MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
ZTDS MCP — Zero-Trust Data Sanitizationno update data
—
smithery -
sanitized-db-mcpgithub.com/ruminaider/sanitized-db-mcpupdated this year
MCP server for PII/PHI-safe database queries via AST-level SQL rewriting
pypi MIT ★ 1 -
llm-sanitizergithub.com/warnes-innovations/llm-sanitizerupdated this year
CLI + MCP server for detecting, classifying, and redacting embedded LLM agent instructions in documents, source code, and web pages.
pypi AGPL-3.0-or-later -
mcp-code-sanitizergithub.com/notasandy/mcp-code-sanitizerupdated this year
Strict AI code reviewer MCP server powered by Groq
pypi MIT ★ 3 -
data-sanitizer-mcpgithub.com/marilynceo/data-sanitizer-mcpupdated this year
Clean and validate data for AI agents. Sanitize JSON, CSV, emails, dates, text, detect PII, normalize phone numbers. Built for the AI agent economy.
-
@mukundakatta/llm-output-sanitizer-mcpgithub.com/mukundakatta/llm-output-sanitizer-mcpupdated this year
MCP server exposing llm-output-sanitizer: strip dangerous HTML, SQL, and shell snippets from LLM output before rendering, executing, or persisting. Built for Claude Desktop, Cursor, Cline, Windsurf, and Zed.
npm MIT -
MCP server: scan web pages, mails, PDFs and tool output for prompt injection before your agent reads them (17 languages).
MIT -
CloakMCPgithub.com/ovitrac/CloakMCPupdated this year
CloakMCP — local-first, deterministic sanitizer for secrets before LLMs
pypi MIT ★ 8 -
mcp-server-privacyactive
Model Context Protocol (MCP) server for automated PII sanitization, confidential compute boundaries, and prompt privacy budgeting.
npm MIT -
aegis-protocolgithub.com/aethel-foundation/aegis-protocolupdated this year
The absolute antidote for dev-tool telemetry and marketing contamination. A sovereign-first boilerplate sanitizer and MCP server.
-
MCP server that lets AI coding agents actually test C++ code: sanitizers, static analysis, and a profiler behind eight tools.
MIT -
CLI toolbox for developers and AI agents: audit, run, test, lint, coverage, secrets, profiling, sanitizers, LSP, MCP and autonomous agent
npm MIT -
jv-watchtower-mcpgithub.com/janvrsinsky/jv-watchtower-mcpupdated this year
Read-only MCP operations console over a 24/7 algorithmic trading fleet (sanitized portfolio extract). Sanitization is enforced in the data layer, so the strategy never reaches the model. CI leak-scans every tracked file and every tool output.
MIT ★ 1 -
noatmark-mcpgithub.com/ylwl1997/noatmark-text-hygieneupdated this year
MCP server for text hygiene: sanitize text before feeding it to an LLM (strip invisible characters, flag prompt injection), scan for hidden text, and clean LLM formatting. Companion to noatmark.com.
npm MIT -
Zero-Trust Data Sanitization (ZTDS RFC v1.0) reference MCP server for Claude Desktop, Cursor, and Windsurf. In-memory PII de-identification and deterministic surrogate tokenization.
Apache-2.0 ★ 1 -
24 deterministic text tools for AI agents — URL sanitizer, JSON/SQL/YAML formatters, hex/base64/hash, token counter, cron explainer, and more. Runs locally over stdio; no API key, no network.
npm MIT -
Self-hosted MCP gateway. Connects Claude, ChatGPT, Codex and any MCP agent to 50+ enterprise tools (Jira, Confluence, GitLab, Notion, Miro, Google Workspace, Slack, Grafana, Sentry, Figma, ...). Pre-integrated, GDPR-ready, with PII sanitization, write-safety, and audit logging. Mirror of gitlab.com/mcpgate/mcpgate.
NOASSERTION ★ 3 -
PrivacyScrubber PII Masking MCPno update data
Zero-Trust Data Sanitization (ZTDS) MCP Server for Claude Desktop, Cursor, Windsurf, and other AI clients. Automatically intercepts and redacts PII, credentials, and sensitive corporate data locally on your machine before they are sent to external LLMs. ### 🔒 100% Local & Airplane Mode Verified All sanitization runs inside local RAM. No data ever leaves your computer, ensuring compliance with GDPR, HIPAA, SOC 2, and internal GRC policies. Zero network calls, zero server logs. ### 🛠️ Supported Formats & File Types Locally parse and sanitize: - **Documents:** `.docx` (Microsoft Word) parsed locally with Zero-Server extraction. - **Code & Configs:** `.js`, `.py`, `.go`, `.rs`, `.json`, `.yaml`, `.ini`, `.env`, and source code files. - **Data & Logs:** `.txt`, `.log`, `.csv`, `.tsv`, `.md`, and plain text outputs. ### 🏷️ Redacted Entity Types - **Personal Data:** Names (`NAME`), Emails (`EMAIL`), Phone Numbers (`PHONE`). - **Credentials:** API Keys, passwords, tokens, SSH keys, database URIs. - **Identifiers (`ID`):** SSNs, Tax IDs, credit card numbers, and custom regex patterns. ### 🎛️ 22+ Specialized Industry Detection Profiles Specify detection rules tailored to your workload (requires PRO key): - **Engineering & IT:** `Dev`, `Tech`, `Security`, `Agents` - **Corporate & Operations:** `General`, `Bizops`, `Sales`, `Support`, `Marketing`, `Creative` - **Financial & Professional:** `Finance`, `WealthMgmt`, `Insurance`, `Accounting` - **Legal & Compliance:** `Legal`, `Compliance`, `CCPA`, `HR` - **Healthcare & Research:** `Medical`, `Pharma`, `Academic` - **Personal Use:** `Personal` ### 🔧 Available Tools - `sanitize_text` — Scrub PII/Secrets locally in text context. - `reveal_text` — Reversible token mapping (Original -> Token -> Original). - `sanitize_file` — Local sanitization of raw plain text and DOCX files.
smithery -
Content safety for AI: inspect, sanitize, contain, quarantine. MCP server. OWASP LLM01/LLM06.
MIT -
Golang based Postgres MCP with plugin support, data sanitization, protection
go MIT -
Public AiSCent support, agent guidance, known issues, and sanitized resolutions.
-
html-mcpgithub.com/MukundaKatta/html-mcpupdated this year
MCP server: strip HTML tags, extract plain text, and sanitize HTML.
MIT -
hermes-shieldgithub.com/amurlaniakea/hermes-shieldupdated this year
Input sanitizer for AI agents — anti-prompt-injection shield
AGPL-3.0 ★ 1 -
commerce-mcp-servergithub.com/aleayrees-com/commerce-mcp-serverupdated this year
Sanitized MCP-style server foundation for e-commerce catalog, orders and commerce API operations.
-
origin-pro-mcp-skillgithub.com/leima-max/origin-pro-mcp-skillupdated this year
Sanitized Origin Pro MCP skill package with bilingual documentation
MIT ★ 237 -
thinchaingithub.com/SnipMCP/thinchainupdated this year
MCP server that cuts options chain tokens 95% for AI trading agents. Sanitize, compress, circuit-break.
pypi MIT -
fastmail-clean-mcpgithub.com/MalcolmWardlaw/fastmail-clean-mcpupdated this year
Sanitizing Fastmail MCP proxy: speaks JMAP directly and returns mail bodies stripped of HTML, trackers, and padding
MIT ★ 2 -
email-cleaner-for-llmsgithub.com/MalcolmWardlaw/email-cleaner-for-llmsupdated this year
Sanitizing MCP proxies between a mail API and an LLM for bulk clearing an email inbox.
★ 1 -
MCP server implementing the Vibe Leading Privacy Shield: PII sanitization, tiered sovereignty classification, and compliance scoring.
npm MIT -
@dayby/mcp-serverupdated this year
DayBy MCP Server — Write, publish, and manage blog posts from Claude, Cursor, or any MCP client. Built-in content sanitization.
npm MIT -
@vinumcms/mcpgithub.com/thidal/vinum-cmsupdated this year
An MCP server over a Vinum install: read the content model, read and write pages, through the same sanitizers the admin uses.
npm MIT -
Sanitizing Microsoft 365 MCP proxy: strips HTML and tracker cruft from mail bodies before they hit the LLM
MIT ★ 1 -
mcp-safe-fetchgithub.com/PortfolioKB/mcp-safe-fetchupdated this year
An injection-aware content fetcher exposed over MCP: layered prompt-injection sanitization and a resolve-and-classify SSRF guard.
MIT -
DSH addon kit: reusable MCP servers (desktop/browsers), A2A agent bridge, skill, plugins and mobile-remote kit - sanitized for public reuse
MIT -
Cloudflare official API MCP (Code Mode) for the agent runtime, with the JSON-Schema sanitizer that makes its tools register.
npm MIT -
Sanitized personal reproduction of an industrial CAM Agent using LangGraph, MCP, deterministic validation and Siemens NXOpen.
★ 1 -
Policy-gated local SQLite MCP server that lets AI agents query sanitized database snapshots without exposing protected data.
MIT -
MCP server for Kiln: give AI agents safe, scoped write access to your website — every edit a sanitized, scoped, revertible git commit.
npm AGPL-3.0-only -
Built a 5-stage multi-agent workflow (Triage, Document Verification, Fraud Analysis, Decisioning, Compliance Auditing) with guardrails for input sanitization and PII redaction.
-
Secure, self-hosted remote MCP server for an Obsidian vault, with OAuth, sanitization, atomic writes, sync and recovery. WIP.
MIT -
Kimi Code plugin for TencentDB Agent Memory (TDAI): auto recall (L1/L2/L3/L0) + sanitized capture + memory/skill/wiki MCP tools
MIT -
@leonai/clockify-mcp-servergithub.com/leonai/clockify-mcp-serverupdated this year
Secure Clockify MCP server with HTTP + stdio transport. Wraps clockify-master-mcp with security fixes (SSRF protection, stdout fix, API key sanitization).
npm MIT -
Cyberpunk (William Gibson-style) placeholder text tools: a shared dictionary, a text generator/CLI, and a Playwright screenshot sanitizer (text + CRT dead-channel images)
MIT -
FinanceOps Copilot — local AI agent connecting ERPs via MCP, with RAG over finance policies and finance-department automation. Architectural showcase (sanitized prototype, synthetic data).
MIT -
ragalgo-mcp-serverupdated this year
Dynamic RAG Engine for AI Reliability. We provide mathematically scored context & sanitized data to prevent hallucinations in both static & volatile domains (starting with Korean Finance).
npm MIT -
visus-mcpgithub.com/visus-mcp/visus-mcpupdated this year
Security-first MCP server. Sanitizes web content before it reaches your LLM — strips prompt injection, redacts PII, and reduces token consumption by up to 70%.
npm MIT -
SUMIPDF - local-first PDF editor: true redaction, text replacement, OCR, AES-256, page ops, sanitize. MIT. MCP server built-in.
MIT -
Model Context Protocol (MCP) server for OpenSVG — search 322,000+ vector icons, generate React/Vue/Svelte components, and sanitize SVGs directly in AI coding assistants.
npm MIT -
htmemgithub.com/droggy992/htmemupdated this year
HTML as canonical LLM memory and inter-agent comms. Claude Code plugin + MCP server. Anchor-signed, schema-validated, sanitized. Apache-2.0.
Apache-2.0 ★ 1 -
@iflow-mcp/kokogo100-ragalgo-mcp-serverupdated this year
Dynamic RAG Engine for AI Reliability. We provide mathematically scored context & sanitized data to prevent hallucinations in both static & volatile domains (starting with Korean Finance).
npm MIT -
mcp-guardgithub.com/sainitish1609/mcp-guardupdated this year
🛡️ Ultra-fast local security firewall, secret sanitizer, and context token compressor for Claude Code, Cursor, and MCP AI agents.
MIT ★ 4 -
Secure, local-first document-to-Markdown conversion. Zero-trust input sanitization, multi-column PDF layout, LaTeX math, PII masking. No cloud dependencies.
MIT ★ 6 -
Read-only, sanitized Spring Boot runtime diagnostics (beans, conditions, routes, health, migrations, startup, config, OpenAPI, drift) for coding agents over MCP
pypi Apache-2.0 ★ 1 -
Google Ads MCP server + analytics toolkit in Python: weekly monitoring, CPC root-cause diagnostics, and automated dashboards. Sanitized portfolio showcase (synthetic data, no credentials).
-
MCP server that hands private-data or large-output work to a local LLM: the cloud model gets sanitized digests and stable placeholders, the material never leaves your network
MIT ★ 1 -
Persistent-memorygithub.com/Rohan473/Persistent-memoryupdated this year
Knowledge graph + live memory layer for systematic alpha research on WorldQuant Brain: NetworkX graph, WQB API simulation loop, overfit/correlation gating, sanitized multi-model critic, MCP + FastAPI interfaces.
MIT ★ 1 -
Secure MCP server for ComfyUI — workflow inspection, path sanitization, rate limiting, and audit logging. Generate images from Claude and other AI assistants with built-in security controls.
pypi MIT ★ 2 -
Local-first PII pseudonymization for LLM workflows — sanitize text, files, and LLM traffic with a reversible vault that never leaves your machine. Works with Cline, OpenClaw & any MCP client. Free, MIT.
MIT -
ObsidianScrub & CMMC 2.0 Zero-Trust Security Model Context Protocol (MCP) Server — Deterministic CUI/PII/Secret Sanitization, NIST SP 800-171 Auditing & Smart Contract Invariant Checks.
-
dispatch-agentgithub.com/shivamkrsharma006-lang/dispatch-agentupdated this year
Multi-agent research digest built with Google ADK — MCP tool integration, sanitization against prompt-injection, semantic dedup via embeddings, and a two-layer evaluation gate. Built for the Kaggle × Google AI Agents Intensive capstone.
MIT