Claude Desktop - Stackone

Overview

Claude Desktop is Anthropic’s GUI application for macOS and Windows with full MCP support for tools, resources, and prompts.

For complete Claude Desktop MCP documentation, see the official MCP quickstart.

Setup

Claude Desktop requires the mcp-remote package to connect to remote HTTP servers.

The fastest way to get your configuration is directly from the StackOne dashboard — it generates a ready-to-paste JSON block for Claude Desktop.

Get your MCP URL from the dashboard

Go to Connectors in the left nav and open the connector you want to use
Click Use in Agent in the top right
On the Use tab, click MCP Server under “Use with Agent Client”
Select a linked account from the dropdown
Choose Claude Desktop as the client
Copy the generated JSON block

The config uses a single token URL — no separate API key encoding required.

The token expires after one year. Regenerate it at any time using the refresh button in the MCP tile.

Locate Configuration File

Open Claude Desktop
Navigate to Settings → Developer
Click “Edit Config” to open the configuration file in your default editor

The config file is located at:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Claude Desktop Settings page showing Developer tab with Edit Config button highlighted

Add StackOne MCP Configuration

Paste the config from the dashboard into your claude_desktop_config.json. It looks like this:

{
  "mcpServers": {
    "gsheets": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?token={session_token}"
      ]
    }
  }
}

Use short names for easier identification: gsheets, slack, hubspot-sales. You can prefix with stackone- or s1- if you have other MCP servers, but it’s not required.

Multiple accounts example

For multiple linked accounts, add an entry for each. Get each token from the dashboard by selecting the relevant account.

Claude Desktop Connectors page showing multiple MCP servers configured for different integrations — Screenshots show 'stackone-' prefix — this is optional.

{
  "mcpServers": {
    "gsheets": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?token={google_sheets_session_token}"
      ]
    },
    "slack": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?token={slack_session_token}"
      ]
    }
  }
}

Alternative: Manual API key setup

If you prefer to use your API key and account ID directly, encode your API key first:

Terminal showing base64 encoding command and output

Then add to your config:

{
  "mcpServers": {
    "gsheets": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id={account_id}",
        "--header",
        "Authorization: Basic {base64_encoded_api_key}"
      ]
    }
  }
}

Restart Claude Desktop

Close and reopen Claude Desktop to load the new configuration.

Verify connection

After restarting, navigate to Settings → Developer to verify your servers are configured:

Claude Desktop Settings showing configured Local MCP servers

A green “running” badge indicates the server is connected. If you see “failed”, click Open Logs Folder to troubleshoot. Your servers will also appear in Settings → Connectors with a “Local Dev” tag, where you can configure tool permissions:

Claude Desktop Connectors page showing tool permissions with options to enable or require approval for each tool — Screenshots show servers with 'stackone-' prefix — this is optional.

Once connected, try prompts like:

What StackOne tools are available?

Search recent calls in Gong

You can also ask about API schemas or documentation.

For troubleshooting, see Claude Desktop’s logging capabilities in the official MCP documentation.

Programmatic integration

For programmatic integration with Anthropic’s Claude API, see the Anthropic SDK Framework Guide.

Handling large tool catalogs

If the connector exposes many actions, add the tool-mode=search_execute query parameter to the MCP URL in your config. The client then registers just two tools — search + execute — and the agent discovers actions at runtime, so the context footprint stays flat however large the catalog:

https://api.stackone.com/mcp?tool-mode=search_execute

For a token URL, append it as an extra parameter: https://api.stackone.com/mcp?token=<session_token>&tool-mode=search_execute. See Tool Discovery for how search works, its accuracy, and the other modes. For example, with API-key auth:

{
  "mcpServers": {
    "stackone-bamboohr": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?tool-mode=search_execute",
        "--header",
        "Authorization: Basic <BASE64_APIKEY_COLON>",
        "--header",
        "x-account-id: <ACCOUNT_ID>"
      ]
    }
  }
}

Optimize and secure

With your agent connected, use StackOne’s platform features to optimize performance and secure every call.

Search & Execute

Reduce context and save tokens.

Data Sync

Reduce latency and enable semantic search.

Defender

Block prompt injections before they reach your agent.

​Overview

​Setup

​Verify connection

​Programmatic integration

​Handling large tool catalogs

​Optimize and secure

Search & Execute

Data Sync

Defender

Overview

Setup

Verify connection

Programmatic integration

Handling large tool catalogs

Optimize and secure