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.
-
MCP server with deterministic text tools for Claude, Cursor, Codex and other AI assistants: remove duplicate lines, CSV to JSON, extract emails, JSON format, clean text. stdio and Streamable HTTP (Cloudflare Workers, Deno, Bun).
npm MIT -
PText: paste text, get a useful result. Open-source deterministic text tools (remove duplicate lines, CSV to JSON, extract emails, JSON formatter and validator, clean text) as a zero-dependency library, CLI and MCP server for AI assistants.
npm MIT -
webshiftgithub.com/x-hannibal/webshiftupdated this year
Shift noisy web pages into clean, context-ready text for LLMs — Rust library & MCP server
MIT ★ 8 -
MCP server for extracting YouTube video subtitles as clean text
npm MIT -
token-enhancergithub.com/xelektron/token-enhancerupdated this year
A local proxy that strips web pages down to clean text before they enter your AI agent's context window. 704K tokens → 2.6K tokens. No LLM required.
MIT ★ 68 -
An MCP server that gives your AI assistant the whole Drizzle ORM documentation: with typo-tolerant search and full-text search, served as clean Markdown.
MIT ★ 5 -
data-sanitizer-mcpgithub.com/marilynceo/data-sanitizer-mcpupdated this year
Clean and validate data for AI agents. Sanitize JSON, CSV, emails, dates, text, detect PII, normalize phone numbers. Built for the AI agent economy.
-
Read papers as clean text: PDFs and scans become text you can read, translate and ask about, with notes and an agent that reads the pages and the web. MCP connector and REST API. Free to start, the model included.
MIT -
Turn a text PDF or HTML file into clean Markdown, with tables kept as Markdown tables. Runs locally. CLI and MCP server.
pypi MIT -
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.
MIT -
An MCP server exposing a scrape_url tool: fetches a page, strips navigation and ad clutter, and returns clean text. Runs over stdio, drops into any MCP client config.
MIT -
Capiogithub.com/Sai-Lalith-Sistla/Capioupdated this year
Capio — I seize. You saw it, you screenshotted it, then it vanished into 1,000 other photos. Capio reads the text, groups related shots, and saves a clean titled note you can actually search.
MIT ★ 2 -
MCP server that turns any URL into clean Markdown or text for Claude, Cursor & AI agents (article extractor). One tool: extract_url.
npm MIT -
A tiny, keyless, zero-Docker Tavily API mock server & MCP tool for local LLMs (Ollama, Goose, Aider). Backed by DuckDuckGo with TTL caching, single-flight dedupe, and clean page text extraction.
pypi MIT -
Free website crawler for AI coding agents: any site, JavaScript pages and linked PDFs, into clean text. Skill + MCP server for Claude Code, Codex, Gemini CLI, Cursor, Copilot.
MIT -
A general-purpose MCP (Model Context Protocol) server for processing lecture materials from PDFs. Extracts text, chunks it for LLM processing, and converts to clean Markdown with LaTeX support using Google Gemini AI.
MIT -
MCP server: turn any URL into clean Markdown or text for LLMs, RAG and AI agents (article extractor). One tool: extract_url.
npm MIT -
MCP server that converts PDF, DOCX, PPTX, XLSX, HTML and EPUB documents — from a URL or base64 — into clean Markdown, with table extraction, full-text search and OCR for scanned files. No API key required.
pypi AGPL-3.0-or-later -
Free financial reports API — full-text annual, semi-annual and quarterly reports from China, Japan, Korea and Taiwan as clean Markdown. REST API + MCP server for LLMs and RAG.
MIT -
Find and remove the characters that hide in text. The engine behind ghostchars.com, in Python and TypeScript, and the ghostchars CLI and MCP server.
NOASSERTION -
distill-mdgithub.com/gokulnair2001/distillupdated this year
Convert any website into clean, agent-ready Markdown. Local-first, fast, deterministic.
npm GPL-3.0-or-later -
Turn key: value notes, CSV/TSV and Markdown tables into clean, typed JSON. CLI and MCP server. Runs locally.
pypi MIT -
Clean up talk recordings, from one video to a whole event, by hand or through your agent.
MIT -
Web pages and PDFs to clean, LLM-ready Markdown as a remote MCP tool (Claude, Cursor, VS Code) and via the Apify API. Token counts, small crawls, sitemaps, RAG chunks, respects robots.txt. Python and Node examples.
MIT -
CrawlForge MCP Server - Professional Model Context Protocol server with 31 web scraping, crawling, deep-research, and autonomous-extraction tools. Returns clean Markdown and structured JSON for Claude, Cursor, and any MCP client. Defaults to local Ollama
npm MIT