anonym.legal
Վերադառնալ բլոգինՏեխնիկական

Ogtagereck Claude ev ChatGPT-n Aranc PII Arttahosqi

AI ashkhatakayneri anvtang ogtagortsutyun: Tvagir ughekaychy kazzmutyunn e MCP Server integracian pahapanutyyan hamar Claude Desktop, Cursor ev VS Code-um:

February 22, 20267 րոպե կարդալ
MCP ServerClaude DesktopCursor IDEsecure AIdeveloper tools

Tsragri Hayeckayin Bakhdy

Du debug-um es artagorcutyan khorin: Stack trace-y hivanti el. postay hascenner ka: Amena aragh lavagulyn? Kpchekl Claude-i mej ev kbakhtel:

Baits ayd tvyalnery ayjm:

  • Pahutsum en Anthropic-i unakumnery
  • Karogh en ogtagervel model uzhtavarutyann hamar, kalyatsyal jer planicen
  • Tershan en amjovakan mardkants, vok karogh e matis jer chat patmutyummany

Tsragrirneri 77%-y peri tvyalnery kpchum en AI gortsikneri mej: Shaterin khardelum chi nshmagrum meqnabanutyan mej stoghjanum:

Inchpes e Vstatman Lavaguyne Ays Khorin Kargelum

Model Context Protocol-y (MCP) hnaravor e talis serevor, vor nstvy du ev AI gortsikin mijevi: Anonym.legal-i MCP serervy ayd diren ogtagervy, vor hanetq PII-n nakhqan textd hasnum e harkaxoym modekin:

Aynen askhatum e cherry qaylerov:

  1. Du ktum es harcum sovorabar
  2. Vstatumam e gnaluc arraj bghum e
  3. PII-n gtnum e ev pastatasvum e verakangeli jeternerov
  4. AI-n miain tesnum e maqur, anonymizervats tekst

AI-i pataskhanumam galis e irakakan aryunqnerov verakangvats: Jer ashkhatanq chi paynasnum:

Integracian Kargazmakerpum

Inch e Petk

  • Node.js 18 kam avelyin
  • Claude Desktop, Cursor, kam VS Code Claude yndlarjutyumov
  • Anonym.legal API banan — stacek antchar

Qayl 1: Stacek jer API Banany

  1. Gransaverutyumam anomy.legal/auth/signup kaytqum
  2. Gnacel Settings → API Tokens
  3. Stanel nor nishuma
  4. Patchirek — miain mek angam e tesmenom

Qayl 2: Kazmavirirekeq Claude Desktop-y

Xmbagrek config faile jer OS-i hamar:

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

Avelacel anonym.legal serervy:

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

Qayl 3: Veramasnel Claude Desktop-y

Pagel ev verabanel yndarjakagiry: Ktesenq "anonym-legal" zyuypayin sererverum:

Cursor IDE Karzumakerpum

Cursor-n ogtagervy nuynak protocol: Avelacelkeq ays .cursor/mcp.json faili mej:

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

Inch e Anonymizervum

Serervery bgumy e 267+ tsain kategoria 48 lezunerum:

KategorianOrinakner
AndznayinAnuner, el. postay hascener, herekhosahamerum, tsnnundyan amsutyv
FinansakanVarkayan quteryi hamarner, bankayin hasviknery, IBAN-nery
KarravarayinSSN-ner, anjanagri hamarnery, vararordi vkayanagirer
TexnikakanIP hascenner, API bananerr, jetoner
AroghjakayinHivandi ID-nery, apahavarutyann hamarnery
KorportivAshkhatakayin ID-nery, hasvi hamarnery

Orinakeli Kayarperutyumam

Ber harcy: ``` 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 ```

Inch e tesnum modelumam: ``` Debug this error from user [EMAIL_1]: Payment failed for card [CREDIT_CARD_1] Customer ID: [CUSTOMER_ID_1], IP: [IP_ADDRESS_1] ```

Duk tesnum eq: ``` The error for john.smith@acme.com suggests card 4532-1234-5678-9012 may have low funds... ```

Du tesnum es irakakan aryunqner: Modelumam erkbeq likin jetoner e tesnum:

Lracukal Njaradnery

Khordakavarum nmucher — avelacelkeq jer regex CUSTOM_PATTERNS env vari mej:

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

Handarkagir — pahel hasum anuner khaldek qarapum enden:

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

Anaktivutyumam tsaineri tsainerb — tuylatreq voronq kategorianery ankum en.

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

Voropy e Katarum Mshakumy

BaguanatsaryKargachneli
MCP serveryJer maqarumam
PII ntaybanutyumamAnonym.legal serervernery (Germaniya)
AI modelayAnthropic / OpenAI serervernery

Vstatumamam ashkhatumam e jer maqarum: Miain ntaybanutyyan kavich hasum e anonym.legal: Jer harcumerny chi pahvum: Tes gaxtnuytyan qaghakakanutyan manamasnuytyan hamar:

Gnery

Integracian ner e bolor planerum:

PlanJetoner/amisGiny
Antchar200€0
Hashayin2,000€3/amis
Pro10,000€15/amis
Bznesh50,000€29/amis

Tsragrirneri mec masam mnum en Hashayin-um €3/amsov:

Endldrutyumam

AI gortsiknery oravayreri tsragri ashkhatavarki masy en: Nranq chi petq tesinein jer hakakakneri tvyalnery, vor ogtakar leyin: Vstatumamam xandum e ayd dery jer hamar:

Integracian:

  • Ashkhatavarqi paymanakunery petq chi paynaser
  • Ashkhatumam e Claude Desktop-i, Cursor-i ev VS Code-i het
  • Pahpanum e PII-n amsov bolor harcumum, amboghjutyamb
  • Narbek tsragrirneri hamar arjakhy e €3/amsov

Kazmavirireq mek angam: Jer tvyalnery lracelutsich anvtang en:

Akbyurner

Limitations / When this doesn't apply

Detection happens server-side and is not perfect: the proxy can miss an unusual identifier or one embedded in code or log output, and anything it misses reaches the AI provider in the clear — so for highly sensitive material, sanity-check the masked output rather than trusting every prompt blindly.

  • The proxy only protects traffic that flows through it. A teammate who pastes into the web UI directly, uses an AI surface not wired through MCP, or disables the server for a "quick question" bypasses it entirely; protection depends on consistent configuration across every tool and developer.
  • Tokens are reversible, so the mapping is sensitive. Under the GDPR, tokenized output is pseudonymized, not anonymized — treat it as personal data and protect the key accordingly.
  • You still trust the detection service and your own machine: the detection call goes to anonym.legal and the proxy runs locally with your API key, so a compromised machine or leaked key undermines the protection regardless of how well the proxy works.

Հոդվածներ, որոնք կապված են

Տեխնիկական

Presidio: 3-Week Setup vs Managed PII

Microsoft Presidio has thousands of GitHub stars and hundreds of open issues. Setup complexity, PySpark integration overhead, and Python dependency.

Տեխնիկական

6 Weeks to 3 Days: Managed PII Setup

Healthcare SaaS teams spend 6 weeks on self-hosted Presidio production deployment before switching to managed API. The managed API replaces the deployment.

Տեխնիկական

Free PII Detection Costs €13K/Year

Self-hosting Presidio requires 40-80 hours initial setup and 5-10 hours/month ongoing maintenance. At €100/hour engineering rates, that's €13,200+.

Պատրաստ եք պաշտպանելու ձեր տվյալները?

Սկսեք PII անանոնիմացնել 267+ կազմակերպության տեսակներով 48 լեզուներով:

Սկսեք անվճար փորձաշրջանԴիտել առանձնահատկությունները

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, held by our hosting provider.
  • 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 company HQ is in Saarbrücken, Germany. Our servers run in Hetzner's Falkenstein datacenter.

Hetzner holds 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

Automated checks run on every release.

Each surface gets its own sweep script and report.

Human reviewers spot-check the output each week.

We test detection against sample documents before each release.

A failing unit or integration run stops the release.

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.

Paid plans can buy top-up credits.

Credits reset at the end of each cycle.

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.