Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion content/en/bits_ai/mcp_server/_index.md
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ The Datadog MCP Server supports _toolsets_, which allow you to use only the tool
- `software-delivery`: Tools for interacting with Software Delivery ([CI Visibility][21] and [Test Optimization][24])
- `synthetics`: Tools for interacting with Datadog [Synthetic tests][20]

To use a toolset, include the `toolsets` query parameter in the endpoint URL when connecting to the MCP Server ([remote authentication][27] only).
To use a toolset, include the `toolsets` query parameter in the endpoint URL when connecting to the MCP Server (not available with [local binary authentication][39]).

{{< site-region region="us,us3,us5,eu,ap1,ap2" >}}
For example, based on your selected [Datadog site][36] ({{< region-param key="dd_site_name" >}}):
Expand Down Expand Up @@ -774,3 +774,4 @@ The Datadog MCP Server is under significant development. Use [this feedback form
[36]: /getting_started/site/#navigate-the-datadog-documentation-by-site
[37]: https://help.datadoghq.com/hc/en-us/requests/new
[38]: /service_management/case_management/
[39]: /bits_ai/mcp_server/setup#local-binary-authentication
110 changes: 44 additions & 66 deletions content/en/bits_ai/mcp_server/setup.md
Original file line number Diff line number Diff line change
Expand Up @@ -45,12 +45,10 @@ To install the extension:

{{% tab "Claude Code" %}}

You can connect Claude Code to the Datadog MCP Server using remote authentication (HTTP) or local binary authentication (stdio).

### Remote authentication
Point your AI agent to the MCP Server endpoint for your regional [Datadog site][1].

{{< site-region region="us,us3,us5,eu,ap1,ap2" >}}
Point your AI agent to the MCP Server endpoint for your regional [Datadog site][1]. For example, the endpoint for your selected site ({{< region-param key="dd_site_name" >}}) is: <code>{{< region-param key="mcp_server_endpoint" >}}</code>.
For example, the endpoint for your selected site ({{< region-param key="dd_site_name" >}}) is: <code>{{< region-param key="mcp_server_endpoint" >}}</code>.

* **Command line**: Run:
<pre><code>claude mcp add --transport http datadog-mcp {{< region-param key="mcp_server_endpoint" >}}
Expand Down Expand Up @@ -78,32 +76,7 @@ Point your AI agent to the MCP Server endpoint for your regional [Datadog site][
[1]: /getting_started/site/
{{< /site-region >}}

### Local binary authentication

Use this option if remote authentication is not available. After installation, you typically do not need to update the local binary to benefit from MCP Server updates, as the tools are remote.

1. Install the Datadog MCP Server binary (macOS and Linux):
```bash
curl -sSL https://coterm.datadoghq.com/mcp-cli/install.sh | bash
```
This installs the binary to `~/.local/bin/datadog_mcp_cli`.

2. Run `datadog_mcp_cli login` manually to walk through the OAuth login flow and choose a [Datadog site][1].

3. Configure Claude Code. Add to `~/.claude.json` (replace `<USERNAME>` with your username):
```json
{
"mcpServers": {
"datadog": {
"type": "stdio",
"command": "/Users/<USERNAME>/.local/bin/datadog_mcp_cli",
"args": [],
"env": {}
}
}
}
```
Or run: `claude mcp add datadog --scope user -- ~/.local/bin/datadog_mcp_cli`
<div class="alert alert-info">If remote authentication is not available, use <a href="#local-binary-authentication">local binary authentication</a> instead.</div>

[1]: /getting_started/site/
{{% /tab %}}
Expand Down Expand Up @@ -245,9 +218,7 @@ The [Datadog plugin][3] integrates with these agent CLIs. For an uninterrupted e

{{% tab "Other" %}}

The following clients can connect to the Datadog MCP Server: [Goose][1], [Kiro][2], [Kiro CLI][3], [Cline][4], and other MCP-compatible clients. Use **remote authentication** when your client supports it. For Cline or when remote authentication is unreliable, use **local binary authentication**.

### Remote authentication
The following clients can connect to the Datadog MCP Server: [Goose][1], [Kiro][2], [Kiro CLI][3], [Cline][4], and other MCP-compatible clients. Use these instructions for remote authentication when your client supports it. For Cline or when remote authentication is unreliable or not available, use [local binary authentication](#local-binary-authentication).

{{< site-region region="us,us3,us5,eu,ap1,ap2" >}}
Point your AI agent to the MCP Server endpoint for your regional [Datadog site][1]. For example, the endpoint for your selected site ({{< region-param key="dd_site_name" >}}) is: <code>{{< region-param key="mcp_server_endpoint" >}}</code>.
Expand Down Expand Up @@ -282,43 +253,11 @@ Point your AI agent to the MCP Server endpoint for your regional [Datadog site][
[1]: /getting_started/site/
{{< /site-region >}}

### Local binary authentication

Local authentication is recommended for Cline and when remote authentication is unreliable.

1. Install the Datadog MCP Server binary:

- macOS and Linux: Install the binary to `~/.local/bin/datadog_mcp_cli`:

```bash
curl -sSL https://coterm.datadoghq.com/mcp-cli/install.sh | bash
```

- Windows: Download the [Windows version][6].

2. Run `datadog_mcp_cli login` manually to walk through the OAuth login flow and choose a [Datadog site][5].

3. Configure your AI client to use the stdio transport with `datadog_mcp_cli` as the command. Example:
```json
{
"mcpServers": {
"datadog": {
"type": "stdio",
"command": "/Users/<USERNAME>/.local/bin/datadog_mcp_cli",
"args": [],
"env": {}
}
}
}
```
On Windows, replace the `command` path with the location of the downloaded `.exe` file (for example, `C:\Users\<USERNAME>\bin\datadog_mcp_cli.exe`).

[1]: https://github.com/block/goose
[2]: https://kiro.dev/
[3]: https://kiro.dev/cli/
[4]: https://cline.bot/
[5]: /getting_started/site/
[6]: https://coterm.datadoghq.com/mcp-cli/datadog_mcp_cli.exe

{{% /tab %}}
{{< /tabs >}}
Expand Down Expand Up @@ -363,6 +302,43 @@ For example, based on your selected [Datadog site][17] ({{< region-param key="dd

For security, use a scoped API key and application key from a [service account][13] that has only the required permissions.

### Local binary authentication

Local authentication is recommended for Cline and when remote authentication is unreliable or not available. After installation, you typically do not need to update the local binary to benefit from MCP Server updates, as the tools are remote.

{{% collapse-content title="Set up Datadog MCP Server local binary" level="h5" expanded=false id="mcp-local-binary" %}}

1. Install the Datadog MCP Server binary (macOS and Linux):
```bash
curl -sSL https://coterm.datadoghq.com/mcp-cli/install.sh | bash
```
This installs the binary to `~/.local/bin/datadog_mcp_cli`.

For Windows, download the [Windows version][20].

2. Run `datadog_mcp_cli login` manually to walk through the OAuth login flow and choose a [Datadog site][21].

3. Configure your AI client to use the stdio transport with `datadog_mcp_cli` as the command. For example (replace `<USERNAME>` with your username):
```json
{
"mcpServers": {
"datadog": {
"type": "stdio",
"command": "/Users/<USERNAME>/.local/bin/datadog_mcp_cli",
"args": [],
"env": {}
}
}
}
```

On Windows, replace the `command` path with the location of the downloaded `.exe` file (for example, `C:\Users\<USERNAME>\bin\datadog_mcp_cli.exe`).

<div class="alert alert-tip">For Claude Code, you can instead run:
<pre><code>claude mcp add datadog --scope user -- ~/.local/bin/datadog_mcp_cli</code></pre></div>

{{% /collapse-content %}}

## Test access to the MCP Server

1. Install the [MCP inspector][2], a developer tool for testing and debugging MCP servers.
Expand Down Expand Up @@ -400,4 +376,6 @@ For security, use a scoped API key and application key from a [service account][
[16]: /ide_plugins/vscode/
[17]: /getting_started/site/#navigate-the-datadog-documentation-by-site
[18]: /ide_plugins/idea/
[19]: https://claude.ai
[19]: https://claude.ai
[20]: https://coterm.datadoghq.com/mcp-cli/datadog_mcp_cli.exe
[21]: /getting_started/site/
Loading