Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.tavily-ai/tavily-mcp

NPM · TAVILY-MCP · SCANNED SEP 20

MCP server for advanced web search using Tavily

Available components

+1 this week 76 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects @modelcontextprotocol/sdk 1.25.2, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 38 of 123 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability59
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1017 tokens (~254/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the io.github.tavily-ai/tavily-mcp server?

io.github.tavily-ai/tavily-mcp runs locally as an npm package, launched with npx -y tavily-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · tavily-mcp

# add to Claude Code
claude mcp add tavily-ai-tavily-mcp -- npx -y tavily-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "tavily-ai-tavily-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "tavily-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "tavily-ai-tavily-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "tavily-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add tavily-ai-tavily-mcp -- npx -y tavily-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tavily-ai-tavily-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "tavily-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add tavily-ai-tavily-mcp --command npx --arg -y --arg tavily-mcp
# ~/.hermes/config.yaml
mcp_servers:
  tavily-ai-tavily-mcp:
    command: "npx"
    args: ["-y", "tavily-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "tavily-ai-tavily-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "tavily-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add tavily-ai-tavily-mcp -t stdio -c npx -a -y tavily-mcp
// mcp.json
{
  "mcpServers": {
    "tavily-ai-tavily-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "tavily-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 0
    • Security disclosure: unverified → fail functional
  • 16 Sept 26 −2
    • Security disclosure: fail → unverified functional
    • Stability: pass → 0.83 functional
  • 15 Sept 26 0
    • Stability: 0.97 → pass security
  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/tavily-mcp@0.2.15

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-345p-7cg4-v4c7 CVE-2026-25536 high CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 123 packages
Packages resolved 123
Stale 38
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 4 exposed · ~1,017 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
tavily_crawl ~290

Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.

NameTypeReqDescription
allow_externalbooleanWhether to return external links in the final response
extract_depthstringAdvanced extraction retrieves more data, including tables and embedded content, with higher success but may increase latency
formatstringThe format of the extracted web page content. markdown returns content in markdown format. text returns plain text and may increase latency.
include_faviconbooleanWhether to include the favicon URL for each result
instructionsstringNatural language instructions for the crawler. Instructions specify which types of pages the crawler should return.
limitintegerTotal number of links the crawler will process before stopping
max_breadthintegerMax number of links to follow per level of the tree (i.e., per page)
max_depthintegerMax depth of the crawl. Defines how far from the base URL the crawler can explore.
select_domainsarrayRegex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\.example\.com$)
select_pathsarrayRegex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)
urlstringyesThe root URL to begin the crawl

No output schema declared.

No examples provided.

tavily_extract ~110

Extract content from URLs. Returns raw page content in markdown or text format.

NameTypeReqDescription
extract_depthstringUse 'advanced' for LinkedIn, protected sites, or tables/embedded content
formatstringOutput format
include_faviconbooleanInclude favicon URLs
include_imagesbooleanInclude images from pages
querystringQuery to rerank content chunks by relevance
urlsarrayyesList of URLs to extract content from

No output schema declared.

No examples provided.

tavily_map ~201

Map a website's structure. Returns a list of URLs found starting from the base URL.

NameTypeReqDescription
allow_externalbooleanWhether to return external links in the final response
instructionsstringNatural language instructions for the crawler
limitintegerTotal number of links the crawler will process before stopping
max_breadthintegerMax number of links to follow per level of the tree (i.e., per page)
max_depthintegerMax depth of the mapping. Defines how far from the base URL the crawler can explore
select_domainsarrayRegex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\.example\.com$)
select_pathsarrayRegex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)
urlstringyesThe root URL to begin the mapping

No output schema declared.

No examples provided.

tavily_search ~416

Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.

NameTypeReqDescription
countrystringBoost search results from a specific country. This will prioritize content from the selected country in the search results. Available only if topic is general.
end_datestringWill return all results before the specified end date. Required to be written in the format YYYY-MM-DD
exclude_domainsarrayList of domains to specifically exclude, if the user asks to exclude a domain set this to the domain of the site
include_domainsarrayA list of domains to specifically include in the search results, if the user asks to search on specific sites set this to the domain of the site
include_faviconbooleanWhether to include the favicon URL for each result
include_image_descriptionsbooleanInclude a list of query-related images and their descriptions in the response
include_imagesbooleanInclude a list of query-related images in the response
include_raw_contentbooleanInclude the cleaned and parsed HTML content of each search result
max_resultsnumberThe maximum number of search results to return
querystringyesSearch query
search_depthstringThe depth of the search. 'basic' for generic results, 'advanced' for more thorough search, 'fast' for optimized low latency with high relevance, 'ultra-fast' for prioritizing latency above all else
start_datestringWill return all results after the specified start date. Required to be written in the format YYYY-MM-DD.
time_rangestringThe time range back from the current date to include in the search results. This feature is available for both 'general' and 'news' search topics
topicstringThe category of the search. This will determine which of our agents will be used for the search

No output schema declared.

No examples provided.

Common questions

What is the io.github.tavily-ai/tavily-mcp server?

io.github.tavily-ai/tavily-mcp is listed in the public MCP registry as io.github.tavily-ai/tavily-mcp. MCP server for advanced web search using Tavily. This page covers its npm package (tavily-mcp).

Is the io.github.tavily-ai/tavily-mcp server safe to use?

io.github.tavily-ai/tavily-mcp scores 76 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.tavily-ai/tavily-mcp server expose?

io.github.tavily-ai/tavily-mcp exposes 4 tools: tavily_search, tavily_extract, tavily_crawl, tavily_map. Their descriptions and schemas cost roughly 1,017 tokens of context every time the server is loaded.

Is the io.github.tavily-ai/tavily-mcp server still maintained?

io.github.tavily-ai/tavily-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.tavily-ai/tavily-mcp server under?

io.github.tavily-ai/tavily-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.