anonym.legal

By · Last updated 2026-02-22

Kembali ke BlogTeknikal

Gunakan Claude & ChatGPT Tanpa Membocorkan PII

Panduan pembangun untuk menggunakan pembantu AI dengan selamat. Sediakan integrasi Pelayan MCP untuk perlindungan PII yang telus dalam Claude Desktop, Cursor, dan VS Code.

February 22, 20267 min baca
MCP ServerClaude DesktopCursor IDEsecure AIdeveloper tools

Dilema Pembangun

Anda sedang melakukan debug masalah pengeluaran. Jejak tindanan mempunyai alamat e-mel pelanggan di dalamnya. Pembetulan terpantas? Tampalkan ke dalam Claude dan minta bantuan.

Tetapi data itu kini:

  • Disimpan dalam sistem Anthropic
  • Mungkin digunakan untuk latihan model, bergantung pada pelan anda
  • Boleh dilihat oleh sesiapa yang boleh mengakses sejarah perbualan anda

77% pembangun menampal data sensitif ke dalam alat AI. Kebanyakan tidak menyedari masalah itu sehingga kemudian.

Cara Proksi Menyelesaikan Ini

Protokol Konteks Model (MCP) membolehkan pelayan duduk antara anda dan mana-mana alat AI. Pelayan MCP anonym.legal menggunakan kedudukan itu untuk melucutkan PII sebelum teks anda mengenai mana-mana model.

Ia berfungsi dalam empat langkah:

  1. Anda menaip gesaan seperti biasa
  2. Proksi menangkapnya sebelum menghantar
  3. PII ditemui dan ditukar dengan token yang boleh diterbalikkan
  4. AI hanya melihat teks bersih yang dianonymkan

Balasan AI kembali dengan nilai sebenar dipulihkan. Aliran kerja anda tidak berubah.

Menyediakan Integrasi

Apa Yang Anda Perlukan

  • Node.js 18 atau lebih baru
  • Claude Desktop, Cursor, atau VS Code dengan sambungan Claude
  • Kunci API anonym.legal — dapatkan satu percuma

Langkah 1: Dapatkan Kunci API Anda

  1. Daftar di anonym.legal/auth/signup
  2. Pergi ke Tetapan → Token API
  3. Buat token baharu
  4. Salinnya — anda hanya melihatnya sekali

Langkah 2: Konfigurasikan Claude Desktop

Sunting fail konfigurasi untuk OS anda:

macOS: `/Library/Application Support/Claude/claude_desktop_config.json`
Windows: `%APPDATA%\Claude\claude_desktop_config.json`
Linux: `/.config/Claude/claude_desktop_config.json`

Tambah pelayan anonym.legal:

```json { "mcpServers": { "anonym-legal": { "command": "npx", "args": ["-y", "@anonym-legal/mcp-server"], "env": { "ANONYM_API_KEY": "your-api-key-here" } } } } ```

Langkah 3: Mulakan Semula Claude Desktop

Tutup dan buka semula aplikasi. Anda akan melihat "anonym-legal" disenaraikan di bawah pelayan aktif.

Persediaan Cursor IDE

Cursor menggunakan protokol yang sama. Tambah ini ke `.cursor/mcp.json`:

```json { "mcpServers": { "anonym-legal": { "url": "https://anonym.legal/mcp", "transport": "sse", "headers": { "Authorization": "Bearer your-api-key-here" } } } } ```

Apa Yang Dianonymkan

Pelayan menangkap lebih 285 jenis entiti merentasi 48 bahasa:

KategoriContoh
PeribadiNama, e-mel, nombor telefon, DOB
KewanganKad kredit, akaun bank, IBAN
KerajaanSSN, nombor pasport, lesen memandu
TeknikalAlamat IP, kunci API, token
Penjagaan kesihatanID pesakit, nombor insurans
KorporatID pekerja, nombor akaun

Contoh Transformasi

Gesaan anda: ``` Debug this error from user john.smith@acme.com: Payment failed for card 4532-1234-5678-9012 Customer ID: CUST-12345, IP: 192.168.1.100 ```

Apa yang model lihat: ``` Debug this error from user [EMAIL_1]: Payment failed for card [CREDIT_CARD_1] Customer ID: [CUSTOMER_ID_1], IP: [IP_ADDRESS_1] ```

Balasan yang anda lihat: ``` The error for john.smith@acme.com suggests card 4532-1234-5678-9012 may have low funds... ```

Anda melihat nilai sebenar. Model hanya pernah melihat token.

Pilihan Lanjutan

Corak tersuai — tambah regex anda sendiri ke pembolehubah persekitaran `CUSTOM_PATTERNS`:

```json "CUSTOM_PATTERNS": "JIRA-[0-9]+,TICKET-[A-Z0-9]+" ```

Senarai dibenarkan — elakkan nama awam daripada disamarkan:

```json "ALLOWLIST": "Anthropic,Claude,anonym.legal" ```

Nyahdayakan jenis entiti — biarkan kategori tertentu melalui:

```json "DISABLED_ENTITIES": "PHONE_NUMBER,URL" ```

Di Mana Pemprosesan Berlaku

KomponenLokasi
Pelayan MCPMesin anda
Pengesanan PIIPelayan anonym.legal (Jerman)
Model AIPelayan Anthropic / OpenAI

Proksi berjalan pada mesin anda. Hanya panggilan pengesanan pergi ke anonym.legal. Gesaan anda tidak disimpan. Lihat dasar privasi untuk butiran.

Harga

Integrasi disertakan dalam semua pelan:

PelanToken/bulanHarga
Percuma200€0
Asas2,000€3/bulan
Pro10,000€15/bulan
Perniagaan50,000€29/bulan

Kebanyakan pembangun kekal pada Asas pada €3/bulan.

Kesimpulan

Alat AI kini adalah sebahagian daripada kerja pembangunan harian. Mereka tidak perlu melihat data pelanggan anda untuk berguna. Proksi menguruskan itu untuk anda.

Integrasi:

  • Tidak memerlukan perubahan aliran kerja
  • Berfungsi dengan Claude Desktop, Cursor, dan VS Code
  • Menjaga PII pada setiap gesaan, setiap masa
  • Berharga €3/bulan untuk kebanyakan pembangun

Sediakan sekali. Data anda selamat secara lalai.

Sumber

Artikel Berkaitan

Teknikal

Cross-Platform PII: Mac, Linux, and Windows

Privacy officers on Mac, legal on Windows, data engineers on Linux — all processing the same data with different tools. Here's why OS-agnostic detection.

Teknikal

Cross-Application PII: Word, Chrome, and AI

Customer data flows from browser research to Word drafts to Claude prompts. Each context switch is a potential leakage point.

Teknikal

GDPR in App Logs: JSON PII Compliance

Application logs contain customer email addresses, IPs, and account numbers that GDPR Article 5(1)(e) requires be managed.

Sedia untuk melindungi data anda?

Mulakan pengenalan PII dengan 285+ jenis entiti dalam 48 bahasa.

Mulakan Percubaan PercumaLihat Ciri-ciri

About this page

We update this page when our platform or the law changes.

Read our founder note for how we work.

Each change shows up in the timestamp at the top.

Related reading

We follow these rules

  • GDPR (EU 2016/679).
  • ISO/IEC 27001:2022.
  • NIS2 (EU 2022/2555).
  • HIPAA safe harbor under 45 CFR § 164.514(b)(2).

Our promise

We do not sell your data.

We do not train models on your text.

We store your files in Germany.

You can delete your account at any time.

You own your work.

Where we run

Our servers live in Falkenstein, Germany.

We use Hetzner. They hold ISO 27001 certification.

All data stays in the EU.

Backups run every day.

Need help?

Email support@anonym.legal.

We reply within one business day.

How we test

We run a full check suite on every release.

Each surface gets its own sweep script and report.

Human reviewers spot-check the output each week.

We track recall and precision on a labelled set.

Bad runs block the deploy.

What we never do

  • We never sell your information to third parties.
  • We never train models on what you upload.
  • We never keep your work after you delete it.
  • We never share keys with any outside firm.
  • We never run ads inside the product.

Plans in plain words

We sell credits, not seats.

One credit covers one short job.

Long jobs use a few credits each.

You can top up at any time.

Unused credits roll over each month.

Read the plans page for current rates.

Who built this

A small team of engineers and lawyers built this.

We ship from Europe and work in the open.

Our founder note spells out why we started.

Where to start

How the parts fit

A browser add-on cleans text inside Chrome.

A Word plug-in handles drafts in Office.

A small desktop tool works on whole folders.

An agent protocol link feeds large models safely.

All four share one core engine and one rule set.

Words from our team

We started this work after a lunch about cookies.

One friend kept getting odd ads on her phone.

We asked why a court file leaked through a draft.

We sketched the first build on a napkin that week.

By month three we had a tiny demo for a friend.

She used it on her first case the next day.

Common questions we hear

Can the tool read scanned PDFs? Yes, with OCR.

Does it work on long files? Yes, in small chunks.

Can I roll my own rule set? Yes, save it as a preset.

Does it run offline? The desktop build runs offline.

Do you keep my files? No, the cloud build wipes after each run.

Will it learn from my work? No, we never train on inputs.

A short tour of the workflow

Upload a file or paste a snippet of prose.

Pick the entities you want gone from the draft.

Choose a method: replace, mask, hash, encrypt, or redact.

Press run and watch the side panel show each hit.

Skim the result and tweak any rule that misfired.

Save the cleaned file or send it to a teammate.