SDKs & integrations
MCP server
An MCP server that gives any AI agent reversible PII redaction. Your agent redacts personal data before a payload leaves (for another model, a tool or a third-party API), then restores the real values in the reply. It is a thin wrapper over the Obscate API.
Status: built and tested, not yet on PyPI. uvx obscate-mcp and pip install obscate-mcp work once the package is published; this page will drop this note then.
Known limitation: partial values come back wrong. If the agent (or a model downstream) quotes only part of a redacted value (“your card ending in 7588”), restore can’t fix it: it matches whole tokens, and a fragment isn’t one. With fpe this fails silently and plausibly: the fake card looks like a real card, so its last four digits look real, and your user sees a confident, wrong statement about their own data. Assistants do this often.
Measured with real Claude (claude-haiku-5-5, 3 runs each, a small test): plain fpe prompt, 2 of 3 replies stated wrong card digits; fpe plus the instruction below, 0 of 3; tokenize, 0 of 3.
For user-facing output, add to your system prompt: “When you mention a card number, email or phone number, repeat it exactly and in full as given. Never abbreviate, mask or quote part of it.” Or use strategy="tokenize": models don’t split [CREDIT_CARD_1]. This is a boundary of any reversible-redaction approach: a fragment of a stand-in can never map back to a fragment of the original.
| Tool | What it does | API units |
|---|---|---|
redact | redact a text; default fpe keeps formats and needs no map to restore | 1 per 100 KB |
restore | put the original values back | free |
detect | classify what PII a text contains (labels, offsets, counts) without changing it | 1 per 100 KB |
redact_json | redact values inside a JSON object/array; keys and shape are unchanged | 1 per 100 KB |
restore_json | restore any JSON reply | free |
list_entities | supported labels and strategies | free, no key |
Quickstart (about 3 minutes)
- Get a free API key (here): 1,000 requests a month at 60 a minute, no card. The key is shown once.
- Install with one of these:
uvx obscate-mcp --version # no install, runs from PyPI pip install obscate-mcp # or install into an environment - Add it to your MCP client (below), with the key in the
envblock. - Ask your agent: “Redact this before you send it to the CRM: Ravi Kumar, ravi@example.com, +91 98765 43210”.
Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"obscate": {
"command": "uvx",
"args": ["obscate-mcp"],
"env": { "OBSCATE_API_KEY": "ob_..." }
}
}
}
Claude Code
claude mcp add obscate --env OBSCATE_API_KEY=ob_... -- uvx obscate-mcp
Cursor
~/.cursor/mcp.json (global) or .cursor/mcp.json (per project). Use the same JSON block as Claude Desktop.
Configuration
| Env var | Default | |
|---|---|---|
OBSCATE_API_KEY | none | required for every tool except list_entities |
OBSCATE_BASE_URL | https://api.obscate.com | point at a self-hosted Obscate (the self-hosted edition is in pilot; ask contact@obscate.com) |
Do not commit config files that contain the key. obscate-mcp --transport streamable-http serves over HTTP instead of stdio.
Example agent flow
The agent has a customer record and must create a ticket in a third-party helpdesk tool, which should never see the raw PII.
user: File a ticket: Ravi Kumar (ravi@example.com, +91 98765 43210) was double-charged on card 4242 4242 4242 4242.
agent → redact_json({"json": {"customer": "Ravi Kumar", "email": "ravi@example.com",
"phone": "+91 98765 43210", "issue": "double-charged on card 4242 4242 4242 4242"}})
← {"redacted": {"customer": "[PERSON:…]", "email": "<email-shaped value>", "phone": "<phone-shaped value>",
"issue": "double-charged on card <valid-looking card number>"},
"type_changes": [], "keys_redacted": false, …}
agent → helpdesk.create_ticket(<the redacted object>) # the tool only sees redacted values
← {"ticket": 812, "summary": "Refund for [PERSON:…], reply to <email-shaped value>"}
agent → restore_json({"json": <the tool's reply>, "type_changes": []})
← {"json": {"ticket": 812, "summary": "Refund for Ravi Kumar, reply to ravi@example.com"}}
With strategy: "tokenize" the redacted values look like [EMAIL_1], and you pass the returned token_map to restore / restore_json. With fpe (the default) there is no map. See the fpe caveat about values a model invents.
What to expect
- Structured IDs (email, phone, cards, Aadhaar, PAN, GSTIN, IBAN, SSN, IPs, AWS keys) are near-perfect; names and places are best-effort (details).
- The server never logs, prints or stores the text, the detected values or the token map.
redactanddetectdon’t echo the original values back into the model’s context (detectcan, withinclude_values: true). - Verified: every tool above runs end to end against the hosted API over a real stdio connection. Not yet tried inside the Claude Desktop or Cursor apps themselves.