What it does
Gate for coding agents' MCP and built-in tool calls: rules, approvals and hash-chained receipts
- Connects –
- Account or key No key needed
- Category 开发者工具
可搭配使用
教 AI 做这类工作的 Skill,可与本项一起使用
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
为什么排在这里
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 6/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 7/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 13/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
安装
选择你使用的 AI 应用,然后复制设置。
通过 3/3 项检查 · 在你的电脑上运行
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
Claude 暂时无法连接 Derbent
开发者尚未在 MCP 注册表中填写安装方式
ChatGPT 暂时无法连接 Derbent
开发者尚未在 MCP 注册表中填写安装方式
你可以改用这些方式
B · 开发者工具 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
- Sentry✓ ChatGPT
- Compiler Explorer✓ ChatGPT
- GitDiagram✓ ChatGPT
Claude Code 暂时无法连接 Derbent
开发者尚未在 MCP 注册表中填写安装方式
Cursor 暂时无法连接 Derbent
开发者尚未在 MCP 注册表中填写安装方式
VS Code 暂时无法连接 Derbent
开发者尚未在 MCP 注册表中填写安装方式
一览
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19日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 tunahanaliozturk 验证,该账户拥有此仓库
- ✓ 通过
仍在维护
代码最后更新于上个月
- ✓ 通过
有许可证
使用 Apache-2.0
- – 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
作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/tunahanaliozturk-derbent)讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
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 6136 个服务器的 77%
- 发布到注册中心的时间比此分类中其他 6136 个服务器的 41% 更新
- 基础检查结果等于或优于此分类中其他 6136 个服务器的 99%
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
Derbent 安全吗?
它在 3 项适用的基础检查中通过了 3 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 仓库最后更新于上个月,最新版本(1.0.0)于2个月前进入注册中心。
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。
有什么可以替代它?
同一分类中有:GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise
功能相近的其他选择
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ 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
GitDiagram
Architecture diagrams, explanations and Mermaid source for public GitHub repositories.
Appllama
Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.
Omnara
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Repowise
Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.
| 本项 Derbent | GitDiagram | Appllama | Cloudflare MCP | Omnara | Repowise | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 云端或安装在电脑上都可以 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 是 | 否 | 否 |
| 基础检查 | 3/3 | 4/4 | 4/4 | 4/4 | 4/4 | 5/5 |
| 许可证 | Apache-2.0 | MIT | MIT | Apache-2.0 | Apache-2.0 | AGPL-3.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
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。
Derbent
One guarded pass for all your coding agents.
Every tool call that reaches Derbent, MCP or a CLI's built-in tools, is decided by one policy and written to a tamper-evident log, and the calls you care about wait for you.
Derbent guards against mistakes and prompt injection, and keeps an audit trail. It is not a sandbox: an agent that can already run shell commands as you can get around it (see Limits).
In Turkish history, a derbent was a guarded post on a mountain pass: its keepers decided who went through and kept a record of everyone who did. Derbent does the same for your coding agents' tool calls.
Claude Code, Codex, GitHub Copilot CLI and Antigravity CLI connect to Derbent as one MCP server, and your other MCP servers sit behind it. Each CLI's pre-tool hook sends its built-in tools, such as the shell and file edits, through the same gate. Every call is decided by your rules and written down.
Support for Codex and Antigravity CLI is experimental (configured from their docs, not yet checked in a real session).
It is one binary for Windows, macOS and Linux. There is no daemon and no network listener: a SQLite file is the only shared state (ADR 0001).
What you get
- Rules that allow, deny or ask, by agent, tool and argument. The first match wins. The same rules apply to MCP tools and to built-in tools such as the shell, in all four CLIs, and a repository can add project rules that only make them stricter.
- Approvals. A call your rules ask about waits until you press
ain the terminal UI, or is denied after 50 seconds by default. - Receipts. Every call gets a hash-chained receipt, and
derbent verifynames the first receipt where the chain breaks after one was edited, moved, inserted or removed. Keep the head hash it prints to catch the newest ones being deleted too.
Also:
- Shared memory and handoffs. Agents keep notes per repository and can leave tasks for each other.
- Pins hold back a downstream server's tool when its definition changes.
- Budgets stop an agent stuck in a loop.
Install
Download the binary for your system and SHA256SUMS from the latest release, check the hash, and put it on your PATH as derbent (derbent.exe on Windows):
# Linux on amd64; the other files differ only in the end of the name
curl -LO https://github.com/tunahanaliozturk/derbent/releases/download/v1.0.0/derbent-v1.0.0-linux-amd64 curl -LO https://github.com/tunahanaliozturk/derbent/releases/download/v1.0.0/SHA256SUMS sha256sum --ignore-missing -c SHA256SUMS install -m 755 derbent-v1.0.0-linux-amd64 ~/.local/bin/derbent
Or build it with Go 1.27 or later:
go install github.com/tunahanaliozturk/derbent/cmd/derbent@latest
Homebrew (brew install tunahanaliozturk/tap/derbent) and Scoop install it too; see Install and set up.
Every release can be rebuilt byte for byte from its tag. Install and set up has the other systems, how to check a release, and each CLI's entries by hand.
Quick start
derbent init --preset balanced # add Derbent to each CLI it finds, and write a first config
derbent doctor # check what init wrote derbent # open the terminal UI in a terminal of its own
derbent init shows every change and asks once before it makes any. It copies each file it changes first and never replaces an entry you already have. With --dry-run it only shows the changes. Two of them, from a real run with the paths shortened:
claude: ~/.claude.json
copied first to ~/.claude.json.derbent-backup-20260930T205424Z runs: claude mcp add --scope user derbent -- ~/bin/derbent mcp --agent claude derbent: ~/.config/derbent/config.toml a new file adds the balanced preset (derbent init --preset balanced --print shows it)
It also adds the derbent gate hook to each CLI's settings; Install and set up shows every entry. Start your agents as usual. Their calls now appear in the UI, and calls the rules ask about wait there for you. Built-in tools says what each CLI's hook covers.
To put your other MCP servers behind the gate, so each agent needs only the one derbent entry, see Downstream servers.
How a call is decided
Rules live in config.toml in your user config directory (%AppData%\derbent\ on Windows, ~/.config/derbent/ on Linux, ~/Library/Application Support/derbent/ on macOS). A downstream MCP server's tools are named __ , and a CLI's built-in tools native__ :
[[rule]]
tool = "github__issue_read" action = "allow"
[[rule]] tool = "github__*" # every other GitHub tool waits for you action = "ask"
[[rule]] agent = "claude" tool = "native__Bash" # Claude Code's shell, through the hook args = { command = "git push*" } action = "ask"
[[rule]] action = "allow" # the last rule has no condition
To see how a call would be decided before it happens:
derbent explain --agent claude --tool native__Bash --args '{"command":"git push origin main"}'
It prints each rule and why it matches or not, down to the first match, then the project's rules, budgets, pin and grant, and ends with verdict: ask (rule:3) for this call under the rules above. Rules covers globs, the three presets (watch, balanced, strict), project rules, budgets and rule suggestions.
Receipts
derbent verify # count, head hash, and whether the chain is intact
derbent receipts --agent codex --since 1h # also --tool, --project, --limit, --json
A receipt keeps the arguments after masking secrets, and only the size and hash of what a tool returned (ADR 0004). Someone who can write the database could still rewrite the whole chain or delete the newest receipts, so keep the head hash somewhere else if you want to be able to tell later. Receipts and verify covers exports that can be checked without the database.
Commands
| Command | What it does | More |
|---|---|---|
derbent | Terminal UI: waiting calls, agents, live receipts, memory, grants | Approvals |
derbent init, derbent doctor | Add Derbent to each CLI, then check the setup | Install |
derbent mcp --agent | The MCP server each CLI starts | Install |
derbent gate --agent | The pre-tool hook for built-in tools | Built-in tools |
derbent pending, approve, deny | Answer waiting calls from any shell | Approvals |
derbent grants, revoke | List and take back session grants | Approvals |
derbent explain | Show how a call would be decided | Rules |
derbent suggest | Print the rules your answers point to | Rules |
derbent config check | Validate the config and list each server's tools | Servers |
derbent pins | See and accept changed downstream tools | Servers |
derbent receipts, verify | Read, export and verify receipts | Receipts |
derbent handoffs | List the tasks agents left for each other | Memory and handoffs |
derbent version | Print the release |
Overhead
Measured on GitHub's hosted runners on 2026-10-01 (Linux on an Intel Xeon Platinum 8370C, Windows on an AMD EPYC 9V74, 4 vCPUs each), median of ten runs at p50, from docs/benchmark-results:
| Linux | Windows | |
|---|---|---|
| MCP tool call, direct to the server | 256.5 µs | 293.0 µs |
| MCP tool call, through the gate | 756.0 µs | 909.0 µs |
| Starting the binary and exiting | 4.292 ms | 40.40 ms |
Hook call, derbent gate, allowed | 6.421 ms | 64.51 ms |
The gate adds 499.5 µs to an MCP call on Linux and 616.0 µs on Windows, for the extra stdio hop, the rule decision, the project rules check and the receipt written to SQLite. A hook call costs about 2.1 ms more than starting the binary on Linux and 24 ms more on Windows, where most of its cost is the process start. The numbers come from one run on shared runners, and runs differ by more than one run's intervals: the day before, the same code on the same Windows CPU model put the gate 459.5 µs over a direct MCP call, against 616.0 µs here. The results page has p99, calls per second and the caveats.
Limits
The whole list, with the reasons, is under Known limits and risks. The ones to know first:
- Only calls that pass through the gate are seen. Tools a CLI never shows its hook, such as Codex's hosted web search, are outside it.
- The CLIs marked experimental at the top have entries and hook adapters that follow each CLI's documentation and have not been checked in a real session. Claude Code and Copilot CLI (1.0.88, on 2026-10-02) have.
- Argument globs match strings, not meaning:
git push*does not matchcd repo && git push. - Approvals guard against mistakes and prompt injection inside MCP. They do not stop an agent that can already run shell commands as you: it can run
derbent approveitself. - A receipt export shows its last run unchanged only against a head you kept, and never that nothing was left out of it.
- A suggestion refuses the shells, launchers and operators it knows, but a text rule can be fooled and those lists cannot be complete, and an
allowfor a command prefix lets any options through. - A handoff's address is a label, not an identity: any agent that can call
handoff_takecan claim every open handoff addressed to*. - Approvals depend on you watching. Unattended,
askmeans denied after the timeout. - Pins trust the first definition they see, including a new tool that an update adds to a pinned server, so name the tools you allow for a server who