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.
-
siteglass-mcpgithub.com/siteglassio/siteglass-mcpupdated this year
Archive any URL to a shareable snapshot (rrweb/pdf/png) + agent-driven web QA — an MCP server for siteglass.io. No CAPTCHA, no signup.
npm MIT -
A Model Context Protocol (MCP) server over the Internet Archive Wayback Machine — web-archive lookup for born-digital-art conservation.
MIT -
MCP server for excavating 1990s-2000s Japanese personal websites from web archives
npm MIT -
Save web pages locally in SQLite and query the archive through MCP.
MIT -
magi-archive-mcp-proxygithub.com/Magi-AGI/magi-archive-mcp-proxyupdated this year
Cloudflare Worker proxy for Magi Archive MCP server - enables Claude Web/Mobile connections
-
Internet Archive & Wayback Machine — historical web snapshots plus search and metadata across texts, audio, video, and software.
smithery -
松果 Acorn:完全属于你的信息系统——订阅、阅读、批注、翻译、本地存档。A self-hosted reader and personal web archive.
AGPL-3.0 -
Web scraper & crawler → clean Markdown with byte-level SHA-256 provenance + WARC archival for LLM/RAG knowledge bases
pypi MIT ★ 2 -
Zero-install, server-preserving web archiver and ISO 28500 forensic engine for offline replication and digital preservation.
Apache-2.0 ★ 1 -
NewsBlur MCP server and Web Capture Archive Protocol orchestrator — local-first feed/story index, plus URL preservation into a content-addressed blob store via chrest + madder — read-only mirror of code.linenisgreat.com/nebulous
MIT -
article2mdgithub.com/tzrea1-Q/article2mdupdated this year
Archive web articles — WeChat 公众号, Zhihu, Xiaohongshu, or any URL — as clean Markdown with local images. Built for Obsidian and LLM workflows.
npm MIT ★ 2 -
Local async MCP middleware for archiving web pages to Internet Archive without blocking AI reasoning loops.
pypi MIT -
Local, searchable archive of your own AI chats (Claude Code, Cowork, claude.ai, ChatGPT, Gemini): web interface, CLI and MCP server
MIT -
Local archive + web viewer + MCP server for Claude Desktop and Claude Code conversations. Browse, search, export, and let Claude query its own history.
pypi Apache-2.0 -
Self-hosted knowledge base shared by a human and their AI agents: archive links, repos and documents with a why; search them over MCP, REST and a web UI.
AGPL-3.0 -
Trove — save anything, keep everything. A Raindrop-style library on Notion: web app, browser extension (incl. X bookmarks archive), Apple Shortcut, MCP server & API for AI agents.
MIT -
@iflow-mcp/steipete-conduit-mcpgithub.com/steipete/conduit-mcpupdated this year
MCP server for rich file system ops, web content fetching (HTML/Markdown), image processing, search, diff & archives, via concise tools.
npm MIT -
Personal archive of CV entries, with a web page and an MCP server.
-
arquivo-pt-mcpgithub.com/thaenor/arquivo-pt-mcpupdated this year
Model Context Protocol server for Arquivo.pt — the Portuguese Web Archive
pypi MIT -
simexp-mcpgithub.com/gerico1007/simexpupdated this year
MCP (Model Context Protocol) server for simexp web content extraction and archiving
pypi MIT -
Privacy‑focused web, social media, and archive search server exposing tools via the Model Control Protocol (MCP)—perfectly suited for integration with LM STUDIO
MIT ★ 8 -
MCP server tailored to connecting web crawler data and archives
pypi NOASSERTION ★ 46 -
Rust MCP server for multi-agent coordination: 45 tools and 25 resources, Git-backed archive, SQLite indexing, advisory file locks, a 16-screen TUI, a server-rendered web UI, and an agent-first robot CLI.
go NOASSERTION ★ 256 -
WhatsApp on your own machine: linked-device daemon, full local archive, WhatsApp Web-like client and an MCP server for Claude Code, Claude Desktop and any MCP agent. Single Go binary, AGPL.
go AGPL-3.0 -
MCP server for witnessd — a neutral third-party witness for the machine-readable web. Agents pay cents via x402 (USDC on Base) to have any URL or API response independently fetched, hashed, timestamped and archived, Merkle-anchored hourly. Tools: witness_url, get_certificate, retrieve_snapshot.
npm MIT -
🚀 自托管的抖音、TikTok、B 站数据采集与无水印视频下载 API,支持 AI agent 通过 MCP 调用与离线语音转文字,Docker 一键部署。| Self-hosted TikTok, Douyin & Bilibili scraper and no-watermark video downloader — async REST API, MCP server for AI agents, CLI and web console, plus offline speech-to-text for downloaded videos. Self-healing identity pool, PostgreSQL archive, one docker compose up.
go Apache-2.0 ★ 21,418 -
Open-source deep research assistant with citations and memory. Ask a question and it searches the web, papers, old newspapers, archives and GitHub, writes a report, checks its citations against the sources, and keeps what it found. Use it for a literature review or your family tree. It runs with a local LLM (Ollama, llama.cpp) or a hosted API.
npm Apache-2.0 ★ 1 -
mcp-archivegithub.com/jeffereychown-Max/mcp-archiveupdated this year
6 Wayback Machine + Internet Archive tools for Claude. Returns archived pages as clean readable text (doesn't blow your context window). Free, MIT.
npm MIT -
MCP server and CLI tool for interacting with the Internet Archive's Wayback Machine
npm NOASSERTION ★ 66 -
har-parser-mcpgithub.com/c0dn/har-parser-mcpupdated this year
Parse and analyze HTTP Archive (HAR) files via MCP
-
Wayback Machine for agents: closest archived copy of a URL with its text, and full capture history
MIT ★ 1 -
Model Context Protocol (MCP) server for interacting with waybackurls for historical URL discovery
npm Apache-2.0 -
Skills-ContextManagergithub.com/Eustaceerrhine977/Skills-ContextManagerupdated this year
🚀 Manage and organize AI skills and workflows with a self-hosted web app featuring MCP integration and dynamic context loading.
-
Three agent-economy products: a GovCon data feed with MCP + x402, an agent-readiness audit engine, and an archive-to-plan tool
-
Open-source, local-first content downloader for AI agents. Save public articles, papers, images, videos, podcasts and subtitles through MCP and a Chrome extension.面向 AI Agent 的开源本地内容下载器,通过 MCP 运行时和 Chrome 扩展,将公开文章、论文、图片、视频、播客与字幕保存为可直接使用的本地文件。
MIT -
Obsidian-Cloud-MCPgithub.com/amarisaster/Obsidian-Cloud-MCPupdated this year
Access your Obsidian vault from Claude — phone, desktop, or web. Syncs to Cloudflare R2, exposes as MCP endpoint.
Apache-2.0 ★ 10