Connect AI agents to the Tavily MCP server

Vendor MCP

The Tavily MCP connector routes your AI agent's tool calls to Tavily's own MCP server through Scalekit. Each user signs in to Tavily once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 5 tools.

Tools: 5
What they doRead · write · destructive: 5 · 0 · 05 read0 write0 destructive
Users sign in with: OAuth
OAuth app: Scalekit's or your own

What you can do

Search the web: find current information and return snippets with their source URLs
Extract page content: pull the content of one or more URLs as markdown or plain text
Crawl and map sites: crawl a website from a starting URL and map its URL structure
Research a topic: run multi-source research on a question or topic

Setup

Install the SDK
- Node.js
- Python
Terminal window
npm install @scalekit-sdk/node dotenv
Terminal window
pip install scalekit-sdk-python python-dotenv
Set your credentials
Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.
.env
```
SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
SCALEKIT_CLIENT_ID=<your-client-id>
SCALEKIT_CLIENT_SECRET=<your-client-secret>
```
Create the Tavily MCP connection
In AgentKit > Connections, create a Tavily MCP connection. The name you give it is the connection_name your code passes. See Configure connections.
Scalekit credentials are available for Tavily MCP server, so you don't need to register an OAuth app.

Authorize a user and make your first call

Node.js
Python

1
import { ScalekitClient } from '@scalekit-sdk/node'
2
import 'dotenv/config'
3
import { createInterface } from 'node:readline/promises'
4

5
const scalekit = new ScalekitClient(
6
  process.env.SCALEKIT_ENVIRONMENT_URL,
7
  process.env.SCALEKIT_CLIENT_ID,
8
  process.env.SCALEKIT_CLIENT_SECRET,
9
)
10
const actions = scalekit.actions
11

12
const connector = 'tavilymcp'
13
const identifier = 'user_123'
14

15
// Generate an authorization link for the user
16
const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
17
console.log('Authorize Tavily MCP:', link)
18
const rl = createInterface({ input: process.stdin, output: process.stdout })
19
await rl.question('Press Enter after authorizing...')
20
rl.close()
21

22
// Make your first call
23
const result = await actions.executeTool({
24
  connector,
25
  identifier,
26
  toolName: 'tavilymcp_tavily_crawl',
27
  toolInput: { url: 'https://example.com/url' },
28
})
29
console.log(result)

npx tsx quickstart.mts

1
import os
2
from scalekit import ScalekitClient
3
from dotenv import load_dotenv
4
load_dotenv()
5

6
scalekit_client = ScalekitClient(
7
    env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
8
    client_id=os.getenv("SCALEKIT_CLIENT_ID"),
9
    client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
10
)
11
actions = scalekit_client.actions
12

13
connection_name = "tavilymcp"
14
identifier = "user_123"
15

16
# Generate an authorization link for the user
17
link_response = actions.get_authorization_link(
18
    connection_name=connection_name,
19
    identifier=identifier,
20
)
21
print("Authorize Tavily MCP:", link_response.link)
22
input("Press Enter after authorizing...")
23

24
# Make your first call
25
result = actions.execute_tool(
26
    tool_input={"url":"https://example.com/url"},
27
    tool_name="tavilymcp_tavily_crawl",
28
    connection_name=connection_name,
29
    identifier=identifier,
30
)
31
print(result)

python quickstart.py

Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool

Try in Playground Request a tool

tavilymcp_tavily_crawlCrawl a website from a starting URL and extract page content with configurable depth and breadth.Read-only
Tavily Crawl
Crawl a website from a starting URL and extract page content with configurable depth and breadth.
Inputs
urlstringrequired
The root URL to begin the crawl
allow_externalboolean
Whether to return external links in the final responsedefault true
extract_depthstring
Advanced extraction retrieves more data, including tables and embedded content, with higher success but may increase latencyone of basicadvanceddefault basic
formatstring
The format of the extracted web page content. markdown returns content in markdown format. text returns plain text and may increase latency.one of markdowntextdefault markdown
include_faviconboolean
Whether to include the favicon URL for each resultdefault false
instructionsstring
Natural language instructions for the crawler. Instructions specify which types of pages the crawler should return.default
limitinteger
Total number of links the crawler will process before stoppingdefault 50
max_breadthinteger
Max number of links to follow per level of the tree (i.e., per page)default 20
max_depthinteger
Max depth of the crawl. Defines how far from the base URL the crawler can explore.default 1
select_domainsarray
Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\.example\.com$)
select_pathsarray
Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)
tavilymcp_tavily_extractExtract raw content from one or more URLs in markdown or plain text format.Read-only
Tavily Extract
Extract raw content from one or more URLs in markdown or plain text format.
Inputs
urlsarrayrequired
List of URLs to extract content from
extract_depthstring
Use 'advanced' for LinkedIn, protected sites, or tables/embedded contentone of basicadvanceddefault basic
formatstring
Output formatone of markdowntextdefault markdown
include_faviconboolean
Include favicon URLsdefault false
include_imagesboolean
Include images from pagesdefault false
querystring
Query to rerank content chunks by relevancedefault
tavilymcp_tavily_mapMap a website's URL structure starting from a base URL.Read-only
Tavily Map
Map a website's URL structure starting from a base URL.
Inputs
urlstringrequired
The root URL to begin the mapping
allow_externalboolean
Whether to return external links in the final responsedefault true
instructionsstring
Natural language instructions for the crawlerdefault
limitinteger
Total number of links the crawler will process before stoppingdefault 50
max_breadthinteger
Max number of links to follow per level of the tree (i.e., per page)default 20
max_depthinteger
Max depth of the mapping. Defines how far from the base URL the crawler can exploredefault 1
select_domainsarray
Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\.example\.com$)
select_pathsarray
Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)
tavilymcp_tavily_researchRun comprehensive multi-source research on a topic or question.Read-only
Tavily Research
Run comprehensive multi-source research on a topic or question.
Inputs
inputstringrequired
A comprehensive description of the research task
modelstring
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 subtopicsone of miniproautodefault auto
tavilymcp_tavily_searchSearch the web for current information and return snippets with source URLs.Read-only
Tavily Search
Search the web for current information and return snippets with source URLs.
Inputs
querystringrequired
Search query
countrystring
Boost search results from a specific country. Must be a full country name (e.g., 'United States', 'Japan', 'Germany'). ISO country codes (e.g., 'us', 'jp') are not supported. Available only if topic is general. See https://docs.tavily.com/documentation/api-reference/search for the full list of supported countries.default
end_datestring
Will return all results before the specified end date. Required to be written in the format YYYY-MM-DDdefault
exact_matchstring
Only return results containing the exact phrase(s) in quotes in your query
exclude_domainsarray
List of domains to specifically exclude, if the user asks to exclude a domain set this to the domain of the site
include_domainsarray
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
include_faviconboolean
Whether to include the favicon URL for each resultdefault false
include_image_descriptionsboolean
Include a list of query-related images and their descriptions in the responsedefault false
include_imagesboolean
Include a list of query-related images in the responsedefault false
include_raw_contentboolean
Include the cleaned and parsed HTML content of each search resultdefault false
max_resultsinteger
The maximum number of search results to returndefault 5
search_depthstring
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 elseone of basicadvancedfastultra-fastdefault basic
start_datestring
Will return all results after the specified start date. Required to be written in the format YYYY-MM-DD.default
time_rangestring
The time range back from the current date to include in the search results
topicstring
Search category. Use 'general' for almost all searches, including current events and requests that combine news with other information. Use 'news' only when the user explicitly asks for news, headlines, or news coverage.one of generalnewsdefault general

Connect AI agents to the Tavily MCP server

What you can do

Setup

Install the SDK

Set your credentials

Create the Tavily MCP connection

Authorize a user and make your first call

Tools

Call it

Returns

Tavily Crawl

Inputs

Tavily Extract

Inputs

Tavily Map

Inputs

Tavily Research

Inputs

Tavily Search

Inputs

What you can do

Setup

Install the SDK

Set your credentials

Create the Tavily MCP connection

Authorize a user and make your first call

Tools

Call it

Returns

Tavily Crawl

Inputs

Tavily Extract

Inputs

Tavily Map

Inputs

Tavily Research

Inputs

Tavily Search

Inputs

Related: other Search connectors