Add custom middleware to Managed Deep Agents

Managed Deep Agents support the normal Deep Agents middleware configuration surface. Add LangChain middleware to defineDeepAgent to monitor tool calls, add guardrails, redact data, retry transient failures, or customize model calls.

Managed Deep Agents is in public beta and available on LangSmith Cloud in the US region only.

Project structure

Keep the agent entry point at the project root and custom middleware under middleware/:

my-agent/
  agent.ts
  middleware/
    audit.ts

The managed runtime still owns backend, store, checkpointer, memory, skills, and the system prompt. Middleware should focus on agent behavior around model calls, tool calls, and lifecycle hooks. For deeper hook, state, and context details, see custom middleware.

Use prebuilt middleware

You can use LangChain prebuilt middleware directly in the agent definition.

agent.ts

import { defineDeepAgent } from "managed-deepagents";
import { modelCallLimitMiddleware, piiMiddleware } from "langchain";

export const agent = defineDeepAgent({
  name: "support-agent",
  model: "openai:gpt-5.5",
  middleware: [
    piiMiddleware("email", { strategy: "redact", applyToInput: true }),
    modelCallLimitMiddleware({ runLimit: 50 }),
  ],
});

Middleware is the right place for cross-cutting behavior such as PII handling, rate limits, retry policies, model fallbacks, dynamic model selection, and tool-call monitoring.

Add a custom middleware module

For a more advanced option, you can also define custom middleware.

middleware/audit.ts

import { createMiddleware } from "langchain";

export const logToolCalls = createMiddleware({
  name: "LogToolCalls",
  wrapToolCall: async (request, handler) => {
    console.log(`Calling tool: ${request.toolCall.name}`);
    const result = await handler(request);
    console.log(`Finished tool: ${request.toolCall.name}`);
    return result;
  },
});

Import the middleware into the project-root agent entry and pass it in the middleware list.

agent.ts

import { defineDeepAgent } from "managed-deepagents";

import { logToolCalls } from "./middleware/audit";

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

mda dev and mda deploy copy the project files into the compiled build. Your middleware imports should work the same way they do in a normal local TypeScript project.

Use runtime context

Middleware can read per-run context through the normal LangChain runtime APIs. Use context for user IDs, organization IDs, feature flags, request metadata, or credentials that should not be part of the model prompt by default. For examples, see Custom middleware.

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

Edit this page on GitHub or file an issue.

Get started

Agent definition

Build and deploy

Add custom middleware to Managed Deep Agents

Project structure

Use prebuilt middleware

Add a custom middleware module

Use runtime context

​Project structure

​Use prebuilt middleware

​Add a custom middleware module

​Use runtime context

Project structure

Use prebuilt middleware

Add a custom middleware module

Use runtime context