Scale GP TypeScript MCP Server

It is generated with Stainless.

Installation

Direct invocation

You can run the MCP Server directly via npx:

export SGP_API_KEY="My API Key"
export SGP_ACCOUNT_ID="My Account ID"
export SGP_CLIENT_ENVIRONMENT="production"
npx -y scale-gp-mcp@latest

Via MCP Client

There is a partial list of existing clients at modelcontextprotocol.io. If you already have a client, consult their documentation to install the MCP server.

For clients with a configuration JSON, it might look something like this:

{
  "mcpServers": {
    "scale_gp_api": {
      "command": "npx",
      "args": ["-y", "scale-gp-mcp"],
      "env": {
        "SGP_API_KEY": "My API Key",
        "SGP_ACCOUNT_ID": "My Account ID",
        "SGP_CLIENT_ENVIRONMENT": "production"
      }
    }
  }
}

Cursor

If you use Cursor, you can install the MCP server by using the button below. You will need to set your environment variables in Cursor's mcp.json, which can be found in Cursor Settings > Tools & MCP > New MCP Server.

VS Code

If you use MCP, you can install the MCP server by clicking the link below. You will need to set your environment variables in VS Code's mcp.json, which can be found via Command Palette > MCP: Open User Configuration.

Open VS Code

Claude Code

If you use Claude Code, you can install the MCP server by running the command below in your terminal. You will need to set your environment variables in Claude Code's .claude.json, which can be found in your home directory.

claude mcp add scale_gp_mcp_api --header "x-api-key: My API Key" --transport http https://sgp-dev.stlmcp.com

Running Locally (without a Stainless API key)

If you do not have a Stainless API key, you can run both code execution and docs search locally. Local code execution requires Deno:

# macOS
brew install deno

# or via npm
npm install -g deno

Pass --code-execution-mode local and --docs-search-mode local when starting the server:

export SGP_API_KEY="My API Key"
export SGP_ACCOUNT_ID="My Account ID"
export SGP_CLIENT_ENVIRONMENT="production"
npx -y scale-gp-mcp@latest \
  --code-execution-mode local \
  --docs-search-mode local

For clients with a configuration JSON:

{
  "mcpServers": {
    "scale_gp_api": {
      "command": "npx",
      "args": [
        "-y", "scale-gp-mcp",
        "--code-execution-mode", "local",
        "--docs-search-mode", "local"
      ],
      "env": {
        "SGP_API_KEY": "My API Key",
        "SGP_ACCOUNT_ID": "My Account ID",
        "SGP_CLIENT_ENVIRONMENT": "production"
      }
    }
  }
}

For Claude Code:

claude mcp add sgp_dev --scope user \
  -e SGP_API_KEY=<api-key> \
  -e SGP_ACCOUNT_ID=<account-id> \
  -e SGP_CLIENT_ENVIRONMENT=development \
  -- npx -y scale-gp-mcp@latest \
  --code-execution-mode local \
  --docs-search-mode local

The configuration is saved to ~/.claude.json. Use --scope project instead of --scope user to scope the server to a single project.

Environment Configuration

The MCP server can target different environments by setting the SGP_CLIENT_ENVIRONMENT variable:

| Environment | Base URL | | --- | --- | | production (default) | https://api.egp.scale.com | | production-multitenant | https://api.sgp.scale.com | | staging | https://api.staging-sgp.scale.com | | development | https://api.dev-sgp.scale.com | | local | http://127.0.0.1:5003/public |

Alternatively, you can set SGP_CLIENT_BASE_URL to point at an arbitrary URL. Note that SGP_CLIENT_BASE_URL and SGP_CLIENT_ENVIRONMENT are mutually exclusive — setting both will cause an error.

Multiple Environments

To work with multiple environments simultaneously, you can configure separate MCP server entries, each with its own credentials and target environment. This is useful when you need to interact with production, staging, and development APIs side by side.

For Claude Code, add one server per environment using the CLI:

# Production
claude mcp add sgp_production \
  -e SGP_API_KEY=<prod-api-key> \
  -e SGP_ACCOUNT_ID=<prod-account-id> \
  -e SGP_CLIENT_ENVIRONMENT=production \
  -- npx -y scale-gp-mcp@latest

# Staging
claude mcp add sgp_staging \
  -e SGP_API_KEY=<staging-api-key> \
  -e SGP_ACCOUNT_ID=<staging-account-id> \
  -e SGP_CLIENT_ENVIRONMENT=staging \
  -- npx -y scale-gp-mcp@latest

# Development
claude mcp add sgp_dev \
  -e SGP_API_KEY=<dev-api-key> \
  -e SGP_ACCOUNT_ID=<dev-account-id> \
  -e SGP_CLIENT_ENVIRONMENT=development \
  -- npx -y scale-gp-mcp@latest

For Cursor, add the following to your mcp.json (Cursor Settings > Tools & MCP > New MCP Server):

{
  "mcpServers": {
    "sgp_production": {
      "command": "npx",
      "args": ["-y", "scale-gp-mcp@latest"],
      "env": {
        "SGP_API_KEY": "<prod-api-key>",
        "SGP_ACCOUNT_ID": "<prod-account-id>",
        "SGP_CLIENT_ENVIRONMENT": "production"
      }
    },
    "sgp_staging": {
      "command": "npx",
      "args": ["-y", "scale-gp-mcp@latest"],
      "env": {
        "SGP_API_KEY": "<staging-api-key>",
        "SGP_ACCOUNT_ID": "<staging-account-id>",
        "SGP_CLIENT_ENVIRONMENT": "staging"
      }
    },
    "sgp_dev": {
      "command": "npx",
      "args": ["-y", "scale-gp-mcp@latest"],
      "env": {
        "SGP_API_KEY": "<dev-api-key>",
        "SGP_ACCOUNT_ID": "<dev-account-id>",
        "SGP_CLIENT_ENVIRONMENT": "development"
      }
    }
  }
}

Each entry runs its own MCP server process. Tools from each server are namespaced by the server name (e.g., sgp_production, sgp_staging), so the client can distinguish which environment is being targeted.

Code Mode

This MCP server is built on the "Code Mode" tool scheme. In this MCP Server, your agent will write code against the TypeScript SDK, which will then be executed in an isolated sandbox. To accomplish this, the server will expose two tools to your agent:

• The first tool is a docs search tool, which can be used to generically query for documentation about your API/SDK.

• The second tool is a code tool, where the agent can write code against the TypeScript SDK. The code will be executed in a sandbox environment without web or filesystem access. Then, anything the code returns or prints will be returned to the agent as the result of the tool call.

Using this scheme, agents are capable of performing very complex tasks deterministically and repeatably.

Running remotely

Launching the client with --transport=http launches the server as a remote server using Streamable HTTP transport. The --port setting can choose the port it will run on, and the --socket setting allows it to run on a Unix socket.

Authorization can be provided via the following headers: | Header | Equivalent client option | Security scheme | | ----------- | ------------------------ | --------------- | | x-api-key | apiKey | APIKeyHeader |

A configuration JSON for this server might look like this, assuming the server is hosted at http://localhost:3000:

{
  "mcpServers": {
    "scale_gp_api": {
      "url": "http://localhost:3000",
      "headers": {
        "x-api-key": "My API Key"
      }
    }
  }
}