Skip to content

tavily

Runs web searches optimized for feeding accurate, sourced results directly into AI agent reasoning and retrieval.

From plugin
tavily
4906 skills1 MCP

Claude Code

> /plugin marketplace add tavily-ai/skills
> /plugin install tavily@tavily-plugins

Security report

Found

Low risk

  • Known flaws

    Not published

  • Signed build

    Not published

  • Maintained

    Nov 9, 2026

    Last push

  • Licence

    MIT

  • Runs as

    Remote

    mcp.tavily.com

  • Deprecated

    Not published

Signals from public registries, not an audit. Checked Nov 11, 2026.

tavily README

Tavily Agent Skills

Web search, content extraction, site crawling, URL discovery, and deep research — powered by the Tavily CLI.

Installation

Recommended: guided CLI setup

Install the Tavily CLI:

curl -fsSL https://cli.tavily.com/install.sh | bash

On a fresh interactive desktop install, the installer starts tvly init automatically. Otherwise run it after installation:

tvly init

# Prefer to open the sign-in link yourself
tvly init --no-browser

tvly init authenticates, detects Claude Code, Codex, and Cursor, installs these skills, and verifies a live search. It reuses an existing credential and is safe to rerun. Skills installed this way are pinned to the CLI release, so run tvly update before tvly init when refreshing them.

tvly search and tvly extract also work without authentication, subject to a keyless rate-limit cap. Use tvly init --skip-auth to keep keyless mode while installing the skills. map, crawl, and research require authentication.

Browser-based OAuth is the preferred interactive sign-in method. --no-browser simply prints the sign-in link instead of opening it automatically; the flow still returns to a localhost callback on the machine running tvly. In remote sessions, make sure that callback is reachable (SSH may require port forwarding). For unattended agents or CI, authenticate beforehand or provide TAVILY_API_KEY securely so the process does not wait for human input.

Manual skill installation

For other agents, or when you only want to install the skills:

npx skills add https://github.com/tavily-ai/skills

Install the CLI separately if needed:

uv tool install tavily-cli   # or: pip install tavily-cli

Then use tvly init --skip-skills for guided authentication and verification, or tvly login when you only need to authenticate.

Claude Code plugin

/plugin install tavily --marketplace tavily-ai/skills

It adds these skills and the hosted Tavily MCP server.

Cursor plugin

Install Tavily from the Cursor Marketplace. It adds these skills and the hosted Tavily MCP server.

Codex plugin

codex plugin marketplace add tavily-ai/skills

Then install Tavily from /plugins. It adds these skills and the hosted Tavily MCP server.

Grok Build plugin

In Grok Build, open /plugin, search for Tavily, and install it. It adds these skills and the hosted Tavily MCP server.

OpenCode plugin

Add @tavily/opencode-plugin to the plugins array in opencode.json (plugin on OpenCode 1.x):

{
  "$schema": "https://opencode.ai/config.json",
  "plugins": ["@tavily/opencode-plugin"]
}

It adds these skills. The plugin's source is in .opencode-plugin/.

Antigravity plugin

agy plugin install tavily-ai/skills

It adds these skills and the hosted Tavily MCP server.

Gemini CLI extension

gemini extensions install https://github.com/tavily-ai/skills

It adds these skills and the hosted Tavily MCP server.

Keep the CLI current

tvly update --check
tvly update

Available Skills

SkillTypeDescription
tavily-searchCoreSearch, extract, map and crawl as one toolkit. Search is in the skill; the other tools live in references/.
tavily-researchTaskIn-depth research: many sources gathered and weighed into a cited report.
tavily-entityTaskOne company or person for a CRM, or a CSV of rows they already have.
tavily-listTaskDeduplicated table of matches, with a cap. Not an exhaustive census.
tavily-monitorTaskA search or extraction built to run on a cadence, with a baseline.
tavily-sdkDevelopersReference docs for building production-ready Tavily integrations.

Workflow

Start simple, escalate when needed:

  1. Search — Find pages on a topic (tvly search "query" --json)
  2. Extract — Get content from a specific URL (tvly extract "https://..." --json)
  3. Map — Discover URLs on a site (tvly map "https://..." --json)
  4. Crawl — Bulk extract from a site section (tvly crawl "https://..." --output-dir ./docs/)
  5. A finished result — in-depth research (tavily-research), a CRM record or CSV enrichment (tavily-entity), a capped table of matches (tavily-list), or a check on a cadence (tavily-monitor)
@tavily-ai
Ships withtavily

Web search, content extraction, site crawling, URL discovery, and deep research — powered by the Tavily CLI.

Stars on GitHub

Momentum

stars in total
490
Star history of tavily-ai/skills on GitHub, a chart by star-history.com

More MCP servers from other plugins.

idea-reality

idea-reality

MCP

Ships with idea-reality-mcp: How to check if someone already built your app idea — automatically. idea-reality-mcp is an MCP…

Questions about tavily.

Which coding agents can use tavily?
tavily works in any agent that reads an MCP config file: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf. Each agent reads it from its own file; this page names the file for each one.
How do I add tavily to Claude Code?
Run these in order, one at a time. 1. In Claude Code: /plugin marketplace add tavily-ai/skills 2. In Claude Code: /plugin install tavily@tavily-plugins
Is tavily safe to install?
Low risk. Signals from public registries, not an audit.