Claude 助手
- 作者仓库星标 0
- 作者更新于 实时读取
- 作者仓库 skills-registry
- 领域
- 通用
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @tomevault-io · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- macOS · Windows
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- 读取环境变量
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: connect-claude
description: >- Use when this capability is needed. This is the final phase of the Minecraft Bedrock MCP setu…
category: 通用
runtime: 无特殊运行时
---
# connect-claude 输出预览
## PART A: 任务判断
- 适用问题:通用任务拆解、检查和交付。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Connecting Claude Code / Connecting Claude Desktop / Verify the connection”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于通用任务拆解、检查和交付,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Connecting Claude Code / Connecting Claude Desktop / Verify the connection”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、读取环境变量、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、读取环境变量;主要在本地完成;通常不需要额外 API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文出现了 `/mcp` 这类斜杠命令;如果你的 Agent 支持命令触发,优先用命令开场,再补充目标和边界。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件、读取环境变量。
先用一个小任务确认它会围绕“Connecting Claude Code / Connecting Claude Desktop / Verify the connection”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: connect-claude
description: >- Use when this capability is needed. This is the final phase of the Minecraft Bedrock MCP setu…
category: 通用
source: tomevault-io/skills-registry
---
# connect-claude
## 什么时候使用
- 把通用方向的常用动作沉淀成 Agent 可调用的技能 适合处理通用任务拆解、检查、交付和复盘,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的步骤;通常不需要额外…
- 面向通用任务拆解、检查和交付,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Connecting Claude Code / Connecting Claude Desktop / Verify the connection」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件、读取环境变量;主要在本地完成;通常不需要额外 API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "connect-claude" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Connecting Claude Code / Connecting Claude Desktop / Verify the connection
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件、读取环境变量 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} Connect Claude to the Minecraft world (Step 4 of 4)
This is the final phase of the Minecraft Bedrock MCP setup. It assumes
Phase 3 (setup-mcp-server) is done: the MCP server is running and its bridge
handshake with the world succeeded.
Before starting, get two things from the user:
- The
/mcpURL —http://<host>:<port>/mcp, e.g.http://localhost:8765/mcp. Uselocalhostonly if Claude runs on the same machine as the MCP server; otherwise use the host's LAN IP or hostname. If the MCP server uses TLS, the scheme ishttps. - The
BRIDGE_CLIENT_TOKEN— the first secret from Phase 3 (the client token, not the agent token).
Name the server
minecraft-bedrock. The builder agent and skills in this plugin expect MCP tools under that name (mcp__minecraft-bedrock__mc_*). Use exactlyminecraft-bedrockas the server name below.
Ask the user which Claude they're connecting: Claude Code (CLI / IDE extension) or Claude Desktop. Follow the matching section.
Connecting Claude Code
The MCP server speaks the Streamable HTTP transport, which Claude Code
supports natively. The simplest path is the claude mcp add command:
claude mcp add --transport http minecraft-bedrock "http://<host>:8765/mcp" \
--header "Authorization: Bearer <BRIDGE_CLIENT_TOKEN>"
Pick a scope with -s: local (default, this project only), project
(shared via a committed .mcp.json), or user (all projects on this
machine). For a personal setup, user is usually what the user wants:
-s user.
Do not commit the token. If the user wants project scope, write the
.mcp.json with the token pulled from an environment variable instead of
inlining it. This plugin ships .mcp.json.example in its repo root showing
that pattern:
{
"mcpServers": {
"minecraft-bedrock": {
"type": "http",
"url": "${MINECRAFT_MCP_URL:-http://localhost:8765/mcp}",
"headers": { "Authorization": "Bearer ${MINECRAFT_MCP_TOKEN}" }
}
}
}
With that, the user sets MINECRAFT_MCP_URL and MINECRAFT_MCP_TOKEN in their
environment and the committed file stays secret-free.
After adding it, the user restarts Claude Code (or reloads the window in the
IDE extension). Confirm the server shows up with claude mcp list or
/mcp — it should report minecraft-bedrock as connected.
Connecting Claude Desktop
Two options:
A — Native custom connector (preferred, if the user's Claude Desktop has
it). In Settings → Connectors, add a custom connector with the URL
http://<host>:8765/mcp and a header Authorization: Bearer <BRIDGE_CLIENT_TOKEN>.
B — Via the mcp-remote adapter. Edit Claude Desktop's config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add under mcpServers:
{
"mcpServers": {
"minecraft-bedrock": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"http://<host>:8765/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer <BRIDGE_CLIENT_TOKEN>"
}
}
}
}
The token goes through the AUTH_HEADER env var so its space isn't mangled by
argument parsing. Then fully restart Claude Desktop — the mc_* tools
appear under the tools (🔌) menu once it reconnects.
Verify the connection
A registered server isn't a working one — confirm with a live call:
- Make sure at least one player is in the world (many tools act relative to players or the world origin).
- Call
mc_world_get_info(ormc_server_get_status). A successful response — time, weather, dimensions — means the full chain is up: Claude → MCP server → bridge → behavior pack → world. - As a visible smoke test, call
mc_world_send_messagewith a short greeting and confirm the user sees it in the in-game chat.
If a call fails:
- Auth / 401 — wrong token, or the agent token was used instead of the client token. The client token is the first secret from Phase 3.
- Connection refused / timeout — MCP server not running, wrong host:port, or a firewall between Claude and the host.
- Tools connect but calls hang or error about the bridge — the world side
is down: re-check the Phase 3 handshake (BDS running, behavior pack active,
secrets.jsontoken).
Wrap up
Once mc_world_get_info returns cleanly, the setup is complete:
-
minecraft-bedrockMCP server registered with Claude. -
mc_*tools visible. - A live test call succeeded against the world.
Tell the user they're done — all four phases are complete. Suggest next steps:
- Try a simple prompt: "What's the time and weather? Set it to clear midday."
- Try building: "Build a small stone-brick house near the nearest player."
Claude works through the
mc_*tools to plan and place blocks in the world.
Source: chapmanjw/minecraft-bedrock-claude-plugin — distributed by TomeVault.
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核