> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-opensw-1787674483-6bd21af.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Add custom tools to Managed Deep Agents

> Define authored tools for Managed Deep Agents projects.

Tools add custom capabilities to your agent.

Define LangChain tools in your project, import them into `agent.ts`, and pass them to `defineDeepAgent`.

To load tools from a remote MCP server instead, use an [MCP connector](/langsmith/javascript/managed-deep-agents-mcp-connectors).

<Note>
  Managed Deep Agents is in **public [beta](/langsmith/release-stages)** and available on [LangSmith Cloud](/langsmith/cloud) in the US region only.
</Note>

## Project structure

Keep the agent entry point at the project root and authored tools under `tools/`:

```text theme={null}
my-agent/
  agent.ts
  tools/
    customer.ts
```

## Add a tool module

```ts tools/customer.ts theme={null}
import { tool } from "langchain";
import { z } from "zod";

export const lookupCustomer = tool(
  async ({ customerId }) => `Customer ${customerId} is on the enterprise plan.`,
  {
    name: "lookup_customer",
    description: "Look up a customer record by ID.",
    schema: z.object({
      customerId: z.string().describe("Customer ID from the CRM."),
    }),
  },
);
```

## Attach tools to the agent

Import the tools into the project-root agent entry and pass them in the `tools` list.

```ts agent.ts theme={null}
import { defineDeepAgent } from "managed-deepagents";

import { lookupCustomer } from "./tools/customer";

export const agent = defineDeepAgent({
  name: "support-agent",
  model: "openai:gpt-5.5",
  tools: [lookupCustomer],
});
```

`mda dev` and `mda deploy` copy the project files into the compiled build.

Your imports should work the same way they do in a normal local TypeScript project.

Use clear, unique tool names to avoid collisions.

## Human-in-the-loop

Pause the agent before sensitive tool calls so a person can approve, edit, or reject them.

Set `interruptOn` in the agent definition, and optionally set `permissions` to gate tool and filesystem access.

```ts agent.ts theme={null}
import { defineDeepAgent } from "managed-deepagents";

import { lookupCustomer } from "./tools/customer";

export const agent = defineDeepAgent({
  name: "support-agent",
  model: "openai:gpt-5.5",
  tools: [lookupCustomer],
  interruptOn: {
    lookup_customer: true,
  },
});
```

The `interruptOn` field applies the same interrupt behavior as LangChain's [human-in-the-loop middleware](/oss/javascript/langchain/guardrails#human-in-the-loop).

For decision types (approve, edit, reject), conditional interrupts, and permission rules, see the Deep Agents [Human-in-the-loop](/oss/javascript/deepagents/human-in-the-loop) and [Permissions](/oss/javascript/deepagents/permissions) guides.

### Respond to an interrupt

When a run hits an interrupt, it pauses and waits for a human response before continuing.

* **During local development**, `mda dev` runs the agent in LangSmith Studio, which surfaces the interrupt so you can inspect the pending tool call and resume the run.

* **On a deployed agent**, resume the paused run through the LangGraph server API with a resume payload. See [Human-in-the-loop using server API](/langsmith/add-human-in-the-loop).

<Note>
  During public beta, Managed Deep Agents is CLI-first and programmatic invocation is not yet documented. To resume runs programmatically from your own application, contact your LangChain team.
</Note>

Human-in-the-loop needs durable thread state to pause and resume. The managed runtime owns the checkpointer, so no extra setup is required.

## Use secrets and context

Tools can read deployment secrets from environment variables. Put local values in `.env` for `mda dev`; `mda deploy` forwards non-reserved `.env` values as hosted deployment secrets.

For per-run values such as request metadata or feature flags, use the normal LangChain runtime context patterns for tools. See [how to access context from within your tools](/oss/javascript/langchain/tools#access-context).

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/langsmith/managed-deep-agents-tools.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>