatusMeaning
400Missing Tavily connection or invalid request
401Invalid or missing Maton API key
429Rate limit exceeded
432Plan limit exceeded
433Pay-as-you-go limit exceeded
4xx/5xxPassthrough error from Tavily API

Resources

FAQ

What does the tavily skill do?

Tavily API integration with managed API key authentication. Perform AI-powered web search, extract content from URLs, crawl websites, map site structure, and run research tasks. Use this skill when users want to search the web, extract page content, crawl websites, discover URLs, or conduct in-depth research with citations. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Requires network access and valid Maton API key.

How do I install tavily?

Run npx skills add https://skills.volces.com --skill tavily in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/tavily/ (personal) or .claude/skills/tavily/ (project).

Which AI agents can use tavily?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is tavily safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains tavily?

It is published by skills.volces.com in skills.volces.com. It has 324 recorded installs.

More from skills.volces.com

View all →

byted-web-search

skills.volces.com

火山引擎豆包搜索 API(原联网搜索/融合信息搜索),返回网页/图片结果。联网搜索场景优先使用本 skill。触发词包括:豆包搜索、查/搜/找、真的吗/靠谱吗/确认/核实、最近/今天/最新/近期、出处/来源/链接、Agent Plan、融合信息搜索、Harness、有什么/有哪些/推荐、价格/政策/汇率/行情、对比/区别/哪个好、听说/据说/不太确定、热搜/热门/火、帮我看/了解一下、求证/辟谣、值不值得/该不该。任务依赖在线事实或时效性时优先使用。若回答可能依赖外部事实,优先调用本 skill 再作答。

byted-supabase

skills.volces.com

火山引擎 Supabase . 管理 AIDAP Supabase 项目、工作区、数据库、分支、Auth、Realtime、Edge Functions、Storage、API Keys、SQL、Schema 变更、TypeScript 类型生成和 MCP 集成。

Data & Databases11.1K installs

find-skills

skills.volces.com

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Backend & APIs1.6K installs

byted-util-ark-cua

skills.volces.com

Delegate broad computer-use tasks to ARK CUA for Volcengine AgentPlan users through an authenticated cloud desktop, and synchronize explicit credentials to a caller-owned CUA through Credential Agent. Use for web or desktop-app operation, file workflows, reusable task contexts, artifacts, temporary CUA App URLs, desktop shutdown/start/recovery, inspection, or exact browser, environment, secret, Credential Set, and managed-file credential setup/sync/status/reset. Do not use when local reasoning or a purpose-built local/API tool can complete the request more directly.

agent-browser

skills.volces.com

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

self-improving-agent

skills.volces.com

AI自我改进与记忆系统 - 解决'同类错误反复犯、用户纠正不长记性'的痛点。自动捕获错误、用户纠正、最佳实践,并转化为长期记忆。

1.4K installs

Popular productivity & automation skills

View category →

agent-browser

vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

OfficialProductivity & Automation1.3M installs

lark-doc

open.feishu.cn

飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

lark-base

open.feishu.cn

飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。

lark-drive

open.feishu.cn

飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。

lark-shared

open.feishu.cn

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.

lark-im

open.feishu.cn

飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。