> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langchain.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Connect to MCP servers

> Add tools from remote MCP servers to Managed Deep Agents.

An MCP connector adds tools from remote [Model Context Protocol (MCP)](/oss/python/deepagents/mcp) servers to a Managed Deep Agent. Managed Deep Agents creates the MCP client, loads the tools, and adds them to the agent.

<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

Declare MCP servers in a module directly under `connectors/`:

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
my-agent/
  agent.py
  connectors/
    mcp.py
```

The module must export a module-level `connector`.

## Add an MCP connector

Use `connectors.mcp` to declare one or more remote servers:

```python connectors/mcp.py theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from managed_deepagents import connectors

connector = connectors.mcp(
    mcp_servers={
        "langchainDocs": {
            "transport": "http",
            "url": "https://docs.langchain.com/mcp",
            "include_tools": ["search_docs_by_lang_chain"],
        },
    },
)
```

Managed Deep Agents supports Streamable HTTP (`"http"`) and legacy SSE (`"sse"`) transports. Stdio MCP servers are not supported. Expose a stdio server over HTTP or implement its operation as an [authored tool](/langsmith/python/managed-deep-agents-tools).

## Select tools

By default, the connector exposes every tool from each server. To expose only selected tools, set an allowlist inside that server's configuration:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{
    "transport": "http",
    "url": "https://docs.langchain.com/mcp",
    "include_tools": ["search_docs_by_lang_chain"],
}
```

To expose every tool except selected tools, replace `include_tools` with `exclude_tools`.

You can use both options together. The denylist applies after the allowlist, and the same tool cannot appear in both lists.

Selection uses raw MCP tool names before Managed Deep Agents prefixes them. Tool names are prefixed with the server name by default to avoid collisions. For example, the `search_docs_by_lang_chain` tool from the `langchainDocs` server is exposed as `langchainDocs__search_docs_by_lang_chain`.

## Configure connections

Each server accepts the following options:

| Option                                            | Description                                                                        |
| ------------------------------------------------- | ---------------------------------------------------------------------------------- |
| `transport`                                       | Required. Use `http` for Streamable HTTP or `sse` for legacy SSE.                  |
| `url`                                             | Required. The remote MCP endpoint URL.                                             |
| `headers`                                         | Static headers to send to the server, such as an authorization header.             |
| `include_tools` / `includeTools`                  | Raw MCP tool names to expose.                                                      |
| `exclude_tools` / `excludeTools`                  | Raw MCP tool names to hide.                                                        |
| `default_tool_timeout` / `defaultToolTimeout`     | Timeout for each tool call, in seconds for Python and milliseconds for TypeScript. |
| `automatic_sse_fallback` / `automaticSSEFallback` | For HTTP, allow the client to fall back to SSE.                                    |
| `reconnect`                                       | For SSE, configure reconnection behavior.                                          |

The connector also accepts these options:

| Option                                                               | Default | Description                                               |
| -------------------------------------------------------------------- | ------- | --------------------------------------------------------- |
| `prefix_tool_name_with_server_name` / `prefixToolNameWithServerName` | `true`  | Prefix each tool with `{server}__`.                       |
| `throw_on_load_error` / `throwOnLoadError`                           | `true`  | Fail loading instead of starting with a partial tool set. |

If a server requires credentials, read them from environment variables and pass them through `headers`. Keep local values in `.env`; Managed Deep Agents forwards eligible values as deployment secrets. Do not hard-code credentials in the connector declaration.

## Distinguish connectors from other capabilities

* **MCP connectors** add tools hosted by remote MCP servers.
* **[Authored tools](/langsmith/python/managed-deep-agents-tools)** implement application logic in the project and are passed through the agent definition.
* **[Channels](/langsmith/python/managed-deep-agents-channels)** receive external messages that start agent runs and deliver responses.

***

<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-mcp-connectors.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>