What is mcp_sample_tavily CLAUDE.md?

A set of Claude Code instructions for a TypeScript MCP server that connects AI assistants to Tavily web search and data-extraction APIs, with optional Skyflow protection for sensitive information.

Use it when developing or testing tools for web searching, extracting, crawling, or mapping information through Tavily.

It explains the project’s build, inspection, and testing workflow so changes can be made and checked consistently.

How SkyflowFoundry/mcp_sample_tavily configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to SkyflowFoundry/mcp_sample_tavily. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/SkyflowFoundry/mcp_sample_tavily/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/SkyflowFoundry/mcp_sample_tavily

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/skyflowfoundry/mcp_sample_tavily/claude-md/github.svg)](https://agentmods.dev/instructions/skyflowfoundry/mcp_sample_tavily/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/skyflowfoundry/mcp_sample_tavily/claude-md"><img src="https://agentmods.dev/badge/instructions/skyflowfoundry/mcp_sample_tavily/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/skyflowfoundry/mcp_sample_tavily/claude-md"><img src="https://agentmods.dev/badge/instructions/skyflowfoundry/mcp_sample_tavily/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,256 This file is loaded in full into every session.

When invoked 1,256 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01256	$0.01256
Opus 5.5	$0.00502	$0.00502
Sonnet 5.5	$0.00251	$0.00251
Haiku 4.5	$0.00126	$0.00126

Measured 2mo ago against content hash 5b837a91ee48, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp_sample_tavily CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a TypeScript-based Model Context Protocol (MCP) server for Tavily's advanced web search and data extraction capabilities with optional Skyflow deidentification integration. It enables AI assistants like Claude to interact with Tavily's search, extract, crawl, and map APIs through the MCP protocol while automatically protecting sensitive data through Skyflow's deidentification service.

Development Commands

Build and Development

npm run build - Compile TypeScript to JavaScript and set executable permissions
npm run watch - Run TypeScript compiler in watch mode for development
npm run prepare - Runs build (used by npm install)
npm run prepublishOnly - Runs build before publishing

Testing and Inspection

npm run inspector - Launch MCP inspector for debugging server tools
npx tavily-mcp --list-tools - List available tools (requires TAVILY_API_KEY)
npm test - Run all tests (Skyflow deidentification + integration tests)
npm run test:skyflow - Run Skyflow deidentification tests only
npm run test:integration - Run integration tests only

Running the Server

npx tavily-mcp - Run the server (requires TAVILY_API_KEY environment variable)
node build/index.js - Run compiled server directly

With Skyflow Integration:

# Set required environment variables
export TAVILY_API_KEY=your_tavily_key
export SKYFLOW_VAULT_ID=your_vault_id
export SKYFLOW_CLUSTER_ID=your_cluster_id
export SKYFLOW_API_KEY=your_skyflow_key

# Run server with deidentification enabled
npx tavily-mcp

Architecture

Core Components

TavilyClient class (src/index.ts) - Main MCP server implementation with Skyflow integration
SkyflowClient class (src/skyflow/client.ts) - Deidentification service wrapper
Four API endpoints: search, extract, crawl, map via Tavily's REST API
Tool definitions with comprehensive input schemas for each API including deidentification options

Read the full file on GitHub · 103 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 103 lines · 1,256 tokens per session scan A 5b837a91ee48

Subscribe to this mod's changes

mcp_sample_tavily CLAUDE.md is an instructions file published in the GitHub repository SkyflowFoundry/mcp_sample_tavily (0 stars, last pushed 1y ago), licensed MIT. It adds 1,256 tokens to every session, about $0.0050 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Research

mcp_sample_tavily CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp_sample_tavily CLAUDE.mdSkyflowFoundry/mcp_sample_tavily	Instructions file	0	1y ago	MIT	A	1,256	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp_sample_tavily: Instructions file for Claude Code