AI-powered search API for real-time web search, extraction, and crawling optimized for AI agents.
AI-powered search API for real-time web search, extraction, and crawling optimized for AI agents. On Nagent, Tavily MCP is exposed as a fully-configurable model context protocol integration that any agent can call — 5 actions, and DCR_OAUTH authentication. No code is required to wire Tavily MCP into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Tavily MCP to automate the kinds of tasks model context protocol teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Tavily MCP into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Tavily MCP, with input parameters and output schema. Drop these into any step of an agent built in Helix.
TAVILY_MCP_TAVILY_CRAWLCrawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.
Input parameters
The root URL to begin the crawl
Total number of links the crawler will process before stopping
The format of the extracted web page content. markdown returns content in markdown format. text returns plain text and may increase latency.
Max depth of the crawl. Defines how far from the base URL the crawler can explore.
Max number of links to follow per level of the tree (i.e., per page)
Natural language instructions for the crawler. Instructions specify which types of pages the crawler should return.
Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)
Advanced extraction retrieves more data, including tables and embedded content, with higher success but may increase latency
Whether to return external links in the final response
Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\\.example\\.com$)
Whether to include the favicon URL for each result
TAVILY_MCP_TAVILY_EXTRACTExtract content from URLs. Returns raw page content in markdown or text format.
Input parameters
List of URLs to extract content from
Query to rerank content chunks by relevance
Output format
Use 'advanced' for LinkedIn, protected sites, or tables/embedded content
Include images from pages
Include favicon URLs
TAVILY_MCP_TAVILY_MAPMap a website's structure. Returns a list of URLs found starting from the base URL.
Input parameters
The root URL to begin the mapping
Total number of links the crawler will process before stopping
Max depth of the mapping. Defines how far from the base URL the crawler can explore
Max number of links to follow per level of the tree (i.e., per page)
Natural language instructions for the crawler
Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)
Whether to return external links in the final response
Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\\.example\\.com$)
TAVILY_MCP_TAVILY_RESEARCHPerform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources, including web pages, documents, and other resources, to answer a question or complete a task. Returns a detailed response based on the research findings.
Input parameters
A comprehensive description of the research task
Defines the degree of depth of the research. 'mini' is good for narrow tasks with few subtopics. 'pro' is good for broad tasks with many subtopics
TAVILY_MCP_TAVILY_SEARCHSearch the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.
Input parameters
Search query
The category of the search. This will determine which of our agents will be used for the search
Boost search results from a specific country. This will prioritize content from the selected country in the search results. Available only if topic is general.
Will return all results before the specified end date. Required to be written in the format YYYY-MM-DD
Will return all results after the specified start date. Required to be written in the format YYYY-MM-DD.
The time range back from the current date to include in the search results
The maximum number of search results to return
The 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
Include a list of query-related images in the response
List of domains to specifically exclude, if the user asks to exclude a domain set this to the domain of the site
A 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
Whether to include the favicon URL for each result
Include the cleaned and parsed HTML content of each search result
Include a list of query-related images and their descriptions in the response
No publicly available marketplace agent is found using this tool yet. There are 84 agents privately built on Nagent that already use Tavily MCP.
Build on Nagent
Connect Tavily MCP to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Tavily MCP, and click "Connect Now." You'll authenticate with DCR_OAUTH — Nagent handles credential storage and refresh automatically. Once connected, Tavily MCP is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Tavily MCP is connected, you configure its 5 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Tavily MCP steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Tavily MCP event fires, the agent kicks off automatically.
Every Tavily MCP action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Tavily MCP ships with 5 pre-built model context protocol actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Tavily MCP together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Tavily MCP-based workflows tailored to your business.