"Best open-source NPX or UVX tools for terminal deployment on Windows" matching MCP servers:

A powerful MCP server for fetching and transforming web content into various formats (HTML, JSON, Markdown, Plain Text) with ease.

Enables a local, read-only search over user-provided tabletop campaign source cards and module directories, routing queries to ranked hits across Markdown, JSON, and YAML text files while excluding core rulebook and SRD content by default. Returns file-and-line pointers with small context windows, plus explicit private-source opt-in, so a game master can locate and open the exact passage in their own library.

Self-hosted OAM memory with cited recall over your existing deployment. Local stdio adapter with six tools for recall, retaining interactions and documents, operation readiness, stored Profile reads and exact memory removal. Run with npx -y @rocke-dong/oam-mcp; requires Node.js 22 and your OAM user-scoped API key. Submitted by the OAM maintainer with AI assistance.

MCP server for searching, browsing, and analyzing decompiled Minecraft source code locally. Supports symbol lookup, text search, reference lookup, and lightweight RAG.

Enables agents to query a self-hosted, locally indexed web corpus through MCP tools for keyword, neural, or hybrid search, to fetch clean text from already-indexed URLs, and to discover pages similar to an indexed URL.

Enables AI coding agents to search and read local Markdown knowledge bases generated by Agent Docs for Markdown, across single or multiple workspaces, including link/backlink discovery and index status checks.

Enables AI agents to drive a user's own signed-in Google NotebookLM (Gemini Notebook) account through 51 MCP tools, covering notebook and source management, grounded chat with numbered citations, fast and deep research, and generating or downloading audio/video overviews, slide decks, quizzes, flashcards, mind maps, infographics, reports and data tables. It runs over stdio or streamable HTTP on localhost and sends progress notifications for long-running jobs.

Stores what AI agents learn — thoughts, decisions, session events and repo facts — in PostgreSQL with pgvector and serves it back through versioned MCP tools with hybrid vector-plus-full-text retrieval and budgeted context packs. Enables multiple agents to share one scoped, role-isolated long-term memory, with deliberate promotion of distilled candidates into durable memories.

Exposes a local SQLite-backed long-term memory to AI agents as MCP tools, letting them add conversations and documents, record dated facts with provenance, search and assemble context, and edit, inspect, or forget what was stored. It runs with your own embedding and LLM keys, so memories stay readable, exportable, and portable as plain markdown.

Multi-datasource MCP server that connects AI assistants to 6 database types (MySQL, PostgreSQL, ClickHouse, MongoDB, SQLite, Huawei DWS) with dynamic configuration, encrypted credential storage, and schema discovery.

Enables AI assistants to perform intent routing, retrieval reranking, and batch semantic judgments on Cloudflare Workers, returning structured answers with confidence scores instead of generated prose.

A self-hosted MCP knowledge server that gives agents a filesystem-shaped store of rules, context, skills, and granted connections — opened in full for standing rules and as an index otherwise, then listed, searched, and read on demand. Agents can only propose diffs and new entries (reviewable and correctable by the owner) and receive credentials for exactly the connections they're bound to.

A comprehensive Model Context Protocol (MCP) server implementing the latest MCP specification with tools, resources, prompts, and enhanced sampling capabilities that features HackerNews and GitHub API integrations for AI-powered analysis.

Enables AI assistants to search a curated database of 200+ AI tool cards with pricing, platforms, use cases, and source links, so users can ask which tool to use for a task and get grounded recommendations.

Enables AI assistants to manage notebooks, sources, notes, search content, and interact with AI models through Open Notebook.

This server enables users to download entire websites and their assets for offline access, supporting configurable depth and concurrency settings.

Personal knowledge graph with 16 MCP tools. Auto-links, deduplicates, tracks themes, synthesizes insights.

Enables multiple MCP agents to read and write a single user-controlled, local-first fact layer under one user identity with explicit scopes, preserving sources, versions, permissions, and audit history. Supports structured memories such as preferences, facts, task state, and decisions, plus structured handoff capsules so one agent can resume another's work by task ID.

MCP server for compressing AI embeddings by 5-7x using TurboQuant (PolarQuant + QJL), with tools to compress, decompress, estimate savings, and embed+compress vectors.

MCP server that provides secure access to a serverless Markdown wiki on AWS, enabling AI assistants to read, search, and edit pages with space-level permission checks and Bedrock-powered semantic search.

A self-hosted second brain MCP server that enables capturing thoughts with deduplication and semantic search using local embeddings and PostgreSQL with pgvector, all running on your own hardware.

Local-first code retrieval MCP server: hybrid semantic + keyword search over an AST-aware index of your codebase, with symbol definition and reference lookup, repo maps, and file tools. Runs fully offline; serves Claude Code, Cursor, and any MCP client over stdio or HTTP.

Gives Claude Code a persistent, fully local long-term memory by automatically capturing session activity, indexing past conversations, projects, scheduled tasks and Obsidian notes, and recalling relevant context through hybrid keyword-plus-semantic search with progressive disclosure. It also writes session handoffs that are injected into later sessions, so work resumes with prior decisions and next steps already in context.

A multi-function Streamable HTTP MCP tool aggregation server that provides web search via Brave, Exa, and SearXNG with multi-key rotation and cross-provider fallback, and supports extensible tool families (URL fetch, code search, RAG) through a pluggable architecture.

Gives Claude Code persistent, local-first project memory: it records sessions, compresses them into searchable observations and summaries, and injects a compact project brief plus prompt-time recall at session start. It also exposes tools for recalling observations and timelines, managing durable tasks and notes, and reading any project's context, all backed by a local SQLite file with compression run on a local LLM.

Enables clinical question answering via OpenEvidence with citation verification, including tools to ask questions, retrieve results, and follow up, plus an integrated skill to check citations against primary sources.

An MCP server for storing and retrieving thoughts, notes, and ideas with semantic vector search, enabling integration with Claude Desktop and other MCP clients.

Extends VS Code Copilot with MCP tools for persistent semantic memory, code indexing and RAG search, sandboxed Python/shell execution, web fetch/search, dynamic tool management via a web UI, and structured multi-step reasoning.

Unified AI Agent SaaS Connector & Multi-Provider Gateway connecting to 1,000+ SaaS platforms, vector databases, and 500+ LLM models via MCP, REST API, and CLI.

An Operit-compatible adapter of the Exa MCP server, enabling web search, code search, and company research capabilities in AI assistants. It fixes MCP handshake compatibility issues, allowing tools like web_search_exa and web_fetch_exa to load and run reliably.

A persistent, cross-session knowledge base for AI agents that indexes session history into a searchable SQLite database with full-text search, enabling recall of past sessions, stored knowledge, and summaries.

Guides problem-solving by breaking down complex problems into steps and recommending appropriate MCP tools for each stage, with confidence scores and rationales for tool suggestions.

A collection of tools that enhance MCP-based workflows with caching, retry logic, batch operations, and rate limiting capabilities.

Enables MCP clients to leverage the Intel Arrow Lake NPU for local speech transcription, screenshot OCR, private semantic search, and hardware diagnostics, all processed locally.

An MCP server providing 22 pay-per-call utility tools for AI agents (scrape, validate, embed, store, moderate, notify, convert, prevent loops) without accounts or API keys, using USDC payments via the x402 protocol.

MCP for Azure DevOps Boards is a MCP server that lets your favourite AI browse, query and update Azure DevOps work items as if it were a project manager. Written in Rust and optimized for tokens usagem, It runs via stdio or HTTP mode and uses standard Azure authentication with az login.

A proof of concept MCP server for Apache OFBiz

This read-only MCP Server allows you to connect to Act-On data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at https://www.cdata.com/solutions/mcp

WordPress plugin that runs an MCP server on your own site: search and read published posts and pages, look up WooCommerce products, describe the site as schema.org types and query site figures, with drafts only when the site enables them. Signed-in access by default; anonymous access and OAuth are optional and off.

Provides access to OpenAI's advanced models (including o3) with integrated web search, Python code interpreter, and combined analysis capabilities. Enables users to perform web searches, execute code in sandboxed environments, and combine search with analysis through natural language.