GitHub
作者：github
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
电脑或云端★ 34,245MIT4天前更新
安装
Dekko
概览
作者提供的说明（英文原文）
Static code map generator: MAP.md + map.json for any repo, plus a Claude Code /map plugin
PopNx MCP 的三大支柱
这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
- 使用情况i尚未统计★ –
它能帮你做什么
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
- 连接方式: 在你的电脑上运行
- 传输方式: stdio
- 分类: 开发者工具
安装
选择你使用的 AI 应用，然后复制设置。
安装之前
- 基础检查：1 项中通过 1 项
- 在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
- 注册中心没有列出需要填写的密钥。
你需要
- PyPI已安装 Python 的 uv（用于 uvx 命令）
你用的是哪个应用？
在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"dekko": {
"command": "uvx",
"args": [
"dekko",
"serve",
"--mcp"
]
}
}
}在终端中运行这条命令
claude mcp add dekko -- uvx dekko serve --mcp或者自己复制设置
粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json
{
"mcpServers": {
"dekko": {
"command": "uvx",
"args": [
"dekko",
"serve",
"--mcp"
]
}
}
}浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"dekko": {
"type": "stdio",
"command": "uvx",
"args": [
"dekko",
"serve",
"--mcp"
]
}
}
}浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。
这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上，无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。
它能做什么
它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。
基础检查i
我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 aahlijia 验证，该账户拥有此仓库
- … 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
- … 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
- – 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表
与“开发者工具”中的其他服务器比较i
- 星标数多于此分类中其他 4921 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 4921 个服务器的 58% 更新
- 基础检查结果等于或优于此分类中其他 4921 个服务器的 100%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。
常见问题
Dekko 安全吗？
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。
它需要哪些密钥或代码？
注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端？
它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。
它还在维护吗？
GitHub 仓库最后更新于–，最新版本（1.9.0）于29天前进入注册中心。
哪些应用可以使用它？
支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
有什么可以替代它？
同一分类中有：GitHub, Desktop Commander, Cloudflare MCP
替代选择
同一分类中其他作者的服务器，按星标数排序。
如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Desktop Commander
作者：wonderwhy-er
MCP server for terminal commands, file operations, and process management
在你的电脑上运行★ 10,225MIT17天前更新
安装
Cloudflare MCP
作者：cloudflare
Cloudflare MCP servers
在云端运行★ 4,446Apache-2.014个月前更新
安装
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Ever watched your coding agent grep blind through a repo, open three files it didn't need, and burn fifteen thousand tokens just to answer "who calls this function"? That's the problem dekko exists to fix.
This demo runs on dekko's own repo (commit 835733c ) — clone it and run the same three commands yourself.
dekko is a fast, offline, dependency-free static code map generator and codebase indexer for LLM coding agents. It scans a repository with tree-sitter (no model tokens spent parsing) and writes:
- `MAP.md` — a human-readable map: a per-directory overview, an embedded architecture diagram, load-bearing/orchestrator rankings, then every file's functions/methods with signatures, doc lines, and who calls and is called by whom.
- `map.json` — the same graph in machine-readable form.
On top of the map, dekko gives an agent a token-cheap way to answer questions like "what does this file contain," "who calls this function," and "what do I need to safely change this" — without reading whole files. It ships as a CLI, a Claude Code `/map` plugin + MCP server (Model Context Protocol), and works with Cline too.
The result: 10x-300x fewer tokens than a plain Read/Grep workflow on the everyday tasks (orientation, outlining a large file, a symbol's callers), measured across 7 real, unmodified open-source repos on dekko 0.43.77. The floor, a small grep-friendly local symbol, is about 2.5x. The full breakdown is right below.
Why dekko?
Most agent workflows gather context by reading whole files or grepping across a repo — expensive, and it throws away structure (who calls what, what a function's fan-in/fan-out looks like). dekko instead parses the repo once into a call graph and answers targeted questions against it. Measured across 7 real, unmodified open-source repos (Go, TypeScript, Java, Rust, Python/C++ — up to 14k files, 172k symbols) on dekko 0.43.77, dekko's structured queries used 10x–300x fewer tokens than the equivalent Read/Grep workflow for the same task (repo orientation, outlining a large file, tracing a symbol's callers).
| Task | Example repo (scale) | dekko | Read/Grep | Savings |
|---|---|---|---|---|
Repo orientation (summary) | awesome-go (10 files) | 359 tok | ~16,328 tok | ~45x |
Repo orientation (summary) | claude-buddy (57 files) | ~349 tok | ~113,514 tok (every source file) | ~325x |
| Outline a large file | claude-code REPL.tsx (5,005 lines) | ~1,154 tok | ~223,963 tok | ~194x |
| Outline a large file | cline SdkController.ts (84 KB) | 1,803 tok | ~21,023 tok | ~11.7x |
| Outline a directory | zed crates/git_ui/src (32 files) | ~35,778 tok | ~418,520 tok | ~11.7x |
| Callers of a symbol | claude-code errorMessage | ~602 tok | ~18,521 tok (323+ grep hits) | ~31x |
| Callers of a symbol | zed MultiWorkspace.new (22 sites, 8 files) | ~809 tok | ~381,446 tok (read the caller files) | ~471x |
| External-API usage | claude-code chalk | ~798 tok | ~8,099 tok | ~10x |
Bundled context (workset) | awesome-go ToHTML | 263 tok | 4,104 tok | ~16x |
dekko's cost stays roughly flat per query while Read/Grep scales with file/repo size, so the ratio grows with scale. It's fast in wall-clock terms too: mapping dekko's own ~4,300-symbol codebase from a cold cache takes about 5 seconds on all cores, an incremental remap after an edit is well under a second, and queries against the resulting map return instantly. The win isn't universal — small, self-contained files and already-grep-friendly local symbols see little benefit (the floor measured was about 2.5x). See benchmarks/real-world-repos/ for the full per-task breakdown, methodology, the original 2026-08 study, and the correctness caveats it raised and how they were closed.
Compared to tag-index tools like ctags/gtags, dekko resolves actual call edges (not just definitions), ranks files by load-bearing-ness, and speaks directly to agents over MCP or the CLI — no editor plugin required.
Install
uv tool install dekko # or: pip install dekko / pipx install dekkodekko --claude-install # add the /map command + MCP server to Claude Code, then restart
Extras (dekko[all] for 43 more languages, dekko[search] for embedding search), installing from a local clone, and uninstalling are in docs/install.md.
Quick start
cd my-projectdekko map # writes .dekko/MAP.md + .dekko/map.json dekko summary # ~40-line digest: dirs, hotspots, entry points
.dekko/ is git-ignored by default; the map regenerates on demand, so you rarely need to run dekko map again by hand. If your repo has languages outside the default Tier-1 set (Python, C, C++, JS/TS, Go, Java, Kotlin, Rust), dekko map will say so per file; install dekko[all] for 43 more languages (see Install) and re-run. The list says how well each one is read.
Documentation
- docs/install.md — installation, extras, local clone, uninstall
- docs/cli.md — every CLI command, symbol targets, excluding files, notes, daemon mode, language support
- docs/claude-code.md — the
/mapplugin, push hooks, Claude Code skills, the MCP server, and Cline
Learn more
- CHANGELOG.md — per-version history
- CONTRIBUTING.md — dev setup, testing, releasing
- benchmarks/ — token-efficiency measurements, including a 7-repo real-world comparison against a plain Read/Grep workflow