# MCP Server

The Archera MCP Server connects your AI assistant to your Archera account using the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction), giving it direct access to your cloud commitments, cost data, and optimization recommendations. Archera hosts and manages the remote MCP server with OAuth authentication — there's nothing to install.

**MCP server URL:** `https://architect.archera.ai/mcp`

***

## Set up your client

Select your client below for setup instructions. All clients connect to `https://architect.archera.ai/mcp` and authenticate with your existing Archera login — no API keys needed.

Use `claude-production` as the `client_id` in every setup flow below.

<details>

<summary>Claude Code</summary>

Run the following command in your terminal:

```bash
claude mcp add --transport http --scope user \
  --client-id claude-code \
  --callback-port 8080 \
  architect-api https://architect.archera.ai/mcp
```

Your browser will open automatically for login. Once you approve access, the server is available in all future Claude Code sessions.

</details>

<details>

<summary>Claude Desktop</summary>

Open Claude Desktop, then go to **Claude** → **Settings** → **Developer** → **Edit Config** and add the following to your `claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "archera": {
      "url": "https://architect.archera.ai/mcp"
    }
  }
}
```

Restart Claude Desktop to apply the changes. You'll be prompted to log in with your Archera account on first use.

If Claude Desktop prompts for `client_id`, enter `claude-production`.

</details>

<details>

<summary>Claude.ai</summary>

1. Go to **Settings** → **Integrations** → **Add More**
2. Enter the server URL: `https://architect.archera.ai/mcp`
3. Specify the client\_id: `claude-production`
4. Follow the login prompt to connect your Archera account

</details>

<details>

<summary>Cursor</summary>

Go to **Cursor** → **Settings** → **Cursor Settings** → **MCP** and add the server. You can also edit your `mcp.json` directly:

```json
{
  "mcpServers": {
    "archera": {
      "url": "https://architect.archera.ai/mcp"
    }
  }
}
```

If Cursor prompts for `client_id`, enter `cursor-production`.

</details>

<details>

<summary>VS Code (GitHub Copilot)</summary>

Open the Command Palette with `CMD+Shift+P`, select **MCP: Add Server**, and enter:

```
https://architect.archera.ai/mcp
```

If VS Code prompts for `client_id`, enter `github-copilot-production`.

</details>

<details>

<summary>Windsurf</summary>

Open Cascade with `CMD+L`, select **Configure MCP**, and add the server URL:

```
https://architect.archera.ai/mcp
```

If Windsurf prompts for `client_id`, enter `windsurf-production`.

</details>

<details>

<summary>Warp</summary>

Go to **Settings** → **MCP Servers** → **+ Add** and select **Streamable HTTP or SSE Server (URL)**. Enter the following:

```json
{
  "archera": {
    "url": "https://architect.archera.ai/mcp"
  }
}
```

Warp supports OAuth one-click installation and will open a browser window to authenticate.

If Warp prompts for `client_id`, enter `warp-production`.

</details>

<details>

<summary>Amp</summary>

**VS Code Extension:** Add the server via the Amp VS Code extension settings, or update your `settings.json`:

```json
"amp.mcpServers": {
  "archera": {
    "url": "https://architect.archera.ai/mcp"
  }
}
```

**Amp CLI:**

```bash
amp mcp add archera --url https://architect.archera.ai/mcp
```

If Amp prompts for `client_id`, enter `amp-production`.

</details>

<details>

<summary>Other clients</summary>

The Archera MCP server works with any client that supports OAuth and Streamable HTTP. Use `https://architect.archera.ai/mcp` as the server URL in your client's MCP configuration.

To register a new client with `client_id` and callback URL, you would need to reach out to Archera for a one-time registration.

</details>

***

## Example prompts

Once connected, try these prompts to get started:

**Visibility**

* What commitment plans do I have active right now?
* Show me my Reserved Instance and Savings Plan coverage across all AWS accounts
* Which of my commitments are expiring in the next 60 days?
* What's my current on-demand spend versus committed spend?

**Analysis**

* Where am I most over- or under-committed?
* Show me EC2 utilization and coverage for the past 30 days
* Which accounts have the lowest commitment coverage?
* Are there any unused reservations I should be aware of?

**Optimization**

* What savings opportunities does Archera see for my environment?
* Generate a commitment plan recommendation for my production AWS account
* How much could I save by converting my top on-demand spend to Savings Plans?
* Compare my commitment efficiency this quarter versus last quarter

***

## Available tools

The Archera MCP server gives your AI assistant access to:

**Commitment management** View and manage your full portfolio of Reserved Instances, Savings Plans, and Archera Insured Commitments across all linked cloud accounts and services. Check status, term lengths, payment options, and renewal dates.

**Coverage & utilization** Analyze how well your existing commitments are being used. Identify underutilized reservations, coverage gaps by service or region, and accounts where on-demand spend is higher than it should be.

**Recommendations & planning** Generate commitment plans and savings recommendations based on your actual usage patterns. Model different scenarios — term length, payment type, coverage targets — to find the right balance of savings and flexibility for your organization.

**Spend & forecasting** Query historical cost data broken down by account, service, region, or commitment type. Get projected spend estimates based on current commitments and usage trends.

**Account management** View linked cloud accounts, their coverage summaries, and commitment activity across your Archera organization.

***

## Troubleshooting

**Auth not completing (Claude Code)** Make sure port 8080 is available and not blocked by a firewall or VPN. If the browser doesn't open automatically, copy the URL from the terminal and paste it manually.

**`Invalid client_id` error** Use the setup values exactly as shown above, including `client_id` set to `claude-production`. Omitting this value or using a different one will cause authentication to fail.

**Reconnecting or switching accounts** In Claude Code, type `/mcp`, select the `architect-api` server, and choose **Clear authentication**. Then re-run the setup command to trigger a fresh login.

**Missing tools or data** Ensure your Archera account has the necessary permissions and that authentication completed successfully. Try disconnecting and reconnecting the MCP server.

**Connection issues** Verify the server URL is correct: `https://architect.archera.ai/mcp`. Check that your network can reach `architect.archera.ai` and `api.archera.ai`.

For further help, contact <support@archera.ai>.