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.
-
cleanweb-mcpstale
A lightweight MCP server for extracting clean web content with intelligent content filtering and Markdown conversion
npm MIT -
MCP server for @Filter Signal Engine API — query content filtering intelligence via Claude Desktop, Cursor, or VS Code
npm MIT -
AgentCloakgithub.com/ryanfren/AgentCloakupdated this year
Secure email proxy for AI agents — content filtering, PII redaction, and prompt injection detection over MCP
NOASSERTION ★ 14 -
ingressward-mcp-servergithub.com/ingressward/ingressward-mcp-serverupdated this year
IngressWard MCP server — filter prompts for injection, evasive spacing, and obscene content
npm -
MCP server for fzf fuzzy finder - enables fuzzy file search, list filtering, and content search
npm MIT ★ 3 -
Brave Search MCP server with intent-aware Jev content filtering.
npm MIT -
mcp-server-requestsgithub.com/coucya/mcp-server-requestsupdated this year
Web Content Retrieval (full webpage, filtered content, or Markdown-converted), Custom User-Agent, Multi-HTTP Method Support (GET/POST/PUT/DELETE/PATCH), LLM-Controlled Request Headers, LLM-Accessible Response Headers, and more.
MIT ★ 7 -
Model Context Protocol server for accessing Shopify Developer and Platform changelogs. 8 specialized tools with configurable sources, category filtering, and full content retrieval.
MIT -
Network operations troubleshooting agent: runbooks as data with metadata filtering, tools over MCP, and an explicit content guard.
MIT -
🔍 MCP server for deep web search - combines Google search with full page content extraction using Mozilla Readability. Supports web, news & image search with domain filtering.
npm MIT ★ 2 -
mcp-server-gsc-progithub.com/ricardo-nth/mcp-server-gscupdated this year
Enhanced MCP server for Google Search Console — fresh data, hourly analytics, search type filtering, content decay detection, keyword cannibalization, and more
npm MIT -
mcp-server-gsc-oauth2github.com/kwp-lab/mcp-server-gsc-oauth2updated this year
Enhanced MCP server for Google Search Console — fresh data, hourly analytics, search type filtering, content decay detection, keyword cannibalization, and more
npm MIT -
A lightweight Model Context Protocol (MCP) server Specialized in intelligently extracting core web content, automatically filtering ads and irrelevant elements, and converting to clean Markdown format
-
MCP server for SearXNG: privacy-friendly web, news, image and video search for AI agents, with page content extraction and structural filtering (headers/footers/nav/sidebars removed on demand)
npm MIT -
Everything-powered MCP server for AI agents: millisecond file search, filtering, aggregation, duplicate detection and content grep on Windows (DSH-ready, 13 tools, 3 resources).
MIT -
Model Context Protocol (MCP) server providing comprehensive access to re:Invent 2025 conference session catalog. Features 13 specialized tools for session discovery, speaker search, and content filtering across 1,843 technical sessions. Includes advanced
npm MIT -
reinventmcpstale
Model Context Protocol (MCP) server providing comprehensive access to re:Invent 2025 conference session catalog. Features 13 specialized tools for session discovery, speaker search, and content filtering across 1,843 technical sessions. Includes advanced
npm MIT -
my-google-search-mcpupdated this year
MCP server that searches Google via Chrome extension and filters any URL's content using an LLM. No bot detection. Works with Claude, VS Code Copilot, and any MCP client.
npm MIT -
Firecrawl Web Scraping Serverno update data
Enable advanced web scraping, crawling, and content extraction with support for JavaScript rendering, batch processing, and smart filtering. Perform deep research and structured data extraction using LLM-powered tools. Monitor credit usage and handle rate limits automatically for efficient and reliable web data integration.
smithery -
vybsly-mcpgithub.com/bluefusionlab/vybsly-mcpupdated this year
MCP server for Vybsly — AI-first search API with 29M+ full-content pages, encyclopedia federation, strict-mode filters, and real-time data tools. Works with Claude Desktop, Cursor, Windsurf, and any MCP client.
npm MIT -
@teamnetwork/m365-mcp-serverupdated this year
MCP server for Microsoft 365 Email and Calendar access using client credentials (app-only auth). Supports multiple accounts, shared mailboxes, per-mailbox read-only access, folder navigation, and date/content filtering.
npm MIT -
Self-hosted family AI gateway with parental controls. Runs on Linux, macOS, and Android (Termux) — Raspberry Pi, mini PC, old laptop, homelab server, even a phone. Telegram, Discord, web. Privacy-first, works with any LLM (local or cloud), OPA content filtering, MCP skill scanning.
AGPL-3.0 ★ 7 -
Secure MCP servers + gateway that connect Claude, ChatGPT, Cursor and other AI assistants to company systems (CRM, helpdesk, read-only SQL, docs, calendar/email). OAuth 2.1, per-role tool filtering, confirmed idempotent writes, untrusted-content marking, audit log. 38/39 agent tasks with a free model. TypeScript
MIT ★ 1 -
ArXivgithub.com/jasonleinart/arxiv-mcp-serverno update data
The ArXiv MCP Server provides a comprehensive bridge between AI assistants and arXiv's research repository through the Model Context Protocol (MCP). Features: • Search arXiv papers with advanced filtering • Download and store papers locally as markdown • Read and analyze paper content • Deep research analysis prompts • Local paper management and storage • Enhanced tool descriptions optimized for local AI models • Docker MCP Gateway compatible with detailed context Perfect for researchers, academics, and AI assistants conducting literature reviews and research analysis. **Recent Update**: Enhanced tool descriptions specifically designed to resolve local AI model confusion and improve Docker MCP Gateway compatibility.
oci -
api-doc-mcp-serverno update data
API Documentation Generation MCP Tool This is an MCP tool for automating the generation of API documentation, which can be integrated into Cursor. The tool orchestrates the entire workflow for generating API documentation, from analyzing the project structure to ultimately producing a complete set of API documents. Features - Automatically orchestrates the API documentation generation workflow - Analyzes the project structure to identify API routes and related code files - Extracts API information (routes, parameters, response structures, etc.) - Generates API documentation in Markdown format - Checks document completeness and automatically supplements missing content Workflow Description - Start Workflow - Initiates the API documentation generation process - Analyze Project Structure - Identifies API routes, controllers, authentication interceptors, and filters within the project - Retrieve API Routes - Locates all relevant code files - Read Code Files - Extracts API route, paramete
pypi -
YouTube Extended Search — FlashDatano update data
# YouTube Extended Search — FlashData Search larger YouTube video result sets, with up to 700 requested results. Map recurring channels and topics from structured video records. Group a larger topic sample by channelId or channelUrl to see which creators appear repeatedly, retaining the underlying video IDs. [YouTube Extended Search API documentation and examples](https://flashdata.dev/docs/sources/youtube_search_extended?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_search_extended-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Extended Search listing](https://smithery.ai/servers/flashdata/youtube-extended-search) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_search_extended`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_search_extended` without submitting a data query. After approving your data-call budget, try: > Search for 100 battery recycling videos, group the observed results by channel, and retain video IDs for later review. This server exposes `youtube_search_extended`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call max_results accepts 1–700, default 20. This is the extended-search product with its own higher rate, not repeated standard search or a guarantee of 700 returned records. The same supported filters are available. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_search_extended", "arguments": { "query": "battery recycling", "max_results": 100 } } ``` ## Work with the output Read results[0].results and group by channelId or channelUrl. Keep the original video IDs and count observed results per channel; retain channel labels for review. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_search_extended", "status": "done", "results": [ { "results": [ { "videoId": "dQw4w9WgXcQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 }, { "videoId": "aqz-KE-bpKQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 } ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The request limit is 700, not a promise of 700 returned videos or pagination. Extended search has its own rate, higher than standard search. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
English profanity filter API + MCP server: find and censor swear words, including obfuscated spellings. Word list, not AI.
MIT -
MCP server for sensitive word detection using Sensitive-lexicon library
npm MIT -
glin-profanity-mcpgithub.com/glincker/glin-profanityupdated this year
MCP (Model Context Protocol) server for glin-profanity - enables AI assistants like Claude, Cursor, and others to use profanity detection as a tool
npm MIT -
Quarto extension that exposes a site's content to in-browser AI agents through WebMCP
MIT -
rss-feeds-mcpgithub.com/aashish/rss-mcp-serverupdated this year
MCP server for fetching, filtering, and searching RSS blog feeds
npm MIT -
rss-feeds-mcpgithub.com/lionkiii/rss-feeds-mcpupdated this year
MCP server for RSS feeds — fetch, filter, search blog posts from any RSS source. Works with Claude Desktop, Cursor, Windsurf. No API keys needed.
MIT ★ 4 -
A light, native macOS browser built on the system's WebKit (SwiftUI + WKWebView, no Chromium). Tabs in a sidebar, ad and tracker blocking with uBlock Origin's filter lists, fingerprinting protection, and an MCP server for AI agents.
GPL-3.0 ★ 1