setup-mcp-server

setup-mcp-server is a skill for Claude Code from chapmanjw/minecraft-bedrock-claude-plugin. It costs 88 tokens per session (1,842 once invoked), scanned A, original, MIT.

A setup guide for connecting Claude to a Minecraft Bedrock server through an MCP server, a program that lets software exchange commands with the game.

In plain words
What is it for?
Installing minecraft-bedrock-mcp-server, configuring a Bedrock behavior pack and its permissions, starting the server, and checking the bridge connection.
Why use it?
It explains the installation, authentication tokens, configuration files, and startup checks needed for the connection to work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the minecraft-bedrock plugin — 20 skills, 2 agents shipped together

Good fit Installing minecraft-bedrock-mcp-server, configuring a Bedrock behavior pack and its permissions, starting the server, and checking the bridge connection.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chapmanjw/minecraft-bedrock-claude-plugin/setup-mcp-server
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add chapmanjw/minecraft-bedrock-claude-plugin --skill setup-mcp-server
Clone the repo
git clone --depth 1 https://github.com/chapmanjw/minecraft-bedrock-claude-plugin

Made for: Claude Code.

Or install minecraft-bedrock, the plugin that ships this one along with the rest of its 20 skills, 2 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for setup-mcp-server

README.md
[![agentmods](https://agentmods.dev/badge/skills/chapmanjw/minecraft-bedrock-claude-plugin/setup-mcp-server/github.svg)](https://agentmods.dev/skills/chapmanjw/minecraft-bedrock-claude-plugin/setup-mcp-server)
Your own site
<a href="https://agentmods.dev/skills/chapmanjw/minecraft-bedrock-claude-plugin/setup-mcp-server"><img src="https://agentmods.dev/badge/skills/chapmanjw/minecraft-bedrock-claude-plugin/setup-mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for setup-mcp-server

Your own site · 80×15
<a href="https://agentmods.dev/skills/chapmanjw/minecraft-bedrock-claude-plugin/setup-mcp-server"><img src="https://agentmods.dev/badge/skills/chapmanjw/minecraft-bedrock-claude-plugin/setup-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00088 $0.01842
Opus 5 $0.00044 $0.00921
Sonnet 5 $0.00018 $0.00368
Haiku 4.5 $0.00009 $0.00184

Measured 9d ago against content hash f44412bb4326, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

setup-mcp-server scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **Liveness:** `curl http://localhost:8765/healthz` returns OK.
skills/setup-mcp-server/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Install and run the MCP server (Step 3 of 4)

This is Phase 3 of the four-phase Minecraft Bedrock MCP setup. It assumes Phase 2 (setup-minecraft-world) is done. You should have, written down:

  • the world path, e.g. /opt/bedrock-server/worlds/mcp-world
  • the behavior-pack path, e.g. <world>/behavior_packs/bedrock-bridge

If either is missing, get it before continuing. The MCP server runs on the same host as BDS and needs Node.js 20+ there — verify with node -v.

How the pieces talk

The MCP server exposes two authenticated surfaces:

  • /mcp — what Claude connects to (Phase 4), guarded by BRIDGE_CLIENT_TOKEN.
  • /bridge — what the behavior pack long-polls, guarded by BRIDGE_AGENT_TOKEN.

So there are two separate tokens. Keep them straight: the client token is for Claude, the agent token is for the behavior pack inside the world.

Step 1 — Install the MCP server

On the BDS host:

npm install -g minecraft-bedrock-mcp-server

Alternatives, if the user prefers: npx minecraft-bedrock-mcp-server (no install), or the Docker image ghcr.io/chapmanjw/minecraft-bedrock-mcp-server:latest (docker run --env-file .env -p 8765:8765 ...). Pin to a version tag for reproducibility, and keep it aligned with the BDS and behavior-pack versions.

Step 2 — Generate the two tokens

Generate two long random secrets:

openssl rand -hex 32   # -> BRIDGE_CLIENT_TOKEN
openssl rand -hex 32   # -> BRIDGE_AGENT_TOKEN

On Windows without openssl:

-join ((1..32) | ForEach-Object { '{0:x2}' -f (Get-Random -Max 256) })

Have the user keep both values somewhere safe. They are needed again in this phase and in Phase 4.

Step 3 — Write the MCP server .env

Create a .env file for the MCP server (this plugin ships .mcp.json.example in its repo root as a reference, but the server's own .env is what matters here):

BRIDGE_CLIENT_TOKEN=<first secret>
BRIDGE_AGENT_TOKEN=<second secret>
BRIDGE_WORLD_PATH=<the world path from Phase 2>
BRIDGE_BEHAVIOR_PACK_PATH=<the behavior-pack path from Phase 2>
BRIDGE_HOST=0.0.0.0
BRIDGE_PORT=8765

Read the full file on GitHub · 193 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 193 lines · 88 tokens per session scan A f44412bb4326

Subscribe to this mod's changes

setup-mcp-server is a skill published in the GitHub repository chapmanjw/minecraft-bedrock-claude-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,842 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

minecraft-modpack-server

Host modded Minecraft servers (CurseForge, Modrinth).

cyborg-garden/hermes-agent-mt · 19 tokens

minecraft-modpack-server

Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

braxtonROSE4/zorro-agent · 48 tokens

sdf

SDFormat/SDF model and world authoring, validation, and simulator handoff. Use for .sdf files, SDFormat XML, models, worlds, links, joints, poses, frames, inertials, visual/collision geometry, mesh URIs, sensors, lights, physics, plugins, includes, Gazebo, static SDF review, or simulator-specific metadata. Do not use…

earthtojake/text-to-cad · 88 tokens

ar-vr-xr

AR/VR/XR development with Unity XR, WebXR, ARKit, ARCore, Meta Quest SDK, and spatial computing. Use when building augmented reality, virtual reality, mixed reality applications, or spatial experiences.

travisjneuman/.claude · 50 tokens

add-puzzle-type

Scaffold a new puzzle type across all 10+ pipeline integration points in jigsawR. Creates the core puzzle module, wires it into the unified pipeline (generation, positioning, rendering, adjacency), adds ggpuzzle geom/stat layers, updates DESCRIPTION and config.yml, extends the Shiny app, and creates a comprehensive…

pjt222/agent-almanac · 100 tokens

openclaw-plugin

You are an autonomous agent in a persistent world. Your character is in SOUL.md. World rules are in WORLD.md.

AIScientists-Dev/WorldSeed · 0 tokens