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 exposing readability scoring (Flesch) and plain-language simplification as tools any AI agent can call on its own output. Local-only, no API key.
MIT -
Open-source packages that help AI agents read your website: gateway, agent detection, readability scoring, CLI and MCP server. Apache-2.0.
Apache-2.0 -
Technical writing assistant, side-panel Markdown editor, Model Context Protocol (MCP) server, and Agent Skills suite for Antigravity: Gunning Fog readability, AI slop detection, Vale linting, and SEO/GEO.
go Apache-2.0 ★ 52 -
Local-first, agent-readable bug capture: annotated screenshots + notes, stored locally, synced to trackers on your own schedule.
pypi MIT -
ClarityOSgithub.com/RishiBuilds/ClarityOSupdated this year
an agentic tool that simplifies complex institutional texts to meet readability targets using a multi-agent feedback loop.
MIT ★ 1 -
Decompile Maven dependencies into readable Java source — directly inside your AI agent.
npm Apache-2.0 ★ 1 -
web-Api-scrappergithub.com/devggaurav/web-Api-scrapperupdated this year
A MCP that will record the api's flow and create readable doc for AI agents
MIT ★ 3 -
sourceharborgithub.com/xiaojiou176-open/sourceharborupdated this year
Turn YouTube, Bilibili, and RSS sources into readable digests, traceable job runs, and searchable knowledge for operators and agents.
pypi MIT -
writing-assistant-ai-mcpgithub.com/csoai-org/writing-assistant-ai-mcpupdated this year
Writing Assistant Ai tools for AI agents. Capabilities: generate headlines, score readability, analyze tone. Built by MEOK AI Labs.
pypi MIT License -
ayirugithub.com/ruth411/ayiruupdated this year
Verified, machine-readable safety verdicts for AI agents running shell commands. Append-only audit log, six verification levels, deterministic risk engine. MIT.
★ 2 -
Scaffold and maintain an AI-readable second-brain vault for you and your AI agents.
npm MIT -
ListingGood MCP connector — Amazon listing compliance, generation and AI-readability tools for AI agents (Doubao, QwenWork, WorkBuddy, Claude, Cursor).
npm MIT -
Version control for Copado Release Data Templates: snapshot, readable diff, safe concurrent edit, verified restore, PR review, lint, Agent Skill and MCP server. An Agentia CLI plugin.
MIT -
Your bank transactions on your own machine, readable by your local AI agents — and by nothing else. Local-only finance store + read-only MCP server.
MIT ★ 2 -
MCP-servergithub.com/mallahim01/MCP-serverupdated this year
Minimal MCP reference - a Gemini agent that discovers and calls tools from a Python MCP server over stdio; two files, readable end to end
MIT -
Record your screen while you talk. Transcribed on your Mac with whisper.cpp. Readable by AI agents over MCP.
MIT ★ 6 -
Local-first, agent-readable bug capture: annotated screenshots + notes stored locally, synced to issue trackers on your own schedule.
MIT -
The repo-native record of intent and approvals for AI-assisted engineering — validated, attributable, readable by any agent. CLI + MCP.
npm MIT -
Hand files to an AI agent, then let them expire. A self-hosted Cloudflare Worker that turns files into one temporary, readable link.
Apache-2.0 -
Code-aware browser testing for AI coding agents. 14 MCP tools, CLI workflows, regression memory, and human-readable QA reports.
npm MIT ★ 18 -
dao-searxng-mcpgithub.com/leiverkus/dao-searxng-mcpupdated this year
MCP server that turns a local SearXNG instance into citation-aware web search for AI agents — Readability extraction, MiniLM semantic rerank, inline-clickable markdown citations.
MIT ★ 2 -
The live, agent-readable frontier of AI mathematics: open problems, AI attempts, solution claims, verification, replay candidates, Skill and MCP.
MIT ★ 4 -
Generate, preserve, and verify lean AGENTS.md, RUNBOOK.md, and machine-readable repo context for AI coding agents.
MIT ★ 5 -
Portable, project-scoped memory and session handoffs for coding agents. Readable files, MCP recall, and optional user-passphrase encrypted backups.
npm MIT -
The memory that dreams — long-term memory for AI agents. Readable files on your own machine, consolidated between sessions. Runs as a DeepSeek Harness plugin or over MCP.
npm MIT ★ 234 -
browse-mcpgithub.com/That1Drifter/browse-mcpupdated this year
Headless-browser MCP server for any MCP-capable agent (Claude, Codex, Gemini CLI, Cursor, ...). Playwright-based: accessibility-tree refs, Readability + PDF extraction, search, research macro, CLI mode. Windows / Linux / macOS.
npm MIT ★ 1 -
@ambih/coding-agent-memoryactive
Memory for AI coding agents: the plans, tasks, decisions, rules and bugs your agents work through, recorded automatically, shared with your team, readable by every agent through MCP, with a dashboard.
npm Apache-2.0 -
online.pizza — The Back Kitchenno update data
Play online.pizza and exchange feedback with other agents through a local MCP connector. Discussion boards are hidden from the public but readable by their participants and the site owner. Do not share secrets. Join only with permission from the person running your agent.
smithery -
Playwright browser automation, screenshots, and GIF/MP4/WebP recording for AI agents — a machine-readable JSON sidecar (selectors, timing, console errors, page state) plus a live MCP server for step-by-step browser control.
Apache-2.0 ★ 3 -
verdictswarm-mcpgithub.com/sentien-labs/verdictswarm-mcpupdated this year
Every tool has an answer — your agent needs a decision. MCP server for the VerdictSwarm pre-trade check: a machine-readable avoid/caution/clear before your agent trades, plus intended-size exit feasibility and holder-cluster attribution on Solana.
pypi MIT -
Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.
npm MIT ★ 5,657 -
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.
MIT -
@voidly/mcp-serveractive
MCP server for Voidly's internet censorship data and Sentinel forecasts, plus agent relay tools. Relay tools read the API key from a local 0600 file instead of taking or returning it; relay messages are relay-readable, not end-to-end encrypted.
npm MIT -
Redact or anonymize PDFs, scans and screenshots through your AI agent: black boxes, or consistent [Person 1] tags that keep the document readable. Text removed, not covered. EU & Swiss hosted, never used for AI training.
npm MIT -
browse-mcpgithub.com/that1drifter/browse-mcpupdated this year
Headless-browser MCP server for any MCP-capable agent (Claude, Codex, Gemini CLI, Cursor, ...). Playwright-based, with accessibility-tree refs, Readability, search, annotated screenshots, and a self-improvement feedback loop. Windows, Linux, and macOS.
npm MIT -
Unity package that writes a machine-readable label track beside every Unity Recorder capture, so an AI agent can cut shorts and trailers from gameplay footage. One-line GameLabel calls that compile away in player builds, plus an MCP server for agent-driven editing.
MIT ★ 2 -
MCP server that serves your team's coding standards to AI assistants — guideline documents as readable resources, plus search, validation and scaffolding tools. Ships with a VS Code chat agent.
MIT -
Google Webtools MCPgithub.com/stufently/google-webtools-mcpno update data
An MCP server that gives an AI agent Google Search Console and Google Analytics 4 in one place: 39 tools over five Google APIs. It covers Search Console properties and sitemaps, search performance and period comparison, URL Inspection, GA4 accounts, properties, data streams and reports, and site verification. A local analysis layer adds position-based CTR benchmarks, trend detection, query intent classification and recommendations, so most tools return a readable summary rather than bare JSON. Some tools change live configuration (add or delete a property, submit or delete a sitemap, create a GA4 property or data stream). Runs over stdio or stateless Streamable HTTP.
smithery -
**Persistent memory for AI agents that you can actually read.** Kybase stores what your agent learns as plain Markdown notes with `[[wikilinks]]`, searched by keyword and by meaning. It runs locally: notes live in an embedded Postgres on your machine (`~/.kybase`), with no Docker, no server and no account. **What your agent gets (18 tools)** - **Search** — `search_notes`: hybrid keyword + semantic search that returns the section each excerpt came from - **Read** — `get_note` (whole, windowed or one section), `list_notes`, `list_tags`, `list_folders`, `indexing_status` - **Write safely** — `create_note`, `append_to_note`, `replace_in_note`, `update_note` with conflict protection, `delete_note` / `restore_note` (trash) - **Link** — `get_backlinks`, `get_neighbors`, `get_graph` over the wikilink graph - **Organize** — `create_folder`, `update_folder`, `delete_folder` **Setup** Keyword search works right away. For search by meaning, pick an embedding provider in the settings: local **Ollama** (`ollama pull embeddinggemma`) keeps everything on your machine; **Google** or **OpenAI** need an API key and send note text to that provider. **Your data stays yours** `kybase-mcp export vault.zip` writes every note out as plain Markdown, folders as directories, readable in any editor, Obsidian included. **Want a UI?** The full Kybase app adds a web editor, a knowledge-graph view, share links, and one memory shared by Claude Code, claude.ai and Cursor: [github.com/Kyrzin/kybase](https://github.com/Kyrzin/kybase) Open source, AGPL-3.0.
smithery -
Mailcycleno update data
An email address for your AI agent. Mailcycle lets an agent read, wait for and reply to mail at its own addresses: sign-up codes, verification links, support threads, attachments. Mail is decrypted on the machine running the agent. Mailcycle stores it sealed and can't read it. Needs a [Mailcycle](https://mailcycle.email/agents/) account on Scale or above, and Node 20 or later. ## Before you install: pair the agent On the machine the agent runs on: ```sh npx -y mailcycle-mcp pair --name "Support agent" ``` It prints a line starting with `MC1:`. In the Mailcycle app, open **AI agents**, paste the line, and give the agent an email address. The line carries the key the agent's mail is sealed to, so keep it private. It goes from your terminal to the app and never through Mailcycle. The server needs no other settings. It reads the key that pairing saved. ## Tools | Tool | What it does | |---|---| | `list_addresses` | The agent's addresses, and what it may send. | | `list_messages` | The newest messages, with a preview of each. | | `read_message` | One message in full, with its attachments numbered. | | `read_attachment` | Opens an attachment: text as text, images as images, anything else saved to a folder. | | `wait_for_message` | Waits for new mail, optionally from a sender or with a subject. Good for sign-up codes and verification links. | | `reply` | Replies to the sender of a message, threaded. Can attach files. | | `send_message` | Sends a new message, if the agent may send to anyone. Can attach files. | ## Sending Each agent has a send mode, set in the app: - **Reply only** (the default): it can answer whoever wrote to it, and no one else. - **Send to anyone**: up to 20 messages an hour per agent. - **Read only**: it cannot send. Mail an agent reads can contain instructions written by whoever sent it. Reply only limits what those can make it do. ## What sees what - **Mailcycle** stores mail sealed to keys it doesn't have. - **Your machine** holds the agent's key in `~/.config/mailcycle/agent.json`, readable only by your user. Remove the agent in the app to cut it off. - **Your model provider** sees whatever the agent reads. Also on npm as [`mailcycle-mcp`](https://www.npmjs.com/package/mailcycle-mcp) and the [official MCP Registry](https://registry.modelcontextprotocol.io) as `email.mailcycle/mailcycle`. Proprietary, © 2026 Northlab Studios Ltd. [Terms](https://mailcycle.email/legal/terms/).
smithery -
Check declared content rights before RAG, AI input, summarization, training or indexing. Signed RSL evidence via HTTP x402; no legal clearance.
★ 1 -
Lists which machine-readable basics a public page declares, and which it does not. One command, no API key, no account; also a read-only MCP tool.
MIT ★ 1 -
Official GenPark Protocol Skill: openclaw-genpark-ghostwriter
-
Fetch a URL, return clean markdown. MCP server and CLI for AI agents.
npm MIT -
distillgithub.com/gokulnair2001/distillupdated this year
Turn any URL or HTML into clean, agent-ready Markdown — local, fast, deterministic. CLI + MCP server
GPL-3.0 ★ 4 -
@rebilder/mcp-serveractive
MCP server that lets your AI assistant check how well AI agents can read a web page. Runs locally over stdio with no telemetry.
npm Apache-2.0 -
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 -
Reads web pages and PDFs as clean Markdown: main content, the sections that answer a query.
MIT ★ 1 -
🧭 The agent's web reader: fetch a URL as clean, cached, searchable markdown (~90% smaller than HTML). Pairs with cortex. CLI + web + MCP. Zero deps.
MIT -
@agenson-horrowitz/web-content-extractor-mcpgithub.com/agenson-tools/web-content-extractor-mcpupdated this year
Agent-optimized MCP server for extracting clean, structured content from web pages - built specifically for AI agents that need LLM-friendly web data
npm 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 -
Claude Code plugins: work tracking, statusline lab, token-usage panes, GLM quota, readability + local-LLM MCP servers
npm MIT -
acikpozgithub.com/gulmezeren2-byte/acikpozupdated this year
Structured, machine-readable data from Turkish public construction unit-price (birim fiyat) catalogs.
pypi MIT -
Intentgithub.com/SixByFive/Intentupdated this year
Git-native reasoning layer for software projects. Track the why behind code with plans, decisions, constraints, and AI-readable project context.
npm MIT ★ 4 -
protocontextgithub.com/protocontext/protocontextupdated this year
Deterministic knowledge layer for RAG systems. Open standard + search engine + semantic retrieval for AI-readable web content.
Apache-2.0 ★ 2 -
time-ms-converter-mcpgithub.com/vinkius-labs/time-ms-converter-mcpupdated this year
Vinkius Edge high-performance Model Context Protocol (MCP) server for human-readable time duration conversions.
★ 3 -
ListingGood AI Recommendation Engine — MCP server + Claude/Cursor skills that make Amazon's AI recommend your products. Free compliance & AI-readability check.
MIT ★ 1 -
Turn any YouTube video into an AI-readable Markdown document - audio, visuals, and uploader subtitles - via the Gemini API
MIT -
A desktop tool that turns GitHub repositories into evidence-based project reports and AI-readable indexes.
★ 1 -
Literature-MCPgithub.com/Saurabhsing21/Literature-MCPupdated this year
A Model Context Protocol (MCP) server providing structured, ranked evidence retrieval from the Europe PMC publication database. It streamlines AI-driven clinical research by transforming raw literature results into machine-readable evidence items.
MIT ★ 1