The Nexis node finds names, emails, card numbers, health and ID numbers in your text, then redacts, masks or encrypts them before the text reaches ChatGPT, your CRM or a third party. Detection follows the regulation you choose.
Verification by n8n in progress. Available now for self-hosted n8n, and on n8n Cloud through the HTTP Request node.
Add Nexis before any step that sends text outside your workflow. For AI steps, encrypt the personal data first, let the model do its work, then decrypt the answer with your own key.
Replaces each value with its type.
Choose a country and regulation, such as UK GDPR or HIPAA. Nexis looks for the personal data that regulation covers, including local IDs like NHS, National Insurance and Social Security numbers.
Seven methods: redact, replace with the type, mask, hash, tokenize, swap in realistic fake values, or encrypt so you can restore it later.
Process every type of personal data, only the types you pick, or everything except some. Add an allow list of values to keep and a deny list of values to always hide, like a project code name.
Your plan sets how many regulations you can use.
United Kingdom
Germany
English and German textUnited States
Canada
Australia
Sign up for Nexis with your work email. Approval usually takes minutes. Then create a key in the dashboard under API Integration.
Self-hosted: Settings → Community Nodes → Install, enter n8n-nodes-nexis. For Docker, see the README.
n8n Cloud: install from the nodes panel once n8n verifies the node. Until then, use the HTTP Request option below.
Create a Nexis API credential, paste your key and click Test. Leave the Base URL as it is unless you run a dedicated Nexis instance.
Add Nexis – PII Anonymizer, pick a Country – Regulation and a method, and map your text. Read the result from anonymised_text and pii_entity_count.
Connect Nexis as a tool for the AI Agent node. On self-hosted n8n, community nodes can only be used as tools when N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE=true is set.
The Encrypt method needs a second credential, Nexis Encryption Key API, holding a Fernet key. Generate one with either command, and keep it safe:
node -e "console.log(require('crypto').randomBytes(32).toString('base64url') + '=')"python -c "from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())"Use the Decrypt Text operation with the same key to restore the values. Ask your AI model to keep the <<ENC:...:ENC>> markers unchanged in its answer.
POST, URL https://api.nexis.intelation.com/api/text/Authorization, value Bearer YOUR_API_KEY{
"text": {{ JSON.stringify($json.message) }},
"regulation": "UK GDPR",
"country": "United Kingdom",
"language": "en",
"anonymisation_method": "redact"
}Use a regulation and country included in your plan.
Can't find your answer? Talk to us.
pii_entity_count in your workflow, add values you always want hidden to the deny list, and review high-risk flows.