Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Minecraft Command Execution MCP Server give me 64 diamonds"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that enables Claude to execute Minecraft commands and get tab completions through the MasterControl API.
This MCP server provides two tools:
execute_commandExecute any Minecraft command remotely as the authenticated player.
Player must be online and on a server
Player receives in-game notification when commands are executed
Returns command output or error messages
To get help: Append "help" to any command (e.g., "island help", "island upgrade help")
Examples:
execute_command("gamemode creative")
execute_command("island help") # Shows island command help
execute_command("island upgrade help") # Shows upgrade subcommand help
execute_command("island upgrade speed 5")tab_completeGet tab completion suggestions for partial commands.
Discover available commands and subcommands
Find valid arguments and parameters
Works exactly like pressing Tab in Minecraft
Examples:
tab_complete("gamemode ") # Returns: survival, creative, adventure, spectator
tab_complete("island ") # Returns: available island subcommandsRelated MCP server: MCP Minecraft Remote
Python 3.10 or higher
uv package manager (install here)
A running MasterControl server with the command API
Valid API key for your Minecraft player
Clone the repo:
git clone https://github.com/<your-user>/minecraft-mcp-server.git
cd minecraft-mcp-serverInstall dependencies:
uv syncConfigure environment variables:
cp .env.example .envEdit .env with your settings:
# Required: Your Midnight API key
MIDNIGHT_API_KEY=your-api-key-here
# Optional: MasterControl API URL (defaults to localhost:8080)
MIDNIGHT_API_URL=http://your-server:8080/api/v2Run the server directly to test:
uv run server.pyIt will wait for stdio input — that's expected for an MCP server. Ctrl+C to exit.
Add the server to Claude Code (use the absolute path to your cloned repo):
claude mcp add midnight \
--transport stdio \
--env MIDNIGHT_API_KEY=your-key-here \
--env MIDNIGHT_API_URL=http://localhost:8080/api/v2 \
-- uv --directory /absolute/path/to/minecraft-mcp-server run server.pyIn Claude Code, check that the server is running:
/mcpYou should see midnight listed with status ✓ Connected.
Execute Commands:
You: "Change my gamemode to creative"
Claude: [Uses execute_command("gamemode creative")]
✓ Command executed successfullyGet Command Help:
You: "How do I use the island upgrade command?"
Claude: [Uses execute_command("island upgrade help")]
Shows the help output for island upgradeExplore Commands:
You: "What island commands are available?"
Claude: [Uses tab_complete("island ")]
Lists: upgrade, create, delete, invite, members...Variable | Required | Default | Description |
| Yes | - | Your player's API key |
| No |
| MasterControl API base URL |
POST /api/v2/command/execute — Execute commands
POST /api/v2/command/tabComplete — Get tab completions
Create a .env file:
echo "MIDNIGHT_API_KEY=your-key-here" > .envCheck that:
MasterControl API is running
API key is correct
Player is online and on a server (not in proxy limbo)
Never commit .env — it contains your API key (already excluded via .gitignore)
Commands execute with your player's permissions
The AI can run any command you can run in-game
Execute a Minecraft command remotely as the authenticated player.
This tool allows you to run any Minecraft command as if the player associated with the API key typed it in-game. The player must be online and on a server. The player will be notified in-game that a remote command is being executed.
To get help for any command, simply append "help" as the last argument. For example: "island help", "island upgrade help", "gamemode help"
Args: command: The Minecraft command to execute (without the leading slash). Examples: "gamemode creative", "tp 100 64 200", "island upgrade speed 5"
Returns: The output from the command execution, or an error message if it failed.
Examples: - execute_command("help") - Shows general help - execute_command("island help") - Shows island command help - execute_command("island upgrade help") - Shows island upgrade help - execute_command("gamemode survival") - Changes gamemode
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: the player will be notified in-game, the command executes as the authenticated player, and it returns output or error messages. It covers the essential mutation behavior and user feedback mechanism, though it doesn't mention rate limits or specific error handling details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured and appropriately sized. It starts with the core purpose, then provides usage details, parameter explanation, return values, and examples. Every sentence adds value, with no redundant information, and it's front-loaded with the most important information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (remote command execution with authentication requirements), no annotations, and an output schema exists, the description provides excellent completeness. It covers purpose, prerequisites, parameter usage, return behavior, and multiple examples. The output schema handles return value structure, so the description appropriately focuses on operational context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, so the description must fully compensate. It provides comprehensive parameter semantics: explains what the 'command' parameter is ('The Minecraft command to execute without the leading slash'), gives multiple examples, and shows how to get help. This adds significant value beyond the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Execute a Minecraft command remotely as the authenticated player') and distinguishes it from the sibling tool 'tab_complete' by focusing on command execution rather than completion suggestions. It specifies the resource (Minecraft command) and the context (remote execution as authenticated player).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool ('run any Minecraft command as if the player associated with the API key typed it in-game'), including prerequisites (player must be online and on a server). It doesn't explicitly mention when not to use it or provide detailed alternatives beyond the sibling tool, but the context is well-defined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get tab completion suggestions for a partial Minecraft command.
This tool provides autocomplete suggestions for commands, just like pressing Tab in the Minecraft client. Useful for discovering available commands, subcommands, and valid arguments.
Args: command_line: The partial command line to complete. Examples: "gamemode ", "island upgrade ", "give diamond"
Returns: A formatted list of completion suggestions, or a message if none are available.
Examples: - tab_complete("gamemode ") -> Lists: survival, creative, adventure, spectator - tab_complete("island ") -> Lists available island subcommands - tab_complete("give ") -> Lists available items
| Name | Required | Description | Default |
|---|---|---|---|
| command_line | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes what the tool does (provides autocomplete suggestions), the context (like pressing Tab in Minecraft), and the return behavior (formatted list or message if none available). It doesn't mention rate limits or error handling, but covers the core behavior well.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured and appropriately sized. It starts with a clear purpose statement, follows with usage guidelines, then provides parameter details, return information, and concrete examples. Every sentence adds value with zero wasted content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (single parameter, no annotations, but with output schema), the description is complete. It explains the purpose, usage, parameter with examples, and return behavior. The existence of an output schema means the description doesn't need to detail return values, and it adequately covers what's needed for this autocompletion tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, so the description must compensate. It provides a clear parameter description: 'command_line: The partial command line to complete' with three concrete examples that illustrate valid inputs. This adds significant meaning beyond the bare schema, though it doesn't detail all possible command formats.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Get tab completion suggestions for a partial Minecraft command.' It specifies the exact action (get suggestions) and resource (Minecraft commands), and distinguishes it from the sibling tool 'execute_command' by focusing on autocompletion rather than command execution.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use this tool: 'Useful for discovering available commands, subcommands, and valid arguments.' It provides clear context for its purpose (autocompletion like pressing Tab) and distinguishes it from the alternative 'execute_command' by not overlapping in functionality.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The two tools have clearly distinct purposes: execute_command runs commands, while tab_complete provides suggestions for command completion. There is no overlap or ambiguity between them, as one is for execution and the other is for discovery/assistance.
Both tools follow a consistent verb_noun naming pattern (execute_command and tab_complete). The naming is clear, predictable, and uses the same style throughout, making it easy to understand their functions at a glance.
With only 2 tools, the server feels thin for its purpose of Minecraft command execution. While the tools cover basic execution and completion, there are likely missing operations such as listing available commands, checking player status, or handling command history, which would enhance the server's utility and completeness.
The tool set is severely incomplete for the domain of Minecraft command execution. It lacks essential operations like listing all available commands, validating commands before execution, managing multiple players, or handling command feedback in a structured way. This forces agents to rely heavily on trial-and-error with execute_command and tab_complete, leading to potential inefficiencies and failures.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Generate AI images and videos from any compatible MCP client.
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mattlack15/midnightsky-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
