CONNECT APP

Build with Tavily

Tavily is the leading search engine designed for LLMs and tailored for RAG purposes.

Artificial Intelligence (AI)

API key

Visit Tavily ↗ Start building

MCP

Give your agent Tavily tools

Every Tavily action is exposed as an MCP tool on Pipedream's remote server. Point a client at it with your end user's ID and Connect resolves that user's Tavily account for each tool call — you store no tokens.

Pipedream Connect

// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": "{project_id}",
        "x-pd-environment": "production",
        "x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
        "x-pd-app-slug": "tavily",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// e.g. run Send Query:
const result = await mcp.callTool({
  name: "tavily-send-query",
  arguments: {
    query: "Query",
    searchDepth: "Search Depth",
  },
})

# access_token: mint a short-lived token with the Connect SDK — see the MCP guide
headers = {
    "Authorization": f"Bearer {access_token}",
    "x-pd-project-id": "{project_id}",
    "x-pd-environment": "production",
    "x-pd-external-user-id": "{external_user_id}",  # any stable ID for this user in your system
    "x-pd-app-slug": "tavily",
}

async with streamablehttp_client("https://remote.mcp.pipedream.net/v3", headers=headers) as (read, write, _):
    async with ClientSession(read, write) as session:
        await session.initialize()
        tools = await session.list_tools()

        # e.g. run Send Query:
        result = await session.call_tool("tavily-send-query", {
            "query": "Query",
            "searchDepth": "Search Depth",
        })

MCP guide →

API PROXY

Call the Tavily API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Tavily API with the connected user's credentials attached. You store no tokens and write no refresh logic.

Pipedream Connect

const resp = await pd.proxy.get({
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  accountId: "apn_xxxxxxx",
  url: "https://api.tavily.com/search",
})

// Any allowed Tavily endpoint works here. Pipedream attaches the
// connected account's credentials to the outgoing request.

# The path segment is the target URL, URL-safe base64 encoded:
# https://api.tavily.com/search

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkudGF2aWx5LmNvbS9zZWFyY2g?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
  -H "Authorization: Bearer {access_token}" \
  -H "x-pd-environment: production"

API proxy guide →

SDK

Run Tavily actions from your backend

Connect a user's Tavily account once, then run Send Query on their behalf from your own code — TypeScript, Python, or plain HTTP.

Pipedream Connect

import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "tavily-send-query",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    tavily: { authProvisionId: "apn_xxxxxxx" },
    query: "Query",
    searchDepth: "Search Depth",
  },
})

from pipedream import Pipedream

pd = Pipedream(
    client_id="{oauth_client_id}",
    client_secret="{oauth_client_secret}",
    project_id="{project_id}",
    project_environment="production",
)

result = pd.actions.run(
    id="tavily-send-query",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "tavily": {"authProvisionId": "apn_xxxxxxx"},
        "query": "Query",
        "searchDepth": "Search Depth",
    },
)

curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
  -H "Content-Type: application/json" \
  -H "X-PD-Environment: production" \
  -H "Authorization: Bearer {access_token}" \
  -d '{
    "external_user_id": "{external_user_id}",
    "id": "tavily-send-query",
    "configured_props": {
      "tavily": { "authProvisionId": "apn_xxxxxxx" },
      "query": "Query",
      "searchDepth": "Search Depth"
    }
  }'