#privacy

MCP server for interacting with Penumbra blockchain - providing privacy-preserving tools for chain interaction

Mirror of

ComplyMe.AI MCP server provides legal & data protection risk analysis and audits.

Strata is a self hosted AI memory server. Your AI remembers everything across every session, on your own hardware. Key features: . Semantic search (find memories by meaning, not keywords) . Per-agent API keys with granular permissions . 3D constellation viewer with live agent activity . File vault (attach real documents to memories) . CSV audit log (full transparency on every agent action) . Pre-Strata history import (your memory doesn't start at install day) . Global MCP kill switch (emergency brake, only a human can undo) . Automatic deduplication . 10 structured thought types . Backend using PostgreSQL . Runs on a Raspberry Pi Always on, always local, always yours.

CodeCompass: AI-powered Vibe Coding with MCP. Connects Git repositories to AI assistants like Claude, using Ollama for privacy or OpenAI for cloud. Integrates with VSCode, Cursor, and more.

Transform natural language into beautiful, interactive data visualizations. This server uniquely integrates powerful technologies like DuckDB, Ollama, and Plotly, streamlining complex data analysis workflows into a single, conversational experience within the Model Context Protocol (MCP) ecosystem. It addresses the fragmented workflow common in current MCP setups by providing seamless workflow orchestration, intelligent database switching, integrated statistical insights, and complete privacy-focused analytics through local Ollama processing.

Vault Tools is a privacy-first MCP server that gives your AI coding agent local file conversion and developer utility tools. Process images (format conversion, compression, resizing, EXIF stripping), manipulate PDFs (merge, split, rotate, page extraction), transform data formats (JSON, CSV, YAML, TOML, Base64, URL encoding), and generate hashes (SHA-256, SHA-512), all on your machine. Files are processed locally and never uploaded to any server or passed into the AI's context window, only file paths and metadata are exchanged.

Fully decentralized P2P web search engine for LLMs. No API key, no billing, unlimited free search via MCP. Crawls, indexes, and searches the web through a peer-to-peer network. Features offline local search, credit-based incentives, privacy-first design, and 5 MCP tools: search, search_local, fetch_page, crawl_url, network_stats.

Manage Pi-hole with the power of AI A Pi-hole MCP (Model Control Protocol) server implemented in Java that allows AI applications to interact with and manage a Pi-hole instance through standard commands.

Mobile proxies, Non-VoIP SMS verifications, and global eSIM data plans for AI agents and MCP clients. 18 tools for renting phone numbers, purchasing mobile proxies, buying eSIM data plans, and managing crypto wallet deposits.

Ra Pay AI is the first AI native payment primitive for AI Agents that uses CLI as its distribution layer and a MCP server for AI Agent automation while keeping humans in control. Ra Pay AI's terminal architecture delivers superior privacy, AI token costs and reduced prompt injection attack surface compared to browser GUI based AI Agent payment applications. Yes, we just solved AI Payments using the terminal as our distribution layer. We did it first. For every computer on earth. Use Ra Pay AI to keep an eye on your payment privacy and your AI token costs. Join us. npm install -g @rapay/cli

BitAtlas is a next-generation cloud storage platform designed with privacy and AI agents in mind. It provides a secure, zero-knowledge environment where your most sensitive documents are encrypted client-side and accessible only to you and the agents you authorize.

Native macOS MCP server. Gives AI assistants access to Mail, Calendar, Teams, OneDrive, Contacts, Notes, Reminders, Finder, Word, Excel, PowerPoint — 82 tools, all running locally. No cloud, no API keys. GDPR compliant by architecture.

Bidirectional DLP scanning for every MCP tool call — secrets, PII, prompt injection, and malicious code caught in both directions. Route all your agents (Claude, ChatGPT, Gemini, Cursor) through one endpoint with unified audit logging. Memory Vault for persistent cross-agent context. Bug Vault with 8.6M+ coding patterns across 48 languages. Free tier with 1,000 requests/day. Team RBAC and tool-level DLP policies coming March 2026.

Spell and grammar checking for AI assistants via Model Context Protocol. 100% offline spell check (zero tokens, zero API calls) using nspell. BYOK grammar checking with your own Gemini, OpenAI, or Claude API key. Works with Claude Desktop, Cursor, ChatGPT, and any MCP-compatible tool. 8 languages supported.

AI tools show when you sent a message. Chron logs when the AI responded too — and keeps a permanent, queryable record of every exchange across every tool you use. Works with Claude Desktop, Claude Code, Cursor, Windsurf, and any MCP-compatible AI tool. Every exchange is stored with precise local timestamps (including timezone offset) to a SQLite file on your machine. Query it directly, export it, or use it to answer: what did the AI say, and exactly when?

MCP server for querying Janus analytics — let your AI agent check your dashboard, events, funnels, and usage.

terminal-history-mcp gives AI agents (Claude Code, Cursor, Cline, Zed, any MCP client) full-text search over your shell history. - Local-only, no cloud — SQLite FTS5 at ~/.terminal-history-mcp/history.db - Supports zsh, bash, fish - Captures cwd, exit code, duration via opt-in shell hook - 11-pattern secret redaction runs BEFORE insert (GitHub PATs, OpenAI keys, AWS, JWTs, bearer tokens, env vars, CLI flags, basic-auth URLs) - Hash-deduped, idempotent reindex - WAL mode — safe across parallel sessions Ask: "When did I last ssh into staging?", "Show failed commands today", "What did I run in /etc/nginx yesterday?", "Show context around kubectl apply".

Lucairn is an EU-based privacy gateway that sits between your MCP-enabled agent and the upstream LLM (Claude, GPT-4o, o1/o3/o4). What it does: - Automatically detects and replaces PII — names, emails, IBANs, addresses, phone numbers, customer IDs — with placeholders before reaching the upstream LLM. The model never sees the raw values. - Each response carries a signed compliance certificate (ed25519 + RFC 3161 timestamp + Sigstore Rekor inclusion proof) that proves what was redacted, when, and by which sanitizer layer. - Cross-provider BYOK: bring your own ANTHROPIC_API_KEY and/or OPENAI_API_KEY. Routing is automatic by model prefix (claude-* → Anthropic, gpt-* / o1-* → OpenAI). - Free Developer tier with 1,000 requests/month. Pro and Enterprise tiers unlock higher quotas and re-linkage of placeholders to original values in the response. Exposes one MCP tool, `chat_via_lucairn`, using the Anthropic Messages API wire format. Compatible with any MCP client (Claude Desktop, Cline, Continue, Cursor, etc.). Source: https://github.com/Declade/lucairn-sdks Glama listing: https://glama.ai/mcp/servers/Declade/lucairn-sdks Docs: https://lucairn.eu

Unified inbox MCP for WhatsApp, Telegram, Email, voice — read/send messages, search conversations, manage contacts, query knowledge graph, and trigger AI agents through natural language.

Read-only MCP server for querying DERO blockchain. Get block heights, inspect smart contracts, look up transactions, query network info. Privacy-first: runs locally, no accounts, no tracking.

Your AI research assistant that cites real sources and stays honest. Search the entire web or narrow it down to just the sites you trust; medical journals, court databases, news outlets, academic papers. Analyze the full source, not just snippets. Links that work, citations you can trust, no made-up closed-garden pre-synthesized results.

Give Claude its own email address. QMailing exposes real, persistent mailboxes as MCP tools — create mailboxes on demand, send and read emails, manage custom domains, and register webhooks through natural conversation. 12 tools out of the box, scoped revocable tokens, RFC-7807 error envelopes, signed webhooks. Free tier available; 3 days of Plus on first connect via Claude.

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)