Overview
The Tavily MCP Server is a lightweight, production ready server that brings live web capabilities search, crawling, and structured data extraction to any AI assistant through the Model Context Protocol (MCP). Once deployed, MCP compatible clients like Claude, Cursor, or custom LLM agents can issue natural language requests that trigger real time search, extraction, and crawling workflows. Results are returned as clean, structured context: summaries, extracted data, metadata, and more, ready to be injected directly as context for AI agents. Once deployed, MCP compatible clients, such as Claude, Cursor, or custom LLM agents, can issue natural language requests that trigger real time search, extraction, and crawling workflows. Results are returned as clean, structured context: summaries, extracted data, metadata, and more. Ready to be injected directly into the models reasoning loop. Built for easy integration, Tavily MCP empowers AI developers to securely, scalably, and with minimal overhead infuse external web knowledge into their agents.
Highlights
- /search : Real Time, High Precision Web Search: Query the live web using natural language to retrieve relevance ranked results with structured summaries and URLs. Designed for LLM and agent consumption, Tavily returns smart content snippets ideal for immediate ingestion, and can extract full page content in the same call, enabling both discovery and extraction in a single step. Results can be customized with filters such as time range, domain, and result count.
- /extract : Structure Aware Content Extraction: Retrieve full page content from up to 20 URLs in a single call. Extracted data is returned as clean text or markdown, ready for downstream use in summarization, Q&A, or embeddings. Advanced mode enables deeper parsing of dynamic pages, embedded media, and structured elements like tables for higher accuracy and coverage.
- /crawl : Intelligent Web Crawling: Intelligently navigate websites using natural language instructions to extract meaningful content across a website starting from a seed URL, interpret structure, and build sitemaps. Handle authentication and access constraints for scalable, compliant crawling. /map : Intelligent Site Mapping: Intelligently scan a website to surface all accessible URLs without loading content. Ideal for link discovery and when preparing inputs for bulk extraction or crawling.
Details
Unlock automation with AI agent solutions

Features and programs
Financing for AWS Marketplace purchases
Pricing
Vendor refund policy
For assistance, please contact support@tavily.com .
Custom pricing options
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Tavily MCP v0
- Amazon Bedrock AgentCore - Preview
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Tavily MCP v0.1.2
Additional details
Usage instructions
Tavily MCP Initialization Guide
This guide walks you through initializing the Tavily MCP (Model Context Protocol).
Upgrade AWS CLI
Ensure the AWS CLI is installed and updated to the latest version. Follow the installation guide here: https://docs.aws.amazon.com/cli/latest/userguide/getting-started-install.htmlÂ
Prepare Configuration Fields
Replace the following placeholders in the command seen in step 2:
-
<AGENT_NAME> - Any name you wish
-
<AGENT_DESCRIPTION> - Any description you wish
-
<AGENT_ROLE_ARN> - An IAM role ARN with the required permissions (see below)
-
<ENVIRONMENT_VARIABLE> - Set to your TAVILY_API_KEY You can get a free API key by signing up at tavily.com replace
--environment-variables '{ "<ENVIRONMENT_VARIABLE>": "<VALUE>" }' with
--environment-variables '{ "TAVILY_API_KEY": "<your-tavily-api-key>" }'
IAM Role Trust Policy
Create/add an IAM role ARN with the below permissions.
- Select Custom trust policy
- Create a custom trust policy to enable others to perform actions in this account.
- Replace the JSON with the below
From your terminal make sure to run aws configure and add the access keys associted to the account you make your IAM role with.
Invocation
Once you execute the command in step 2, you will get the following output
{ "agentRuntimeArn": "...........................", "workloadIdentityDetails": { "workloadIdentityArn": ".................." }, "agentRuntimeId": "...............................", "agentRuntimeVersion": "..", "createdAt": "...........................................", "status": ".................................................." }You need to replace the <AGENT_RUNTIME_ARN> in Step 3: Invoke agent runtime with the output from step 2.
List of Payloads:
- '{"jsonrpc": "2.0", "id": 1, "method": "tools/list"}'
- '{ "jsonrpc": "2.0", "id": "1", "method": "tools/call", "params": { "name": "tavily_search", "arguments": { "query": "latest AI news", "max_results": 10 } } }'
- '{ "jsonrpc": "2.0", "id": "1", "method": "tools/call", "params": { "name": "tavily_extract", "arguments": { "urls": ["<www.tavily.com >"]} } }'
- '{ "jsonrpc": "2.0", "id": "1", "method": "tools/call", "params": { "name": "tavily_crawl", "arguments": { "url": "<www.tavily.com >"} } }'
- '{ "jsonrpc": "2.0", "id": "1", "method": "tools/call", "params": { "name": "tavily_map", "arguments": { "url": "<www.tavily.com >"} } }'
For more details on the tool arguments, visit https://docs.tavily.com/documentation/api-reference/endpoint/searchÂ
Support
Vendor support
For assistance, please contact support@tavily.com .
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.