mrkeyoor.com_
Tue 01 Sept 16:17 UTC
SearchMCP servermeasured 19 Aug 2026

Tavily

Tavily is a hosted web-search API for agents, and tavily-mcp is the vendor's stdio bridge to it. It exposes five tools: search, extract, crawl, map, and research. An agent gets ranked web results and cleaned page text back as JSON instead of raw HTML, so it never has to parse a search results page itself.

BootBOOTS ✓We started it and initialize came back in 6.7s.
Tools5tools/list payload 7,694 bytes
Context tax~1,924estimated tokens for the whole tools/list, chars/4 estimate
Resources / prompts / counts returned by resources/list and prompts/list
Measured19 Aug 2026one run of the harness, clean environment, no credentials · how we test

How we started it

npx -y tavily-mcp
Verdict

Use it if you want your agent to read the live web and you're willing to pay Tavily per call. When we booted it the boot log admitted something most search servers hide: without a key it runs in keyless mode where search and extract work and the rest reply with an apology, so a first test can look healthy while crawl and map are dead. The other cost is that all five tools point at one vendor's index, so your agent's view of the web is whatever Tavily ranked that day. If you need results you can audit or self-host, skip it.

Use it if

Your agent answers questions about things that happened after its training cutoff and you want cleaned text, not HTML soup
You already hold a Tavily key for another service and adding the MCP bridge costs you nothing new
You want crawl and map for walking a documentation site, which plain search servers can't do
You'd rather pay per query than run a scraper and eat the blocking, retries, and proxy bill

Skip it if

You can't send the pages your agent is researching to a third-party API for compliance reasons
You only ever need one plain web search and a lighter single-tool server would do the job for free
Your billing is fixed monthly and per-call search costs make budgeting unpleasant
You need to see or tune the ranking, which a hosted index will not show you
You tested it keyless, liked it, and haven't checked whether the tools you actually depend on were live

The bill for your context window

ToolEst. tokensDescribed?Required params
tavily_search~723yes (145 chars)1
tavily_crawl~484yes (101 chars)1
tavily_map~319yes (83 chars)1
tavily_extract~209yes (79 chars)1
tavily_research~188yes (269 chars)1

Five tools weighing about 1,924 estimated tokens is a fair trade, and it sits almost exactly on the batch median, so Tavily costs you roughly what a typical server costs while doing more than most. The weight is lopsided: tavily_search alone accounts for 723 of those estimated tokens because its schema carries every filter the API supports, while tavily_research is the cheapest of the five despite having the longest description. If you only ever call search, you are still paying for crawl and map on every single turn, and there is no flag to trim the list.

Setup reality

It runs from npx with no build step, and the harness recorded no missing env vars because the server starts happily without any. That is the trap. Set TAVILY_API_KEY from your Tavily dashboard before you judge it, or you're evaluating a crippled copy. Transport is stdio, so it drops straight into a Claude Desktop or client config block with the command and args and nothing else. No OAuth, no callback URL, no local daemon.

Questions people ask

Does the Tavily MCP server work without an API key?

Partly. Our boot log shows it starting in keyless mode with search and extract available; the other tools return a message saying a key is required. Treat keyless as a smoke test, not a trial of the real thing.

How much context does tavily-mcp use?

Its tools/list payload measured 7,694 bytes, about 1,924 tokens by the chars/4 estimate, when we measured version 0.2.22 on 2026-08-19. That is the standing cost before your agent makes a single search call.

What's the difference between tavily_crawl and tavily_map?

Map returns a site's link structure; crawl fetches the pages themselves. Map first when you don't know a docs site's shape, then crawl only the branch you want, since crawling everything is how the bill grows.

Is it slow to start?

It took 6.7 seconds to initialize in our run, which is mostly npx fetching the package. Pin the version in your config or install it locally and that wait mostly disappears on later launches.

Other search servers we started

ServerVendorBootsContext tax
Brave Search (archived)Anthropic (archived)~0 tokens
DuckDuckGo Searchcommunity~0 tokens
ExaExa Labs~534 tokens

How this page is made: the server is spawned as an unprivileged user with a clean environment and no credentials, then asked for its tools, resources and prompts over stdio. Token figures are estimates at four characters per token, not a tokenizer count. One run, one machine. Corrections: contact the desk.

← All measured MCP servers