使用MCP常用器器 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.5 分，整体质量较高。我们推荐使用将其纳入你的 AI 工具库，帮助提升工作效率。
使用MCP常用器器的为常用器器一学一学，常用器器为常用器器的为常用器器一学一学，常用器器为常用器器的为常用器器一学一学，常用器器为常用器器的为常用器器一学一学，常用器器为常用器器的为常用器器一学一学
使用MCP常用器器 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。
使用MCP常用器器的为常用器器一学一学，常用器器为常用器器的为常用器器一学一学，常用器器为常用器器的为常用器器一学一学，常用器器为常用器器的为常用器器一学一学，常用器器为常用器器的为常用器器一学一学
使用MCP常用器器 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。
# 方式一：通过 Claude Code CLI 一键安装
claude skill install https://github.com/FrkAk/mymir
# 方式二：手动配置 claude_desktop_config.json
{
"mcpServers": {
"--mcp----": {
"command": "npx",
"args": ["-y", "mymir"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例： 用户: 请帮我用 使用MCP常用器器 执行以下任务... Claude: [自动调用 使用MCP常用器器 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入："列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"__mcp____": {
"command": "npx",
"args": ["-y", "mymir"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Context management for the agent-native engineering era.
<p align="center"> <a href="#claude-code"><img alt="Claude Code" src="https://img.shields.io/badge/Claude_Code-D97757?style=flat-square&logo=anthropic&logoColor=white" /></a> <a href="#codex"><img alt="Codex" src="https://img.shields.io/badge/Codex-000000?style=flat-square&logo=openai&logoColor=white" /></a> <a href="#cursor"><img alt="Cursor" src="https://img.shields.io/badge/Cursor-000000?style=flat-square&logo=cursor&logoColor=white" /></a> <a href="#gemini"><img alt="Gemini CLI" src="https://img.shields.io/badge/Gemini_CLI-4285F4?style=flat-square&logo=googlegemini&logoColor=white" /></a> </p>
<p align="center"> <img src="assets/mymir-demo.gif" alt="Mymir demo" width="900" /> </p>
Most of us aren't really writing code anymore, we're directing agents that do. But those agents have no memory. Every session starts from zero, and engineers end up spending their time re-explaining what was built, why decisions were made, and what still needs to happen. That's not engineering, that's babysitting.
Mymir replaces that cycle. It's not just a context layer your agents read from, it's an end-to-end project management tool that agents operate natively. Mymir creates tasks, refines them, plans implementations, provides the right context at the right stage, and tracks everything that happens. Your agent harness doesn't need a briefing. It walks into every session knowing exactly what to do next and why.
---
We're working on a hosted version for those who want the full experience without the setup. Run from anywhere, access your team's projects, collaborate across sessions. Privacy is a core value, which is why it's taking longer than usual to get right.
The hosted version will be a paid service. We can't bear the infrastructure costs on our own, and we'd rather be upfront about that than pretend otherwise. Self-hosted remains free and always will.
---
All four plugins bundle the shared components:
| Component | What it does |
|---|---|
| **6 MCP tools** | mymir_project, mymir_task, mymir_edge, mymir_query, mymir_context, mymir_analyze |
**/mymir skill** | Auto-invokes when conversation matches project planning; routes to inline workflows or hands off to a deep-mode workflow when needed |
| **Brainstorm workflow** | Explore and shape a project idea through structured conversation |
| **Onboarding workflow** | Reverse-engineer an existing codebase into a task graph with shipped work recorded as done |
| **Decompose workflow** | Break a project brief into a dependency graph |
| **Manage workflow** | Strategic CTO-mode review: rebalance the graph, audit dependencies, prune orphans, consolidate categories |
In Codex, Cursor, and Gemini each workflow is a skill invoked by slash command. In Claude Code each is also available as a dispatchable agent (via the Task tool) so the main /mymir skill can hand off work in a clean per-agent context.
Claude Code additionally bundles:
| Component | What it does |
|---|---|
**/mymir:composer skill** | End-to-end task orchestrator. Picks the highest-value ready task (or one named ref), drives it through research → plan → implement → propagate via three dispatched subagents per task in clean per-phase contexts, loops until queue empty or user stops. Requires /goal harness for backlog mode (composer emits it on first turn; user pastes). |
| **Composer subagents** | mymir:composer-researcher gathers grounded context and refines the task; mymir:composer-planner writes the unabridged implementation plan; mymir:composer-implementer ships the code, opens a PR, and marks the task done. |
**mymir:decompose-task agent** | Splits an existing oversize task in an active project into 2 to N children, rewires every dependency edge touching the parent, cancels the parent with rationale citing the children. Composer's oversize handler routes here. |
**mymir:decompose-feature agent** | Adds a new feature or capability cluster to an active project. Reuses existing categories and tag vocabulary; creates 5 to 20 tasks plus internal and integration edges. |
(Composer depends on a subagent dispatch primitive for clean per-phase contexts and tool-restriction enforcement. Codex, Cursor, and Gemini do not yet have an equivalent, so composer is Claude Code only for now.)
---
使用MCP常用器器的为常用器器一学一学，常用器器为常用器器的为常用器器一学一学，常用器器为常用器器的为常用器器一学一学
该工具使用 AGPL-3.0 协议，商用场景请仔细阅读协议条款，必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
⚠️ AGPL 3.0 — 最严格的 Copyleft，网络服务端使用也需开源，SaaS 使用受限。
经综合评估，使用MCP常用器器 在MCP工具赛道中表现稳健，质量良好。如果你已有明确的使用需求，可以直接上手体验；如果还在评估阶段，建议对比同类工具后再做决策。
| 原始名称 | mymir |
| Topics | mcpagent-nativeclaude-codeclaude-code-plugincontext-managementcontext-networktypescript |
| GitHub | https://github.com/FrkAk/mymir |
| License | AGPL-3.0 |
| 语言 | TypeScript |
收录时间：2026-05-23 · 更新时间：2026-05-23 · License：AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型，复制安装指令后粘贴到对应客户端