Tavily map integration

Integrate with the Tavily map tool using LangChain Python.

Tavily is a search engine built specifically for AI agents (LLMs), delivering real-time, accurate, and factual results at speed. Tavily offers a Map endpoint that traverses websites and returns a list of discovered URLs without extracting page content, which is ideal for understanding site structure or locating specific pages on a large site.

Overview

Integration details

Class	Package	Serializable	JS support	Version
TavilyMap	langchain-tavily	✅	✅

Tool features

Returns artifact	Native async	Return data	Pricing
❌	✅	list of discovered URLs	1,000 free credits / month

Setup

The integration lives in the langchain-tavily package.

pip install -qU langchain-tavily

Credentials

We also need to set our Tavily API key. You can get an API key by visiting this site and creating an account.

import getpass
import os

if not os.environ.get("TAVILY_API_KEY"):
    os.environ["TAVILY_API_KEY"] = getpass.getpass("Tavily API key:\n")

Instantiation

The tool accepts the following parameters during instantiation:

• max_depth (optional, int): Maximum number of hops from the starting URL. Default is 1.
• max_breadth (optional, int): Maximum number of URLs returned per level. Default is 20.
• limit (optional, int): Maximum total number of URLs to return. Default is 50.
• instructions (optional, str): Natural-language instructions that guide the map traversal.
• select_paths (optional, list[str]): Only include URLs containing these path regexes.
• select_domains (optional, list[str]): Only include URLs from these domain regexes.
• exclude_paths (optional, list[str]): Skip URLs containing these path regexes.
• exclude_domains (optional, list[str]): Skip URLs from these domain regexes.
• allow_external (optional, bool): Allow the map to follow external links.

For a comprehensive overview of the available parameters, refer to the Tavily Map API documentation.

from langchain_tavily import TavilyMap

tool = TavilyMap(
    max_depth=1,
    max_breadth=20,
    limit=50,
    # allow_external=False,
)

Invocation

Invoke directly with args

The Tavily map tool accepts the following arguments during invocation:

• url (required): The base URL to start mapping from.
• The following arguments can also be set during invocation: instructions, select_paths, select_domains, exclude_paths, exclude_domains, allow_external.

NOTE: The optional arguments are available for agents to dynamically set. If you set an argument during instantiation and then invoke the tool with a different value, the tool will use the value you passed during invocation.

tool.invoke({"url": "https://docs.tavily.com"})

{
  "base_url": "https://docs.tavily.com",
  "results": [
    "https://docs.tavily.com/",
    "https://docs.tavily.com/changelog",
    "https://docs.tavily.com/welcome",
    "https://docs.tavily.com/documentation/mcp",
    "https://docs.tavily.com/documentation/about",
  ],
  "response_time": 0.37
}

Invoke with ToolCall

We can also invoke the tool with a model-generated ToolCall, in which case a ToolMessage will be returned:

model_generated_tool_call = {
    "args": {"url": "https://docs.tavily.com", "instructions": "Find API reference pages"},
    "id": "1",
    "name": "tavily_map",
    "type": "tool_call",
}
tool_msg = tool.invoke(model_generated_tool_call)

print(tool_msg.content[:400])

Use within an agent

We can use the map tool directly with an agent by binding it to the model. The agent can then dynamically set instructions and filters to discover the URLs it needs.

if not os.environ.get("OPENAI_API_KEY"):
    os.environ["OPENAI_API_KEY"] = getpass.getpass("OPENAI_API_KEY:\n")

from langchain.chat_models import init_chat_model

model = init_chat_model(model="gpt-5.5", model_provider="openai", temperature=0)

from langchain_tavily import TavilyMap
from langchain.agents import create_agent


tavily_map_tool = TavilyMap(max_depth=2, max_breadth=20, limit=30)

agent = create_agent(model, [tavily_map_tool])

user_input = "Map https://docs.tavily.com and list URLs that look like API reference pages."

stream = agent.stream_events({"messages": user_input}, version="v3")
for snapshot in stream.values:
    snapshot["messages"][-1].pretty_print()

---

API reference

For detailed documentation of all Tavily Map API features and configurations head to the API reference: docs.tavily.com/documentation/api-reference/endpoint/map

---

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.