tavily-mcp
Production ready MCP server with real-time search, extract, map & crawl.
Runssource: GitHubTypeScriptMITcommit 1c1d54c2a619
TypeScript, MIT licensed.
tavily-mcp runs. An Argusic agent installed it in 0.1 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
npm install, TypeScript build, all 6 tests pass, and the MCP server starts in keyless mode responding to JSON-RPC calls on stdio with real Tavily API results.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- npm warns EBADENGINE: @hono/node-server requires Node >=20 but system has v18.19.1
- Install time
- under a minute
- Cold machine to finish
- 2 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm test: 6/6 passed; node build/index.js --version printed '0.2.23'; --list-tools showed 6 tools; tools/list JSON-RPC returned full tool schemas; tools/call tavily_search('test') returned 3533 chars with real Tavily API results (Request ID present, Detailed Results with result IDs)
- Model tokens used
- 32,503
- Exact commit tested
- 1c1d54c2a619
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
duration_ms: 0.134872 duration_ms: 0.141452 duration_ms: 0.275903 duration_ms: 0.171637 duration_ms: 0.136034 # tests 6 # pass 6 # fail 0 # duration_ms 204.499499 0.2.23 tokens used 32,503
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 0.1 minutes, faster than the median of the 35 comparable projects Argusic has measured.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
Of the 36 TypeScript projects Argusic has installed and timed, tavily-mcp was the 2nd fastest to reach a running state, and 30 of 36 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 0.1 minutes after the clone.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/tavily-mcp)Questions
- Does tavily-mcp run?
- Yes. tavily-mcp runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test tavily-mcp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1c1d54c2a619. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test tavily-mcp?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does tavily-mcp take to install?
- 0.1 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does tavily-mcp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing tavily-mcp?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does tavily-mcp compare with the alternatives?
- Of the 36 TypeScript projects Argusic has installed and timed, tavily-mcp was the 2nd fastest to reach a running state, and 30 of 36 reached one at all.
- Where is the evidence for tavily-mcp?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.