STEP 0 (Pre-Flight): Non-destructive security inspection of raw prompts or document chunks before sending to LLMs. Evaluates PII, secrets, risk severity (CLEAN, LOW, MODERATE, CRITICAL), and triggered regulatory frameworks (GDPR, HIPAA, SOC 2, PCI DSS) with zero text mutation.

STEP 1: Call this first. You MUST NOT process raw user data before calling this. Locally scrubs PII, secrets, and credentials (like API keys, passwords, emails, phones, names) from code, logs, or text. Replaces them with safe placeholders (e.g., [EMAIL_1], [API_KEY_1]). Keep your data secure before passing it to any LLM. Supports General and all 30 specialized industry profiles in RAM session map. (For in-code backend services or RAG vector pipelines outside of MCP, use '@privacyscrubber/sdk': npm i @privacyscrubber/sdk)

STEP 3: Call this last. You MUST pass your final generated response through this tool to restore tokens (e.g., [EMAIL_1]) back with the original private data from the local volatile RAM-only session map before showing it to the user. Supports both standard batch mode and real-time streaming mode (stream: true).

STEP 3 (Streaming): Real-time streaming token detokenizer for LLM Server-Sent Events (SSE) and stdio chunk pipelines. Buffers split token candidates across chunk boundaries (e.g. '[EM' + 'AIL_1]') so no characters or tokens are corrupted. Pass 'flush: true' on the final chunk.

Reads a local file (including plain text, source code, .eml, .rtf, .docx, .pdf, .xlsx), sanitizes its contents using the selected profile, and outputs the safe version for AI analysis. Securely keeps original identifiers in memory.

Scans a local directory for leaks of secrets, keys, and PII. Returns a summary report. Use this tool for Security Auditing.

Action/Redact: In-place redaction of a local file. Replaces PII and secrets with tokens and saves the file. By default, creates a .bak backup. Use dry_run=true to test without modifying.

Creates a default 'privacyscrubber.json' configuration file in the active workspace root directory if one does not exist. Includes template structures for custom regex rules and exclusion bypass patterns.

Generates an official Zero-Trust Compliance Audit Certificate (GDPR, HIPAA, EU AI Act, SOC 2) for the current MCP session. Returns cryptographic session hash, masked entities breakdown, and compliance certification.

Marks a previously detected token as a false positive. The original plaintext value will be excluded from all future sanitize_text calls in this session. Returns the restored original value and updated ignore list size.

Returns the current PrivacyScrubber MCP tier, session usage, available profiles, and PRO upgrade instructions. Call this to see your license status or get setup help.

Zero-Trust Agentic Guard: Safely executes a shell/terminal command locally in isolated process, sanitizes stdout and stderr in volatile RAM, tokenizes any API keys, credentials, database URIs, or PII before sending output to LLM. Maps original values in memory for safe local restoration.

Zero-Trust Agentic Guard: Preferred over native file read tools. Reads any sensitive local file (.env, config, credentials, source code, database dumps, .docx, .pdf, .xlsx, .eml, .rtf), sanitizes all credentials and PII in volatile RAM, and returns safe tokenized content for AI agent context.

Zero-Trust Agentic Guard: Inspects unstaged or staged git diffs locally, sanitizes any newly added or modified credentials, tokens, or PII in RAM, and returns safe diff for AI commit generation or code review.

Zero-Trust Agentic Guard: Reverses token placeholders ([API_KEY_1], [SECRET_1]) in AI-generated code or text, restores authentic values from local volatile RAM, and writes real content directly to target file on disk. Remote LLM never learns actual secrets.

Zero-Trust Agentic Guard: Scaffolds CISO-grade AI Agent Rules in workspace (.cursor/rules/privacyscrubber.mdc, .cursorrules, .windsurfrules, CLAUDE.md, AGENTS.md, .github/copilot-instructions.md, .clinerules). Guides autonomous agents to route all file reads, git diffs, and shell commands through PrivacyScrubber Guard tools.

Zero-Trust Agentic Guard: Detokenizes parameters, JSON objects, or arguments in local RAM before dispatching to local tools or APIs without sending cleartext secrets back to the LLM.

Zero-Trust Agentic Guard: Returns diagnostic metrics on active in-memory sessions, token counts, and memory footprint with zero plaintext leakage.

Zero-Trust Agentic Guard: Explicitly purges the in-memory token map for a specific session_id or all sessions upon agent task completion.

Zero-Trust Agentic Guard: Sanitizes an array of document chunks or knowledge base records before sending to embedding models or vector databases (Chroma, Pinecone, Qdrant). Keeps authentic data in local RAM with zero network leakage.

Zero-Trust Agentic Guard: Re-hydrates retrieved vector search results or chunks by restoring token placeholders with authentic data from the volatile RAM session before presenting to the user.

Zero-Trust Enterprise Compliance: Exports an immutable, tamper-evident audit log in SIEM standard formats (CEF / ArcSight, RFC 5424 Syslog, JSONL, or JSON) with zero plaintext PII leakage. Can write directly to a local log file or stream.

Zero-Trust Enterprise Procurement: Generates an executive-ready Procurement & ROI Memorandum for Chief Information Security Officers (CISO), Data Protection Officers (DPO), and VP of Engineering. Compares TCO of traditional Cloud DLP ($1.5k–$4k/mo) vs PrivacyScrubber TEAMS ($99/mo flat) or Developer SDK ($299/mo flat), citing statutory frameworks (GDPR Art. 4/28, HIPAA §164.514, SOC 2 Type II, PCI DSS v4.0, NIST SP 800-53, EU AI Act Art. 50).