Built-in search powered by Parallel

Managed Deep Agents includes built-in web search powered by Parallel. Give your agent access to current information from the web to help answer questions. LangSmith manages the search infrastructure, so you can add search without hosting a service or creating a separate Parallel account or API key. The integration offers zero data retention.

Built-in search is available only on LangSmith Plus and Startup plans. Usage is free during private beta.

Before you begin

You need an existing Managed Deep Agents project, your LangSmith workspace ID, and a personal LangSmith API key for use in Studio.

Add Parallel search

To add Parallel search to your agent:

Step 1. Set your workspace ID

In your project’s .env file, set your LangSmith workspace ID:

.env

LANGSMITH_WORKSPACE_ID=YOUR_WORKSPACE_ID

Step 2. Set your LangSmith API key

In the same .env file, set a personal LangSmith API key for use in Studio:

.env

LANGSMITH_API_KEY=YOUR_LANGSMITH_API_KEY

You do not need a Parallel API key.

Step 3. Configure the search server

If the file already defines mcp, add Parallel to the existing servers map. Define mcp only once.

Python
TypeScript

Add Parallel to the servers map in tools/mcp.py.

tools/mcp.py

from managed_deepagents import define_mcp

mcp = define_mcp(
    servers={
        "Parallel": {
            "transport": "http",
            "url": "https://api.smith.langchain.com/v1/managed-tools/servers/parallel/mcp",
        },
    },
)

Add Parallel to the servers map in tools/mcp.ts.

tools/mcp.ts

import { defineMcp } from "managed-deepagents";

export const mcp = defineMcp({
  servers: {
    "Parallel": {
      transport: "http",
      url: "https://api.smith.langchain.com/v1/managed-tools/servers/parallel/mcp",
    },
  },
});

Your agent can now use Parallel search alongside its other tools.

Terms of use

Your use of this integration must comply with Parallel’s terms of service, including its restrictions on prohibited or abusive use.

Get started

Agent capabilities

Build and deploy

Built-in search powered by Parallel

Before you begin

Add Parallel search

Step 1. Set your workspace ID

Step 2. Set your LangSmith API key

Step 3. Configure the search server

Terms of use

See also

​Before you begin

​Add Parallel search

​Step 1. Set your workspace ID

​Step 2. Set your LangSmith API key

​Step 3. Configure the search server

​Terms of use

​See also

Before you begin

Add Parallel search

Step 1. Set your workspace ID

Step 2. Set your LangSmith API key

Step 3. Configure the search server

Terms of use

See also