@privacyscrubber/mcp-server
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 1 of 3 tools tried
Contacts while installing and starting: nothing
Its tool definitions changed since version 2.4.8. If you approved the earlier ones, read them again.
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y -p @privacyscrubber/mcp-server@2.5.1 mcp-server
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
3 tools that take no input and look read-only were called once with nothing. 1 returned a result.
check_status | No usable answer tool reported an error: Error executing tool: ENOENT: no such file or directory, uv_resident_set_memory |
guard_session_info | No usable answer tool reported an error: Error executing tool: ENOENT: no such file or directory, uv_resident_set_memory |
ztds_info | Returned a result under 0.1 s · 327 characters |
During the calls it contacted nothing it had not already contacted.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
4 tools with commands in capitals or very long text
- Gives the agent orders in
audit_context:valuates PII, secrets, risk severity (CLEAN, LOW, MODERATE, CRITICAL), and triggered regulatory frameworks (GDPR, HIPAA, SOC 2, PCI DSS) with zero text mutation.
- Gives the agent orders in
sanitize_text:STEP 1: Call this first. You MUST NOT process raw user data before calling this. Locally scrubs PII, secrets, and credentials (like A
- Gives the agent orders in
reveal_text:STEP 3: Call this last. You MUST pass your final generated response through this tool to restore tokens (e.g., [EMAIL_1]) back with
- Gives the agent orders in
ztds_audit:Inspects text in RAM and returns riskLevel (CLEAN/MODERATE/CRITICAL), entity breakdown, SHA-256 contentHash, and RFC v1.0 compliance flags without persisting session s
Common and usually harmless: it is how many makers stress how a tool should be used.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
audit_context text, profile, sector, format
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.
sanitize_text text, profile, sector, compact, ignore_list, session_id
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)
reveal_text text, stream, flush, session_id
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).
stream_reveal_text chunk, flush, reset, session_id
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.
sanitize_file file_path, profile, sector, compact, session_id
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.
23 more tools
audit_directory_for_pii directory_path, profile, sector, extensions, ignore_node_modules
Scans a local directory for leaks of secrets, keys, and PII. Returns a summary report. Use this tool for Security Auditing.
redact_file file_path, profile, sector, dry_run, no_backup
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.
create_default_config
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.
generate_compliance_report format, company_name, department, session_id
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.
mark_false_positive token, session_id
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.
check_status
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.
guard_exec command, cwd, profile, sector, timeout_ms, session_id
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.
guard_read_file file_path, profile, sector, max_lines, session_id
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.
guard_git_diff staged, cwd, profile, sector, session_id
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.
guard_apply_patch file_path, content, create_backup, session_id
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.
create_agent_rules agent_types, workspace_dir
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.
guard_unmask_args tool_args, session_id
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.
guard_session_info session_id
Zero-Trust Agentic Guard: Returns diagnostic metrics on active in-memory sessions, token counts, and memory footprint with zero plaintext leakage.
guard_session_reset session_id, all
Zero-Trust Agentic Guard: Explicitly purges the in-memory token map for a specific session_id or all sessions upon agent task completion.
guard_rag_chunk chunks, profile, sector, session_id
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.
guard_rag_restore results, session_id
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.
export_audit_log format, session_id, destination_file, company_name, department, text
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.
generate_procurement_memo target_tier, app_name, developer, team_size, estimated_volume, format
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).
ztds_sanitize text, sessionId, profile, sector
Drop-in ZTDS RFC v1.0 sanitization tool. Redacts sensitive PII, PHI, and credentials locally in process RAM using deterministic reversible surrogate tokens, scoped to sessionId, with zero network egress.
ztds_restore text, sessionId
Drop-in ZTDS RFC v1.0 restoration tool. Rehydrates surrogate tokens back into original cleartext using the local in-memory session table without modifying or deleting the session.
ztds_audit text, profile, sector
Drop-in ZTDS RFC v1.0 read-only dry-run audit. Inspects text in RAM and returns riskLevel (CLEAN/MODERATE/CRITICAL), entity breakdown, SHA-256 contentHash, and RFC v1.0 compliance flags without persisting session state.
ztds_info
Returns ZTDS RFC v1.0 specification metadata, protocol invariants, baseline entity categories, and current local PrivacyScrubber license/profile capability status.
ztds_reset_session sessionId
Irreversibly zeroizes volatile in-memory surrogate token mappings for a specific sessionId or all active sessions.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | SEE LICENSE IN LICENSE.md |
|---|---|
| Needs | not stated |
| Source | github.com/moxno/privacyscrubber-mcp |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-7Q2aGxgVCCFwE6nIxK54Af8+/AmpHbCpRG/6Jxxze8KvocC/MhiZBUUgP6MEVnFORyyYs+J30UAMIMCjMif9Vw== |
Versions reported
| Version | Run | Result | Tools |
|---|---|---|---|
| 2.5.1 | 2026-11-16 | Starts with no setup | 28 |
| 2.4.8 | 2026-11-12 | Starts with no setup | 23 |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/%40privacyscrubber/mcp-server)
New version out? Ask for a fresh report.