serverscom
MCP (Model Context Protocol) server for managing Servers.com dedicated server infrastructure.
claude mcp add --transport stdio serverscom-serverscom-mcp npx -y @servers.com/mcp \ --env SC_TOKEN="your-api-token"
How to use
The serverscom MCP server enables AI assistants to interact directly with the Servers.com API to manage dedicated server infrastructure. It exposes a wide range of tools for operations such as querying server details, managing SSH keys, configuring networks, handling L2 segments, provisioning Remote Block Storage, reinstalling operating systems, and more. To use it, run the MCP server with your Servers.com API token (supplied via the SC_TOKEN environment variable) and connect your AI assistant to issue commands against the available tools. The toolset is organized into categories and documented in TOOLS.md, with asynchronous operations returning status fields that you can poll to determine progress.
You can start the MCP server with: npx @servers.com/mcp --token your-api-token (or via SC_TOKEN=your-api-token npx @servers.com/mcp). The environment variable SC_TOKEN is required by default, and you may override the API endpoint with SC_ENDPOINT if you need to target a different Servers.com instance. Once running, the assistant can invoke tools to manage servers, networks, SSH keys, reinstallation, storage, and more, using the full API surface exposed by the MCP server.
How to install
Prerequisites:
- Node.js and npm (to run npx commands).
- Access token for the Servers.com API.
Installation steps:
- Ensure Node.js is installed. If not, download from https://nodejs.org/ and install.
- Install and run the MCP server via npx, providing your token:
# Quick start (token in env):
SC_TOKEN=your-api-token npx @servers.com/mcp
# Or explicitly pass the token as an argument:
npx @servers.com/mcp --token your-api-token
- If you need to override the API endpoint, set SC_ENDPOINT before launching:
SC_TOKEN=your-api-token SC_ENDPOINT=https://api.servers.com/v1 npx @servers.com/mcp
- Verify the server starts and the CLI outputs information about available tools and commands. Connect your AI assistant to the MCP endpoint and begin issuing tool invocations.
Additional notes
Tips and considerations:
- The MCP server exposes 73 tools across 6 categories; refer to TOOLS.md for the full reference.
- Some operations are asynchronous. After invoking a change, poll the relevant status field (e.g., list_dedicated_server_features, get_dedicated_server) as documented in the README to determine when the operation completes.
- Ensure SC_TOKEN has the necessary scopes/permissions for the actions you intend to perform (e.g., server read/write, SSH key management, network configuration).
- You can override the default API endpoint with SC_ENDPOINT if you’re using a private or staging Servers.com instance.
- If you encounter rate limits or authorization errors, confirm the token is valid and that the endpoint is reachable from your environment.
Related MCP Servers
trpc-agent-go
trpc-agent-go is a powerful Go framework for building intelligent agent systems using large language models (LLMs) and tools.
station
Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.
tiger-cli
Tiger CLI is the command-line interface for Tiger Cloud. It includes an MCP server for helping coding agents write production-level Postgres code.
gopls
MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.
kubernetes
A Model Context Protocol (MCP) server for the Kubernetes API.
gcp-cost
💰 An MCP server that enables AI assistants to estimate Google Cloud costs, powered by Cloud Billing Catalog API and built with Genkit for Go