AI Skill Hub 推荐使用:Kocoro 是一款优质的MCP工具。AI 综合评分 7.5 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
为Mac提供AI协同助手,支持本地计算机访问、Slack/LINE频道和MC。
Kocoro 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。
为Mac提供AI协同助手,支持本地计算机访问、Slack/LINE频道和MC。
Kocoro 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/Kocoro-lab/Kocoro
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"kocoro": {
"command": "npx",
"args": ["-y", "kocoro"]
}
}
}
# 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 Kocoro 执行以下任务... Claude: [自动调用 Kocoro 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": {
"kocoro": {
"command": "npx",
"args": ["-y", "kocoro"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
An AI cowork agent that lives on your Mac.
Kocoro runs AI agents locally with full computer access — files, apps, browser, terminal, screen — and connects to your team's Slack / LINE / Feishu / Telegram channels via Shannon Cloud. Named agents with their own memory and tools, MCP-native, daemon-driven. The shan CLI is the runtime; Kocoro Desktop is the recommended way to use it.
memory_recall lets the agent look up facts learned from prior sessions before asking the user. Structured memory runs as a local sidecar over a Unix socket; the daemon manages spawn, readiness, restart, and bundle pull.
Opt-in — disabled by default; Kocoro Desktop's Episodic Memory toggle enables it. Three modes:
memory.provider: "disabled" (default) — no sidecar; memory_recall falls back to session search + MEMORY.mdmemory.provider: "cloud" — daemon pulls fresh memory bundles from Kocoro Cloud every 24h. Requires cloud.api_key + cloud.endpoint (overridable via memory.api_key / memory.endpoint)memory.provider: "local" — daemon runs the sidecar against bundles you build locally; no Cloud callsshan ghostty workspace writer ops-bot # open one window per agent
shan "list files on my Desktop" # filesystem MCP shan "show all tables in the database" # sqlite MCP ```
| Format | Built-in fallback | Better with |
|---|---|---|
| n/a — suggests upload so cloud renders it as a native Anthropic document block | pdftotext (brew install poppler) | |
| DOCX | unzip + XML strip (raw text) | pandoc (brew install pandoc) |
| XLSX | unzip + raw XML | xlsx2csv (pip install xlsx2csv) |
| PPTX | unzip + XML strip | pandoc (brew install pandoc) |
| HEIC / AVIF | transcoded server-side by cloud | — |
accessibility and computer tools)ghostty tool)npm (recommended) — auto-updates on every launch:
npm install -g @kocoro/kocoro
Install script — downloads the latest binary to /usr/local/bin:
curl -fsSL https://raw.githubusercontent.com/Kocoro-lab/Kocoro/main/install.sh | sh
From source — requires Go 1.25+:
git clone https://github.com/Kocoro-lab/Kocoro.git
cd Kocoro
go install .
go install places the binary in $GOPATH/bin (default ~/go/bin). Add export PATH="$HOME/go/bin:$PATH" to your shell rc if it's not already on PATH.
Verify with shan --help.
Kocoro requires a Gateway API for LLM completions and remote tools.
Shannon Cloud — get an API key from shannon.run:
```bash shan --setup
go build -o shan . # build
go test ./... # run all tests
go vet ./... # lint
shan # interactive TUI
shan "who is wayland zhang" # one-shot
shan --agent ops-bot "check prod health" # named agent
shan --setup # configure endpoint + API key
In the TUI, type / to see built-in commands:
/research deep "latest advances in AI agents"
/swarm "build a marketing plan for our launch"
/model large
/sessions # browse and resume past sessions
/search websocket reconnect # search session history
```bash
shan # interactive TUI
shan "who is wayland zhang" # one-shot (prompts for tool approval)
shan -y "query" # auto-approve all tools
shan --agent ops-bot "query" # use a named agent
shan --setup # configure endpoint + API key
shan mcp serve # MCP server over stdio
shan daemon start # channel messaging daemon
shan schedule list # local scheduled tasks
Flags: -y/--yes auto-approve; --agent named agent; --dangerously-skip-permissions skip checks in interactive mode; --setup interactive wizard.
tlm binary somewhere on $PATH (or set memory.tlm_path). cloud:
endpoint: https://api.shannon.run
api_key: <your key>
memory:
provider: cloud
shan -y "open Chrome, go to x.com, and post a tweet"
Multi-level merge — later overrides earlier:
~/.shannon/config.yaml — global.shannon/config.yaml — project.shannon/config.local.yaml — local (gitignored)Scalars override, lists merge + dedup, structs field-level merge.
Minimal ~/.shannon/config.yaml:
endpoint: https://api.shannon.run
api_key: <your key>
model_tier: medium
permissions:
allowed_commands:
- "git *"
- "make *"
See docs/config-reference.md for the full key list including agent.*, tools.*, mcp_servers, cloud, memory, sync, daemon, hooks, UI settings, etc. Run /config in the TUI to see the merged config with sources.
Per-agent overrides live in ~/.shannon/agents/<name>/_attached.yaml — including agent.model_tier so individual agents can opt into the Large (Opus) tier without changing the global default. See docs/agents-reference.md for the precedence chain.
See the memory: block in docs/config-reference.md for all keys (provider, endpoint, api_key, socket_path, bundle_root, tlm_path, bundle_pull_interval, sidecar_* timeouts).
```
Self-hosted — run the open-source Shannon Gateway locally, then shan --setup with http://localhost:8080 and an empty API key.
Ollama (local LLMs) — set provider: ollama in ~/.shannon/config.yaml. See docs/config-reference.md for the full block.
| Tool | Approval | Description |
|---|---|---|
cloud_delegate | Yes | Delegate to Shannon Cloud for remote research/swarm execution. |
publish_to_web | Yes ⚠️ | Upload to a **public** S3 URL on Shannon Cloud (50 MiB cap). Path blocklist (.env, .ssh, credentials, *.pem, …) and extension allowlist (html/md/txt/pdf/png/jpg/svg/csv/json/mp4/…). Extend allowlist via cloud.publish_allowed_extensions. Uploads are tagged kind=other server-side (Desktop UI's "All / Image / HTML / PDF / Other" filter sits alongside a separate "Session" bucket for daemon-side session shares). Files retractable via retract_published_file, but **anyone with the URL can read content until then** plus up to 5 minutes after via CDN edge cache. |
list_my_published_files | No | List the user's still-active published files. Paginated (limit default 20, max 100). Optional kind filter (session_share / report / landing_page / image / other) — omit to list every category. |
retract_published_file | Yes ⚠️ | Retract a published file by id (UUID from list, **not** the URL). Owner-only; cross-user calls return a friendly 404 (cloud conflates not-found/already-retracted/not-yours to prevent existence leaks). NOT on the high-risk auto-approval denylist — user can opt in to always_allow_tools. CDN edges may serve content for up to 5 min after success. |
generate_image | Yes ⚠️ | Generate via POST /api/v1/images/generations (gpt-image-2); returns a **public permanent** CDN URL. Args: prompt, size, quality (latency 30s→180s), n (1–10), background. Each call consumes paid quota. For charts use kocoro-generative-ui instead. |
edit_image | Yes ⚠️ | Edit via POST /api/v1/images/edits. Args: prompt + image_urls (1–4, must start with https://static.kocoro.ai/ — external URLs rejected; pipe through generate_image / publish_to_web first). No mask field — describe the region in prose. Latency 40s–350s. |
Localhost-only HTTP for native-app integration and scripting.
| Endpoint | Method | Description |
|---|---|---|
/health | GET | Liveness → {"status":"ok","version":"..."} |
/status | GET | Connection state, active agent, uptime, version |
/agents | GET | List named agents |
/sessions | GET | List sessions, optional ?agent= filter |
/sessions/{id} | GET | Full session with messages, ?agent=<name> |
/sessions/{id} | PATCH | Update title, pinned, favorite (any subset) |
/sessions/{id}/edit | POST | Truncate history at index, re-run with new content |
/sessions/{id}/reset | POST | Clear session history in place (named agent only) |
/sessions/search | GET | Search session history, ?q=<query>&agent=<name> |
/message | POST | Send a message; supports HITL injection |
/migrate/claude-code/preview | POST | Scan ~/.claude/ and return what would be imported (dry-run) |
/migrate/claude-code/apply | POST | Execute a previewed import — copies agents, skills, instructions from Claude Code |
/config/reload | POST | Reload config, restart watchers and heartbeat managers |
/events | GET | SSE stream of daemon events (agent_reply, heartbeat_alert, …) |
/shutdown | POST | Graceful shutdown (used by shan daemon stop) |
Send a message:
```bash
Kocoro 是一个 AIcoworker 代理,能够在你的 Mac 上运行 AI 代理,拥有完整的计算机访问权限,包括文件、应用程序、浏览器、终端、屏幕等,并且可以连接到你的团队的 Slack / LINE / Feishu / Telegram 通道。
Kocoro 的功能包括内存(Kocoro 云功能)、MCP 集成、内存回忆、结构化内存、可选模式等。
Kocoro 需要 macOS、Shannon Gateway、Shannon 云 API 密钥、AppleScript、屏幕截图、辅助功能权限等环境依赖和系统要求。
Kocoro 的安装方式包括 npm、安装脚本、从源码安装等。推荐使用 npm 安装并且会自动更新。
Kocoro 的使用方法包括交互式 TUI、单次执行、命名代理、配置端点和 API 密钥等。可以使用 `/` 命令查看内置命令。
Kocoro 的配置文件包括全局配置、项目配置和本地配置。可以使用 `~/.shannon/config.yaml` 文件进行配置。
Kocoro 的 API 包括 Shannon Gateway API、Shannon 云 API 等。可以使用 `shan --setup` 命令配置端点和 API 密钥。
该项目使用Go语言开发,提供AI协同助手功能,支持本地计算机访问、Slack/LINE频道和MC,但评分较低,可能存在一些问题或缺陷。
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。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,Kocoro 是一款质量良好的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | Kocoro |
| 原始描述 | 开源MCP工具:An AI cowork agent for your Mac — local computer access, Slack/LINE channels, MC。⭐270 · Go |
| Topics | mcpgo |
| GitHub | https://github.com/Kocoro-lab/Kocoro |
| License | MIT |
| 语言 | Go |
收录时间:2026-05-22 · 更新时间:2026-05-24 · License:MIT · 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