Securedact MCP server

SecuRedact MCP

<!-- mcp-name: io.github.GigantesHJI/securedact-mcp -->

SecuRedact is a local-first privacy and security layer for AI agents and AI workflows. It detects and protects sensitive data — personal data / PII, GDPR-sensitive information, credentials, API keys, tokens, secrets, and sensitive files — before that data reaches models, tools, files, or external destinations.

SecuRedact MCP is the Apache-2.0 open-source MCP server and reusable Python privacy engine. It detects sensitive text, applies versioned policies, redacts locally, and validates residual output before marking sanitized content approved.

MCP mode does not automatically intercept every prompt. The host must invoke

the tool and send only sanitized_text when status == "ok"; a misconfigured

or malicious MCP host can bypass that ordinary MCP workflow. Provider-native

enforced hooks are separate integration assets: when a supported provider

invokes such a hook at its prompt lifecycle boundary, it can apply the same

deterministic decision before normal model processing. See [SecuRedact

Enforced](docs/enforced.md).

Why SecuRedact

AI agents increasingly read files, call tools, and send prompts to external models. That exposes PII, credentials, and sensitive documents unless something checks the data first. SecuRedact is a privacy and security control for AI workflows:

machine. No network listener by default, no telemetry, no provider calls.

• Local-first — all detection, redaction, and policy evaluation run on your

special-category data are detected and pseudonymized or redacted.

• PII / GDPR detection — names, emails, IBANs, identifiers, and

detected and blocked from leaving your environment.

• Secret & credential protection — API keys, tokens, and passwords are

escapes and blocked from protected paths such as .env.

• Filesystem protection — reads are defended against traversal/symlink

run the same local decision before a prompt, model call, or tool action proceeds.

• AI Agent Privacy Firewall — enforced hooks for Claude Code and Gemini CLI

(internal/external/unknown) so policy can require approval or block egress.

• Network / egress awareness — outbound tool calls are classified

SecuRedact helps reduce exposure of sensitive data; it is not a guarantee of compliance or a claim that every leak is prevented. See Limitations.

HIPAA Safe Harbor (0.5.0)

SecuRedact 0.5.0 adds a HIPAA Safe Harbor mechanical-de-identification aid for 45 CFR 164.514(b)(2) text processing. It builds on the existing deterministic detection stack and adds an 18-category Safe Harbor mapping, US-specific identifiers (SSN with area/group/serial validation, US ZIP/ZIP+4, health-plan beneficiary, account numbers, ages over 89, VIN-format vehicle identifiers, fax), and an optional validated Flair PERSON-only gate for Category A (Names).

Use engine.hipaasafeharbor(text) or the HIPAASAFEHARBORPOLICY policy. This is a mechanical aid, not** a compliance certification: it cannot satisfy the actual-knowledge prong (164.514(b)(2)(ii)) or replace Expert Determination (164.514(b)(1)). See docs/hipaa-safe-harbor-profile.md and docs/hipaa-safe-harbor-gap-analysis.md.

Quick start

Install from PyPI and run the guided setup (Windows):

py -3.12 -m pip install "securedact-mcp[ml]"
securedact-mcp setup

Linux / macOS:

python3.12 -m pip install "securedact-mcp[ml]"
securedact-mcp setup

Protect a piece of text in seconds (deterministic-only demo, no model needed):

Shortened. The full README is on GitHub.