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.
-
llm-differential-privacy-gatewaygithub.com/yashmahajan10/llm-differential-privacy-gatewayupdated this year
Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal guarantee no individual's record can leak even if the agent is adversarial - enforcement lives in trusted code below the model, validated by a runnable attack gallery.
Apache-2.0 ★ 31 -
Agent skills for Clics: privacy-friendly, cookieless web analytics. MCP server and CLI for AI assistants.
MIT ★ 1 -
@kausalayer/mcpupdated this year
KausaLayer MCP Server - Privacy infrastructure for AI agents on Solana
npm Apache-2.0 -
kausalayer-mcpupdated this year
KausaLayer MCP Server - Privacy infrastructure for AI agents on Solana
npm Apache-2.0 -
@clicsdev/mcpactive
Clics MCP server — privacy-friendly, cookieless analytics for AI agents
npm MIT -
brehon-mcp-servergithub.com/brehon-dev/privacy-apiupdated this year
MCP server for the Brehon Privacy API — access 32+ privacy laws from any AI agent
pypi MIT -
Privacy-first local situational awareness for AI agents via MCP
MIT ★ 2 -
brehon-mcp-servergithub.com/brehon-privacy/brehonupdated this year
MCP server for the Brehon Privacy API — access 32+ privacy laws from any AI agent
npm MIT -
A privacy-first, scope-isolated local memory store for AI agents, with a CLI and an MCP server.
pypi MIT -
AgentVeil: a privacy-first, fail-closed browser built for AI agents (MCP server: search, fetch, hardened Firefox, E2E agent messaging)
MIT -
Local-first memory engine for AI agents — Python, MCP, SQLite, knowledge graphs, privacy and governance.
GPL-3.0 -
oak-eventsactive
Privacy-first events from Luxonis OAK cameras for AI agents: JSON lines and an MCP server, never pictures.
pypi MIT -
Privacy-first WeChat archive MCP plugin and Agent Skill for DeepSeek Harness | 本地优先、默认拒绝危险状态的微信归档插件
MIT -
Privacy-preserving AI agent — PII detection, secret scanning, and safe MCP file access for local-first workflows
MIT -
Local privacy boundary for coding agents — detect, transform, and vault sensitive context on-device (Rust, MCP stdio + CLI)
NOASSERTION ★ 1 -
@etalon/mcp-serverupdated this year
ETALON MCP Server — Expose the ETALON privacy registry to AI agents via Model Context Protocol
npm MIT -
proton-mcpgithub.com/jorgenclaw/proton-mcpupdated this year
MCP server for the Proton privacy suite — Mail, Pass, Drive, Calendar, VPN. 36 tools for Claude and other MCP-compatible AI agents.
MIT ★ 30 -
Open-source, local-first work context infrastructure for AI agents. Privacy-hardened workflow evidence via REST and MCP.
Apache-2.0 ★ 1 -
Privacy-first visual grounding fallback with local inference and DOM-visual hybrid routing for MCP browser agents.
AGPL-3.0 -
Fully local, privacy-first autonomous AI agent for laptop management — LangGraph reasoning loop, Ollama local LLM, ChromaDB RAG, MCP server, SHA-256 chained audit log. Zero API keys. Zero cloud calls.
Apache-2.0 ★ 5 -
Self-hostable, privacy-first memory layer for AI agents — typed memory + relation graph, semantic/text retrieval, MCP server, REST/SDK/CLI, PMF. Apache-2.0.
Apache-2.0 -
A personal AI that keeps your secrets and shows its receipts — NVIDIA Nemotron on Nebius Token Factory, provenance memory, privacy guard, MCP for Hermes Agent
MIT -
Autonomous AI Agent compliance engine for EU Deforestation Regulation (EU 2023/1115) with 37 MCP Tools, Supplier Privacy Portal & Smart Escrow
pypi MIT -
Resolver-posture checks for MCP hosts, agents, CLI and CI. Local-first, read-only and privacy-first.
npm NOASSERTION -
Privacy PDF Toolkit - 25 tools + free MCP server for AI agents (local, no cloud)
MIT ★ 3 -
PC diagnostics and safe cleanup built for AI agents: disk space, caches, drivers, privacy, startup, bloat, security and crashes as compact JSON. MCP server included.
npm MIT -
filewash-apigithub.com/cassilup/filewash-apiupdated this year
Privacy-first file tools for AI agents — MCP server, metered REST API & SDK. Compress, convert, merge/split PDFs, strip metadata, remove backgrounds. Zero-retention.
npm MIT -
internull-mcpgithub.com/internullorg/internull-mcpupdated this year
MCP server for AI agents to interact with the InterNull privacy protocol: deposit, claim keys, withdraw across chains via 3-of-5 distributed threshold cryptography
npm MIT -
blackbox-mcpgithub.com/internullorg/blackbox_mcpupdated this year
MCP server for AI agents to interact with the BlackBox privacy protocol — deposit, claim keys, withdraw across chains via 3-of-5 distributed threshold cryptography
npm MIT -
vault-mcpgithub.com/AlexeySamosadov/vault-mcpupdated this year
Vault MCP Suite — 8 privacy-first, local MCP servers for AI agents (PDF, image, data, text, zip, hash, JSON, QR). Free core + one-time crypto Pro.
-
JOMO's privacy layer as MCP tools: private transactions on Robinhood Chain from Claude, OpenAI, Antigravity or any MCP client, approved by you or by limits you set for an autonomous agent.
npm MIT -
Local-first Loom alternative for macOS: records screen + camera, a Privacy Guard blurs and bleeps secrets before anyone can watch, and local AI agents turn recordings into guides and agent-ready action plans (MCP).
MIT -
PrigenFi is a privacy-preserving, agent-native DeFi protocol enabling autonomous AI agents to trade, manage assets, and execute financial strategies across EVM chains using Zama FHE, smart accounts, and MCP.
-
Apple App Store Pre-flight Guideline & Compliance Auditor, Privacy Manifest Generator, and MCP Agent Server.
npm MIT -
@otbossam/searxng-mcp-servergithub.com/damin25soka7/hiupdated this year
SearXNG MCP Server with Better Search - 100% privacy-focused intelligent search with auto Docker management and User Agent rotation
npm MIT -
🛡️ Ephemeral privacy & security middleware for Model Context Protocol (MCP). Zero-persistence credential masking & fail-closed execution guard for AI agents.
MIT -
Privacy-first AI personal data manager. A local trusted agent that external AIs command via MCP — they never see your documents. Encrypted storage, local RAG, activity logging, and per-agent permissions.
Apache-2.0 ★ 2 -
MCP server for RightOS — queue/EV/pickup QR tickets for AI agents (Cursor, Claude). 20 tools, privacy-first, no end-user PII. npm: npx -y @i-s3/rightos-mcp
npm MIT -
BWAV - Bulk WhatsApp Number Checker with MCP. Privacy-first Chrome extension to validate single and bulk WhatsApp numbers, with an optional MCP bridge for AI agents.
MIT ★ 3 -
Privacy-first, self-hosted PDF toolkit with a built-in MCP server. Merge, compress, and OCR documents (including Russian) through a web UI or AI agents. One Docker container.
MIT -
@auditly-fyi/mcpgithub.com/arpitjain099/sigentra-cloneupdated this year
Model Context Protocol server for Auditly — let AI agents run web compliance scans (accessibility, cookies, trackers, privacy policy) against domains they verify ownership of.
npm MIT -
🛡️ The consent firewall for AI agents. Your agent can use the world's public data — the world can't use yours. Field-level minimization, in-flow consent, LLM tokenization, prompt-injection quarantine & hash-chained privacy receipts. MCP server included.
MIT ★ 1 -
askgraphgithub.com/bakhliustov/askgraphupdated this year
Local-first, privacy-first codebase Q&A: structural knowledge graph (tree-sitter) + semantic search + git provenance. CLI, TUI, and MCP server for agents. Runs entirely on your machine.
MIT -
Security, compliance & privacy toolkit for AI agents: SynomosAI Governance MCP — AI governance assessment toolkit (A3 assess, evidence chain, compliance, passport, scan, LGD knowledge). Bilingual EN-first. MIT.
pypi MIT -
lextiva-mcpgithub.com/arturayupov/lextiva-mcpupdated this year
MCP server exposing the Lextiva compliance reference dataset — 18 privacy + AI regulations, 21 jurisdictions, 7 document types, 8 data-subject rights. Lets Claude/Cursor/any MCP-aware agent answer compliance questions with primary-sourced, verifiable data.
NOASSERTION -
analyticsgithub.com/clamp-sh/analyticsupdated this year
Privacy-first analytics SDK for Clamp Analytics. MCP-native — your AI agent can query the same events. Auto-pageviews, sessions, revenue, errors. Browser, server, React, and one-tag CDN install for Webflow / Shopify / WordPress and other hosted platforms.
npm MIT ★ 1 -
mcp-supabase-dbgithub.com/kodydennon/mcp-serversupdated this year
Model Context Protocol (MCP) server for Supabase/PostgreSQL database access with dual-mode operation. Provides AI agents with 35 direct tools AND code execution mode (98% token reduction, privacy-first, streaming). Compatible with Claude Code, Cursor, Gem
npm MIT -
Agent-Bgithub.com/eonedgeproject-code/Agent-Bupdated this year
Privacy-preserving AI agent coordination on Solana — 42 instructions, ZK proofs, autonomous runtime, MCP server
GPL-3.0 -
stellar-agent-spend-hubgithub.com/CaBsCrypto/stellar-agent-spend-hubupdated this year
Privacy-first agentic payments on Stellar for MCP/API and digital-service spend.
-
openinterp-mcpgithub.com/OpenInterpretability/openinterp-mcpupdated this year
Bring-your-own-agent infrastructure for mechanistic interpretability research. MCP server + Colab backend. Privacy-first.
pypi NOASSERTION -
Agentic escrow payments — fiat + crypto, 36 MCP tools, 10 chains, FHE privacy
npm -
Screeny is a privacy-focused macOS MCP server enabling AI agents to capture screenshots of user-approved windows
MIT ★ 18 -
plausible-mcpactive
Plausible Analytics MCP server: privacy-first website statistics, real-time visitors, breakdowns, and trendlines for AI agents.
pypi MIT -
imgpipe-mcpgithub.com/marilynceo/imgpipe-mcpupdated this year
Image processing pipeline for AI agents u2014 resize, convert, optimize, batch. Privacy-first with EXIF stripping.
-
Flowsery agent skill, MCP server and Gemini CLI extension: query privacy-first web analytics and session issues from any AI agent
MIT -
Self-hosted, privacy-tiered memory for your AI agents.
MIT ★ 8 -
agent-domainsgithub.com/purple-flea/agent-domainsupdated this year
Privacy-first domain registration API for AI agents. Powered by Njalla.
npm -
evergreen-notebook-mcpgithub.com/kesjam/evergreen-notebook-mcpupdated this year
Privacy-safe MCP tools and an agent skill for better NotebookLM workflows.
MIT -
@gilangjavier/chronagithub.com/gilangjavier/chronaupdated this year
Local-first, deterministic, time-aware memory store for agents with provenance, privacy scopes, and MCP support.
npm MIT -
Kubernetes security audit agent - declarative kagent agent with MCP tools and privacy-preserving pseudonymization via LLM proxy
Apache-2.0 ★ 1