Local MCP capabilities provider for Expo
Nothing to run from here
Ztds is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
99/100
trust score
14
downloads a day
local
runs on your machine
854
downloads in 30d
What it does
ZTDS MCP Server is the open-source reference implementation of the Zero-Trust Data Sanitization (ZTDS RFC v1.0) protocol for modern AI coding IDEs and agent workflows, including Cursor IDE, Claude Desktop, Claude Code, and Windsurf.
The Problem: Autonomous AI agents routinely scan repositories, indexing .env files, API tokens, database connection strings, customer records, and private codebases. When agents invoke tools or construct prompts, these sensitive strings are transmitted unmasked to frontier cloud LLMs, causing compliance violations and credential leakage.
The ZTDS Solution: ZTDS MCP acts as an in-memory security firewall operating 100% locally in device volatile memory (RAM). Before prompts or tool parameters cross the network, sensitive entities are automatically tokenized into context-preserving synthetic tokens (e.g. [API_KEY_TOKEN_1], [EMAIL_TOKEN_1]). When the LLM responds, the original values are restored locally in RAM. Cloud models never see the cleartext.
The 4 Fundamental Invariants (RFC v1.0):
- Invariant 1: Zero External Egress Prior to Sanitization — Cleartext PII, credentials, and secrets never leave the local execution boundary unmasked.
- Invariant 2: Deterministic Context-Preserving Reversible Tokenization — Surrogates preserve syntactic and grammatical context so transformer attention mechanisms remain accurate.
- Invariant 3: Ephemeral RAM Isolation (Theorem 2 Zeroization) — Bijective mapping tables exist solely in non-swappable volatile memory (
mlock) and are wiped immediately upon session reset. - Invariant 4: Subprocessor Chain Exclusion — Operates strictly as a local computing utility under GDPR Recital 26 and HIPAA Safe Harbor, eliminating the requirement for third-party Data Processing Agreements (DPAs).
1-Click Automated Setup:
Run the universal auto-configurator in your terminal:
npx ztds-mcp init
This automatically detects your installed clients (Cursor, Claude Desktop, Windsurf), configures their MCP settings safely, and runs an in-memory verification test.
Pre-Execution CLI Auditor:
Scan files or directories for leaks before agent ingestion:
npx ztds-mcp audit .env
npx ztds-mcp audit ./src --json
Declared MCP Tool Surface (7 Tools):
ztds_sanitize— Local deterministic masking of PII, secrets, and credentials before LLM dispatch.ztds_restore— Restores cleartext values into LLM-generated code or diffs from volatile memory mappings.ztds_audit— Evaluates text against RFC v1.0 standards, returning a SHA-256 cryptographic attestation receipt.ztds_reset_session— Cryptographically purges and zeroizes all session mappings in RAM.ztds_info— Returns architectural specifications, patent disclosures (IL 331905), and DOI citations.ztds_guard— In-IDE active guardrail interception wrapper.task— Secure execution perimeter runner.
Certified Commercial Implementation (PrivacyScrubber):
For enterprise environments requiring 30 specialized regulatory profiles (HIPAA 18 identifiers, PCI-DSS 4.0, SOC 2 Type II evidence binders, Defense ITAR/CMMC, FRE-502 legal work-product), see PrivacyScrubber, the certified commercial implementation powered by BrandMeWeb:
Production MCP package: @privacyscrubber/mcp-server
Headless SDK: @privacyscrubber/sdk
Website: privacyscrubber.com | Standard & Specifications: ztds.ai
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user ztds-mcp '--' npx -y ztds-mcp
# 2 — ask your agent for something these tools do
# ztds_sanitize, ztds_restore, ztds_audit and 5 more
Ztds costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
PublisherVerified · since 2026
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Ztds as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user ztds-mcp '--' npx -y ztds-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
8 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Sanitize sensitive PII and secrets in prompt text locally using ZTDS RFC v1.0 zero-egress invariants.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | The raw text to sanitize before sending to LLM context. |
| sessionId | string | no | Optional session identifier to preserve token consistency across conversational turns (default: "default"). |
Restore authentic cleartext values into LLM-generated output from local in-memory token mapping.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | The sanitized response text received from the LLM containing surrogate tokens. |
| sessionId | string | no | Optional session identifier used during initial sanitization. |
Audit text for PII/secrets exposure against ZTDS RFC v1.0 standard and generate an attestation receipt.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | The text to inspect for exposure risks. |
Retrieve ZTDS open specification details (RFC v1.0, IETF Standards Track) and enterprise upgrade guide.
No parameter schema on file.
Zeroize and purge volatile in-memory token mappings (Theorem 2 RAM zeroization).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | no | Optional session identifier to clear. If omitted, clears all sessions. |
Activates the ZTDS Zero-Trust Data Sanitization guardrail in Claude or Cursor.
No parameter schema on file.
The task description or prompt to execute safely.
No parameter schema on file.
Zero-Trust Data Sanitization firewall. In-RAM PII, secret, and credential masking with RFC v1.0 cryptographic receipts. Zero external egress.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Ztds or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 99 / 100
Release 1.2.1 · scanned 15 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score99
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digestee23064ef0c422d0774c4f868b4741bc1bdf7d06da3668e21b0f78efa664ddd0
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (5 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| ztds_sanitize | no tags | |
| ztds_restore | no tags | |
| ztds_audit | no tags | |
| ztds_info | no tags | |
| ztds_reset_session | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestee23064ef0c422d0
Scanned2026-10-15
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.2.1. Pin a release below and the command asks for exactly that one.
1.2.1
8 Oct 2026
latestNo release note was published with this version.
1.1.1
7 Oct 2026
- 1-click auto-setup for Cursor, Claude Desktop & Windsurf via npx ztds-mcp init plus CLI audit.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Ztds can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.