"A search engine focused on privacy and minimal tracking" matching MCP servers:

Enables privacy-preserving document retrieval by exposing read-only search tools over MCP, allowing agents to query local vector and structured indexes without sending data to the cloud.

Enables searching documentation from GitHub repositories and web pages via MCP tools, with in-memory indexing and caching for fast retrieval.

Enables Claude/Lyra to create, monitor, and manage live sessions for long-running operations such as downloads, conversions, and agent jobs, with progress metrics, logs, error alerts, and a Textual dashboard; it also ingests updates from external media-server tools.

Enables natural-language queries about US federal and New York privacy law obligations, returning citation-anchored answers with computed deadlines, usable from Claude Desktop or the command line.

A generic MCP server for tracking any entity type (e.g., weight, workouts, books) without predefined schemas, using SQLite with JSON columns for flexible data storage and querying.

A minimal MCP server for creating and updating Google Docs from markdown.

Enables accurate Quranic verse search through natural language queries, returning exact text with no hallucinations.

MCP server for AI-first UI design that enables Codex to create, preview, and commit UI changes to a self-hosted design tool.

Provides instant GDScript syntax validation and diagnostics by bridging Godot's native Language Server Protocol to MCP clients. Enables real-time syntax checking in AI assistants without requiring custom plugins or context switching to the Godot editor.

Enables safe interaction with cloud LLMs by redacting sensitive entities into reversible placeholders, enforcing deterministic egress policies with human approval, and rehydrating responses so real data never leaves the process.

Enables natural language time tracking through Claude with markdown file storage. Supports multi-company tracking, flexible time parsing, auto-calculated summaries, and commitment warnings all through conversational input.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Exposes self-owned AI agent plugins as tools to Claude Code via a stdio MCP server, allowing Claude to call system info, calculator, or scribe transcriber directly.

A minimal MCP server implementation designed for learning how to integrate tools like echo, time retrieval, and Japanese Wikipedia search with Claude Desktop. It serves as a foundational template for developing custom server capabilities using the TypeScript MCP SDK.

Enables sanitizing PII from text, classifying data into sovereignty zones, and monitoring compliance scores to keep sensitive information out of AI outputs.

A minimal MCP server that demonstrates tool usage with rectangle area calculation and history retrieval.

Enables GDPR privacy compliance and DSAR management, including creating, tracking, and updating Data Subject Access Requests, checking GDPR compliance, and maintaining a data processing inventory through MCP tools.

A basic educational MCP server that provides simple tools for mathematical calculations, text manipulation, and time retrieval. Designed for learning MCP implementation patterns and development purposes.

Enables grounded, dated research from a curated AI-knowledge repository, offering free BM25 retrieval and a research loop that combines the knowledge base, curated sources, and the open web with tiered citations.

Eyes for AI coding agents: deterministic MCP server that tells the LLM which CSS rule wins, in which file, on which line — and why. Cascade verdicts, blast radius, interaction timelines, pixel-perfect audits.