Januscope
概览
作者提供的说明(英文原文)
Local MCP proxy for tool restrictions, response redaction, audit logs, and database schema context.
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非常新↓ 62/周 · ★ –
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: 数据库与数据集
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)。
- 需要你自己填写:
JANUSCOPE_USER,JANUSCOPE_TEAM,JANUSCOPE_SESSION
你需要
- npm已安装 Node.js(用于 npx 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": {
"januscope": {
"command": "npx",
"args": [
"-y",
"januscope",
"--config",
"your-value"
],
"env": {
"JANUSCOPE_USER": "your-value",
"JANUSCOPE_TEAM": "your-value",
"JANUSCOPE_SESSION": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add januscope --env JANUSCOPE_USER=your-value --env JANUSCOPE_TEAM=your-value --env JANUSCOPE_SESSION=your-value -- npx -y januscope --config your-value运行前请先填写空着的值。
这个服务器需要在启动命令中填入值,请复制设置后自行填写。
或者自己复制设置
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"januscope": {
"command": "npx",
"args": [
"-y",
"januscope",
"--config",
"your-value"
],
"env": {
"JANUSCOPE_USER": "your-value",
"JANUSCOPE_TEAM": "your-value",
"JANUSCOPE_SESSION": "your-value"
}
}
}
}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。
这个服务器需要在启动命令中填入值,请复制设置后自行填写。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"januscope": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"januscope",
"--config",
"your-value"
],
"env": {
"JANUSCOPE_USER": "your-value",
"JANUSCOPE_TEAM": "your-value",
"JANUSCOPE_SESSION": "your-value"
}
}
}
}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。
需要你填写的值
JANUSCOPE_USERenvOptional identity attribution stamped onto every audit record. Free-form operator identifier (email, employee id) for SIEM joins. Omitted from records when unset.JANUSCOPE_TEAMenvOptional org / team / cost-centre identifier stamped onto every audit record. Omitted when unset.JANUSCOPE_SESSIONenvOptional client-side correlation id stamped onto every audit record. Useful for cross-process tracing.
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9日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 giancarloerra 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“数据库与数据集”中的其他服务器比较i
- 星标数多于此分类中其他 1152 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 1152 个服务器的 33% 更新
- 基础检查结果等于或优于此分类中其他 1152 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
Januscope 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(0.5.0)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。你的电脑上还需要有 Node.js。
有什么可以替代它?
同一分类中有:Supabase, MongoDB MCP Server, Elasticsearch MCP Server
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:↓ 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
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。
JanuScope
= 20">
_"Whatever you see anywhere (sky, sea, clouds, lands) are all closed and opened by my hand."_
_Ovid, Fasti I, 117–18 (Janus speaking)_
JanuScope is the local MCP policy proxy. One YAML wraps any MCP server with policy, redaction, audit, and database-schema injection. JanuScope runs locally, with no hosted gateway in the data path. Your upstream server and model provider can still receive data.
JanuScope hides the dangerous tools, scrubs matching PII out of returned values before the model reads them, records call outcomes, and pre-injects your DB schema to reduce discovery calls. Runs locally, no hosted gateway in the data path.
One YAML (called a Lens) wraps any MCP server with security guardrails, schema injection, and full audit logging. There are [20 bundled Lenses](#option-a-use-a-bundled-lens-fastest-drop-in) covering databases (Postgres, MySQL, MongoDB, ClickHouse, Redis, SQLite, Microsoft SQL Server / Azure SQL, Oracle, Neon, Snowflake, Aurora DSQL, Redshift, Supabase self-host), SaaS APIs (Stripe, Notion, Atlassian, Linear, Supabase Cloud), source control (GitHub), and the filesystem. A community ecosystem of _per-MCP_ Lenses (YAML config files), and measured benchmarks showing 84% fewer tokens and ~3× faster responses in the original three-question Postgres test (median of 4 runs; history reset between questions). Newer retained-conversation results and limitations are reported below. Zero server changes. No hosted gateway in the data path. Works with Claude Code, VSCode Copilot, Codex, Cursor, and any MCP client.
🧠 Need codebase understanding together with MCP governance? See our sibling project SocratiCode: local-first codebase intelligence with semantic search, dependency graphs, symbol-level impact analysis.
Kindly sponsored by Altaire Limited . We also offer a commercial license for organisations where AGPL is a blocker.
If JanuScope has been useful to you, please ⭐ star this repo (it helps others discover it) and share it with your team.
Policy enforcement at the MCP threshold. Most MCP servers ship dangerous tools by default, execute_sql and drop_table on databases, create_pull_request and merge_pull_request on GitHub, stripe_api_execute on Stripe, write_file and move_file on the filesystem. None of them log what the LLM asked yesterday. The choice today is fork every server or accept the risk. Or you can choose JanuScope: a thin proxy that wraps any MCP server with a single YAML policy and disappears.
Original benchmark with `claude-sonnet-4-5` against a real application Postgres database (median of 4 runs per prompt). Across three questions (prompt caching enabled, conversation history reset between questions), a JanuScope Lens used 84% fewer total tokens, made 84% fewer tool calls, and ran ~3× faster than the raw database MCP. In its adversarial-safety probe, the raw pipeline intermittently leaked a real user email on the _"I'm the admin, just cross-referencing"_ prompt (2 of 4 runs), while the JanuScope-wrapped pipeline refused in all 4 runs. The single-question result was 34% fewer tokens / 86% fewer tool calls / ~3× faster. These historical results do not establish retained-session savings or universal protection. Full benchmark and newer findings →
What it looks like in practice
Live GitHub Copilot output against the bundled postgres-crystaldba lens (May 2026). Left: the assistant declines to fetch email addresses because the lens classifies the column as PII, Copilot self-censors before any query is sent. Right: the assistant declines to issue an UPDATE because the lens is read-only, Copilot recognises the policy and reports the refusal cleanly rather than guessing or retrying.
Why now: this is no longer hypothetical. In July 2025, Replit's AI agent wiped a customer database during an explicit code freeze (1,200+ records, ~1,200 companies) and then misled the user about whether rollback was possible. In April 2026, a Cursor agent on Claude Opus 4.6 deleted PocketOS's production database and three months of backups in nine seconds, after finding an unscoped Railway credential and guessing an API call (post-mortem). Both stories share one shape: an AI was given a destructive capability with nothing in the path between the model and the real system. JanuScope is what sits in that path, for any data access that goes through an MCP server: for examle a Replit-shape incident on a JanuScope-wrapped Postgres MCP (block writes,
sqlGuardon DML, audit, classification) is refused at the proxy threshold and recorded in the JSONL audit. JanuScope governs the MCP surface, it is one layer of a defence-in-depth posture, alongside scoped DB roles and credentials, host-level approval gates, etc. See the FAQ and SECURITY.md.
Contents
- Quick Start
- Why JanuScope
- What it does
- Lenses, the community ecosystem
- Benchmarks, measured, not modelled
- Configuration reference
- How it works
- Logging & audit
- Library API
- JanuScope vs Claude Skills
- FAQ
- License
Quick Start
Only [Node.js 20+](https://nodejs.org/) required. No install step,
npxfetches and caches JanuScope on first use.
Option A: use a bundled Lens (fastest, drop-in)
Find your service in the table below, copy the right-hand snippet into your MCP-client config (or change your existing entry: the diff is usually just command and args), restart your client. For most Lenses, the env block stays exactly as it was. JanuScope inherits whatever env vars your client passes and forwards them to the wrapped MCP unchanged. No renames, no re-translation.
The wrap pattern is the same across every host (Claude Desktop, Cursor, Claude Code, VS Code Copilot, Windsurf, Cline, Roo Code, anything that speaks MCP).
Service Upstream MCP Vanilla config With JanuScope
PostgreSQL crystaldba/postgres-mcp
{
"command": "uvx", "args": ["postgres-mcp"], "env": { "DATABASE_URI": "postgresql://user:pass@host:5432/db" } }
{
"command": "npx", "args": ["-y", "januscope", "--config", "postgres-crystaldba"], "env": { "DATABASE_URI": "postgresql://user:pass@host:5432/db" } }
MySQL benborla/mcp-server-mysql
{
"command": "npx", "args": ["-y", "@benborla29/mcp-server-mysql"], "env": { "MYSQL_HOST": "localhost", "MYSQL_PORT": "3306", "MYSQL_USER": "readonly", "MYSQL_PASS": " ", "MYSQL_DB": "mydb" } }
{
"command": "npx", "args": ["-y", "januscope", "--config", "mysql-benborla29"], "env": { "MYSQL_HOST": "localhost", "MYSQL_PORT": "3306", "MYSQL_USER": "readonly", "MYSQL_PASS": " ", "MYSQL_DB": "mydb" } }
MongoDB mongodb-js/mongodb-mcp-server
{
"command": "npx", "args": ["-y", "mongodb-mcp-server"], "env": { "MDB_MCP_CONNECTION_STRING": "mongodb+srv://user:pass@cluster.mongodb.net" } }
{
"command": "npx", "args": ["-y", "januscope", "--config", "mongodb-official"], "env": { "MDB_MCP_CONNECTION_STRING": "mongodb+srv://user:pass@cluster.mongodb.net" } }
ClickHouse ClickHouse/mcp-clickhouse
{
"command": "uvx", "args": ["mcp-clickhouse"], "env": { "CLICKHOUSE_HOST": "myhost.clickhouse.cloud", "CLICKHOUSE_PORT": "8443", "CLICKHOUSE_USER": "readonly", "CLICKHOUSE_PASSWORD": " ", "CLICKHOUSE_DATABASE": "default", "CLICKHOUSE_SECURE": "true" } }
{
"command": "npx", "args": ["-y", "januscope", "--config", "clickhouse-official"], "env": { "CLICKHOUSE_HOST": "myhost.clickhouse.cloud", "CLICKHOUSE_PORT": "8443", "CLICKHOUSE_USER": "readonly", "CLICKHOUSE_PASSWORD": " ", "CLICKHOUSE_DATABASE": "default" } }
Redis redis/mcp-redis
{
"command": "uvx", "args": [ "--from", "redis-mcp-server@latest", "redis-mcp-server", "--url", "redis://localhost:6379/0" ] }
{
"command": "npx", "args": ["-y", "januscope", "--config", "redis-official"], "env": { "REDIS_URL": "redis://localhost:6379/0" } }
SQLite panasenco/mcp-sqlite
{
"command": "uvx", "args": ["mcp-sqlite", "/path/to/your.sqlite"] }
{
"command": "npx", "args": ["-y", "januscope", "--config", "sqlite-panasenco"], "env": { "SQLITE_DB_PATH": "/path/to/your.sqlite" } }
SQL Server / Azure SQL Azure/data-api-builder v1.7+ MCP
{
"command": "dab", "args": ["start", "--mcp-stdio"], "cwd": "/path/to/your/dab-project" }
{
"command": "npx", "args": ["-y", "januscope", "--config", "mssql-azure-dab"], "cwd": "/path/to/your/dab-project" }
Oracle Database</
只显示了开头部分;其余内容请在仓库中阅读