Skip to main content
Glama
komer3

Linode MCP Server

by komer3

Linode MCP Server

PyPI version License: MIT

A Model Context Protocol (MCP) server for interacting with Linode's API to manage cloud resources. This package enables Large Language Models (LLMs) like Claude to manage Linode instances through a standardized interface.

Features

  • List Linode regions, instance types, and instances

  • Create, view details, delete, and reboot Linode instances

  • Secure and easy-to-use interface for LLMs to manage Linode resources

  • Fully compatible with MCP-enabled AI assistants like Claude

Related MCP server: Hetzner Cloud MCP Server

Installation and Configuration

Set your Linode API key as an environment variable:

export LINODE_API_KEY=your_api_key_here

Or use a .env file in the project directory:

LINODE_API_KEY=your_api_key_here

You can generate an API key from the Linode Cloud Manager.

pip install linode-mcp

Using uv

uvx pip install linode-mcp
uvx linode-mcp --api-key $LINODE_API_KEY

From Source

# Clone the repository
git clone https://github.com/yourusername/linode-mcp.git
cd linode-mcp

# Install the package in development mode
./scripts/install.sh

Usage

As a Command Line Tool

# Run with default settings
linode-mcp

# Enable debug logging
linode-mcp --debug

# Specify API key on command line
linode-mcp --api-key your_api_key_here

With Claude for Desktop

  1. Install the package:

    pip install linode-mcp
  2. Manually edit your Claude Desktop configuration file:

    • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json

    • Windows: %APPDATA%\Claude\claude_desktop_config.json

    {
      "mcpServers": {
        "linode": {
          "command": "linode-mcp",
          "args": ["--api-key", "your_api_key_here"]
        }
      }
    }
  3. Restart Claude for Desktop

  4. In a conversation with Claude, you can now ask it to:

    • List your Linode instances

    • Create a new Linode instance

    • Get details about a specific instance

    • Reboot or delete instances

Example prompts:

  • "Show me all my Linode instances"

  • "Create a new 2GB Linode in the Frankfurt region with Debian 11"

  • "Reboot my instance with ID 12345"

Available Tools

The package provides these MCP tools:

  • list_regions - List all available Linode regions

To be added:

  • list_instance_types - List all available Linode instance types and their pricing

  • list_instances - List all existing Linode instances

  • create_instance - Create a new Linode instance

  • get_instance - Get details about a specific Linode instance

  • delete_instance - Delete a Linode instance

  • reboot_instance - Reboot a Linode instance

Development

Project Structure

linode-mcp/
├── bin/                  # Command-line scripts
├── src/                  # Source code
│   └── linode_mcp/       # Main package
│       ├── tools/        # MCP tool implementations
│       └── server.py     # MCP server implementation
├── setup.py              # Package setup file
└── README.md             # This file

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository

  2. Create your feature branch (git checkout -b feature/amazing-feature)

  3. Commit your changes (git commit -m 'Add some amazing feature')

  4. Push to the branch (git push origin feature/amazing-feature)

  5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

Available Tools

1 tool
list_regionsA

List all available Linode regions

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description implies a read-only operation, but does not explicitly state behavioral traits such as idempotency, caching, or rate limits. With no annotations, this is adequate for a simple list tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with five words, perfectly concise and front-loaded. No unnecessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the trivial nature (no parameters, simple list operation, output schema exists), the description provides complete context for an agent to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has no parameters, so schema coverage is 100%. The description does not need to add parameter details. Baseline score of 4 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List') and the resource ('all available Linode regions'), with no ambiguity. There are no sibling tools to distinguish from, so the purpose is precisely conveyed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use when a full list of regions is needed, but does not explicitly state when to use or not use it, nor provide alternatives. Given no siblings, this is acceptable but not maximally helpful.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • Changedlist_regions1 field changed
      • addedInput schema / title
        Added value: +"list_regionsArguments"
  2. 1 tool update
    • First observedlist_regions

TDQS

B3.2/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'list_regions' has a clear and distinct purpose that cannot be confused with any other tool in this set.

Naming Consistency5/5

The naming follows a consistent verb_noun pattern ('list_regions'), and with only one tool, there is no inconsistency to evaluate. The pattern is clear and predictable for any potential future tools.

Tool Count2/5

A single tool is too few for a server named 'Linode MCP Server', which implies broader cloud management capabilities. This feels thin and incomplete for managing Linode resources, as it only covers region listing without any operations for instances, volumes, networking, or other core features.

Completeness1/5

The tool surface is severely incomplete for a Linode server. It only lists regions, missing essential CRUD operations for instances, volumes, networking, DNS, and other Linode services. This leaves significant gaps that will cause agent failures in typical cloud management tasks.

Maintenance

ActivityInactive
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers