gpt-researcher
MCPAn open-source autonomous agent that researches a topic online and compiles findings into a cited report.
Runs web searches optimized for feeding accurate, sourced results directly into AI agent reasoning and retrieval.
Claude Code
> /plugin marketplace add tavily-ai/skills> /plugin install tavily@tavily-plugins
Codex
$ codex mcp add tavily --url https://mcp.tavily.com/mcp
Cursor
{ "mcpServers": { "tavily": { "url": "https://mcp.tavily.com/mcp" } } }
Add it to mcp.json.
Gemini CLI
$ gemini mcp add --transport http tavily https://mcp.tavily.com/mcp
GitHub Copilot
$ copilot mcp add --transport http tavily https://mcp.tavily.com/mcp
OpenCode
{ "mcp": { "tavily": { "type": "remote", "url": "https://mcp.tavily.com/mcp" } } }
Add it to opencode.json.
Windsurf
{ "mcpServers": { "tavily": { "serverUrl": "https://mcp.tavily.com/mcp" } } }
Add it to mcp_config.json.
Security report
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.
Web search, content extraction, site crawling, URL discovery, and deep research — powered by the Tavily CLI.
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.
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.
/plugin install tavily --marketplace tavily-ai/skills
It adds these skills and the hosted Tavily MCP server.
Install Tavily from the Cursor Marketplace. It adds these skills and the hosted Tavily MCP server.
codex plugin marketplace add tavily-ai/skills
Then install Tavily from /plugins. It adds these skills and the hosted Tavily MCP server.
In Grok Build, open /plugin, search for Tavily, and install it.
It adds these skills and the hosted Tavily MCP server.
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/.
agy plugin install tavily-ai/skills
It adds these skills and the hosted Tavily MCP server.
gemini extensions install https://github.com/tavily-ai/skills
It adds these skills and the hosted Tavily MCP server.
tvly update --check
tvly update
| Skill | Type | Description |
|---|---|---|
| tavily-search | Core | Search, extract, map and crawl as one toolkit. Search is in the skill; the other tools live in references/. |
| tavily-research | Task | In-depth research: many sources gathered and weighed into a cited report. |
| tavily-entity | Task | One company or person for a CRM, or a CSV of rows they already have. |
| tavily-list | Task | Deduplicated table of matches, with a cap. Not an exhaustive census. |
| tavily-monitor | Task | A search or extraction built to run on a cadence, with a baseline. |
| tavily-sdk | Developers | Reference docs for building production-ready Tavily integrations. |
Start simple, escalate when needed:
tvly search "query" --json)tvly extract "https://..." --json)tvly map "https://..." --json)tvly crawl "https://..." --output-dir ./docs/)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)Web search, content extraction, site crawling, URL discovery, and deep research — powered by the Tavily CLI.
An open-source autonomous agent that researches a topic online and compiles findings into a cited report.
Ships with amazon-sorftime-research-mcp-skill: 基于 Sorftime,Sif,卖家精灵,西柚等MCP 服务和 Agent Skills 的亚马逊分析工具集。…
Ships with idea-reality-mcp: How to check if someone already built your app idea — automatically. idea-reality-mcp is an MCP…