Seek MCP工具 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。
Seek MCP工具 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。
Seek MCP工具 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/whyiyhw/seek
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"seek-mcp--": {
"command": "npx",
"args": ["-y", "seek"]
}
}
}
# 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 Seek MCP工具 执行以下任务... Claude: [自动调用 Seek MCP工具 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": {
"seek_mcp__": {
"command": "npx",
"args": ["-y", "seek"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="examples/hero.svg" alt="seek — a local agent platform that plans, spawns a team of sub-agents, and ships while you sleep" width="820"> </p>
<p align="center"> <strong>Not an agent demo — a local agent platform that plans, spawns a team of sub-agents, and ships while you sleep.</strong> </p>
<p align="center"> <img src="https://img.shields.io/badge/license-MIT-f5a623?style=flat-square" alt="MIT"> <img src="https://img.shields.io/badge/CI-race--tested-2ea043?style=flat-square&logo=github&logoColor=white" alt="CI"> <img src="https://img.shields.io/badge/release-v0.8.0-f5a623?style=flat-square" alt="release"> <img src="https://img.shields.io/badge/platforms-macOS%20%C2%B7%20Linux%20%C2%B7%20Windows-2b2b32?style=flat-square" alt="Platforms"> · <a href="README.zh.md">中文</a> </p>
A coding agent that runs as a single ~5 MB Go binary in your terminal — no daemon, no telemetry, no Python/Node runtime, no seek-operated backend. Bring your own model key: DeepSeek-first, and it also speaks OpenAI / Anthropic / Gemini and any OpenAI-compatible endpoint (KIMI, …).
---
| **Autopilot** | unattended end-to-end: decompose → parallel worktree fleet → commit → push. [📘](docs/guide-autopilot.md) |
**/goal** | loop across turns until a cheap model judges a condition met — TUI / headless / cron. [📘](docs/guide-goal.md) |
| **OS sandbox** | seatbelt (macOS) / landlock (Linux) — kernel-level confinement, zero runtime deps. [📘](docs/guide-sandbox.md) |
| **ACP / Zed** | run seek as an editor agent via the Agent Client Protocol. [📘](docs/guide-zed.md) |
| **Portable skills** | Anthropic Agent Skills format — any Claude Code skill installs unmodified. [📘](docs/guide-skills.md) |
| **Three-tier memory** | session · project (decay-score GC) · cross-project "soul" (seek -dream). [📘](docs/guide-memory.md) |
| **Checkpoints** | per-turn git snapshot + file-level /undo /redo /restore. [📘](docs/guide-checkpoint.md) |
| **Background jobs** | detach long builds/servers → bg-N; monitor polls / waits / kills. [📘](docs/guide-background.md) |
| **Semantic references** | LSP "who calls this?" (gopls / pyright / tsserver), grep fallback. [📘](docs/guide-references.md) |
| **Offline image OCR** | @img.png or pasted images → local OCR, no VLM / no network. [📘](docs/guide-ocr.md) |
| **Code review** | effort-graded diff review with --fix and --comment. [📘](docs/guide-code-review.md) |
| **MCP client** | pass through any MCP server's tools. [📘](docs/guide-mcp.md) |
| **Push to phone** | cron / autopilot / long-turn completions → webhook. [📘](docs/guide-webhooks.md) |
| **Dual-axis permissions** | Preference (Deny / Ask / Yolo) × Workflow (None / Plan-analyze / Plan-execute). |
Plus shell hooks, a JSON-RPC 2.0 server mode, and DeepSeek extras (V4 reasoning via think, FIM for 5–10× cheaper small edits, off-peak countdown).
---
OS=$(uname -s | tr '[:upper:]' '[:lower:]')
ARCH=$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/')
VER=$(curl -fsSL https://api.github.com/repos/whyiyhw/seek/releases/latest | sed -nE 's/.*"tag_name":[[:space:]]*"v([^"]+)".*/\1/p')
curl -fsSL "https://github.com/whyiyhw/seek/releases/download/v${VER}/seek_${VER}_${OS}_${ARCH}.tar.gz" \
| sudo tar -xz -C /usr/local/bin seek
seek
First launch walks you through picking a provider + saving a key — that's it. Windows: docs/guide-windows.md. Upgrade: seek -upgrade (sha256-verified, atomic) or /upgrade in the TUI.
seek # interactive TUI
seek -p "what does internal/agent do?" # one-shot, pipeline-friendly
seek goal run "all tests in ./auth pass" # autonomous: work until the goal is met
---
~85k lines of Go (~44k non-test) across 66 packages, -race tested on macOS / Linux / Windows in CI. PRD-driven — docs/prd/ holds the v0–v7 design history; a pitfalls log and a behavioral eval harness keep it honest. Zero external deps in the DeepSeek client; stdlib-first throughout. Current release: v0.8.0.
Docs: docs/ · contributing: CONTRIBUTING.md / AGENTS.md
---
Seek是一个高质量的MCP工具,提供了本地编码代理平台
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。
经综合评估,Seek MCP工具 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 | seek |
| 原始描述 | 开源MCP工具: Not just an agent demo — a local coding-agent platform: plan mode, sub-agent te。⭐7 · Go |
| Topics | mcpagentai-agentai-coding-assistant |
| GitHub | https://github.com/whyiyhw/seek |
| License | MIT |
| 语言 | Go |
收录时间:2026-05-31 · 更新时间:2026-06-02 · 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