Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| Web URL Reader MCP Server clsferguson/mcp-web-url-reader Enables fetching and reading content from web URLs through a configurable proxy prefix. Uses curl to retrieve webpage content and return it as text for analysis or processing. | |
| Time Server clssck/mcp-time-server An MCP server providing timezone conversions and time-related operations via RESTful API endpoints, featuring comprehensive error handling and timezone database integration. | |
| MCP-researcher Server clssck/researcher-mcp A powerful research assistant that integrates with Cline and Claude Desktop to leverage Perplexity AI for intelligent search, documentation retrieval, API discovery, and code modernization assistance while coding. | |
| Taiwan Stock Agent clsung/tw-stock-agent Provides comprehensive Taiwan stock market data and analysis through MCP tools. Enables querying real-time stock prices, historical data, company information, technical analysis, and market overviews for TWSE and TPEx listed companies. | |
| always-okay club-paradiso/always-okay-mcp Enables AI assistants to turn a rough brief into a sharp concept, brand idea, launch plan, or honest critique using a Frame → Make → Edit → Deliver method with 32 creative-direction principles. Each recommendation can be traced back to its | |
| Databricks MCP Server clubroom/databricks-mcp-server Enables LLMs to manage Databricks clusters, jobs, and notebooks while providing schema references for gold and silver data layers. It allows agents to perform data discovery and execute SQL queries directly against Databricks environments. | |
| windows-computer-use-mcp clubvillarrealfc-oss/windows-computer-use-mcp MCP server for Windows desktop automation, enabling agents to control mouse, keyboard, and UI elements via 22 tools, with OCR, screenshots, macro recording, and autonomous mission execution. | |
| cluby-mcp clubytech/cluby-mcp Enables agents to read Cluby markets, positions, and pre-trade quotes over stdio, using the same arithmetic as the interface while holding no keys and signing nothing. | |
| clue2app-user-mcp clue2solve/clue2app-user-mcp Exposes user, membership, and role administration tools via MCP, acting as a thin passthrough to a coordinator API with RBAC enforced by the coordinator using caller bearer tokens. | |
| b2c-app-builder clueless-creations/brigade Enables AI agents to compose and manage consumer-app capabilities, providers, recipes, and evidence across the full product lifecycle. | |
| Google Play Store MCP clueless-creations/google-play-store-mcp Manages Google Play Store listing text through the official Android Publisher API with dry-run-first safety, supporting CLI for humans/CI and MCP tools for agents. | |
| OpenClueo MCP Server clueofoundation/clueomcp Provides a universal AI personality layer that uses a scientifically-backed Big Five engine to apply consistent character traits and brand voices across MCP-compatible platforms. It allows users to inject custom personality profiles or pres | |
| MCP Cobot Server cluesang/mcp-cobot-server Controls a MyCobot280 robot arm through MCP tools, allowing joint angle manipulation, home position, LED color, and dance routines. | |
| pyBittle MCP Server cluesang/pybittle-mcp-server A Python server that enables remote control of Bittle robots via Bluetooth using the Model Context Protocol (MCP), allowing users to programmatically send movement and pose commands. | |
| cults3d-mcp clugtu/cults3d-mcp Enables AI agents to upload 3D designs, track stats, manage listings, and monitor community engagement on Cults3D. | |
| pinterest-mcp clugtu/pinterest-mcp Enables AI agents to manage Pinterest boards and pins, create and update pins, and track analytics via the Pinterest API v5. | |
| wxauto MCP Server cluic/wxauto-mcp Provides WeChat automation capabilities for AI development tools via the Model Context Protocol. It enables users to send messages, manage contacts, and handle file transfers through AI assistants like Claude and Cursor. | |
| Aave Liquidation MCP Server clumsynonono/aave-liquidation-mcp Enables AI assistants to analyze Aave V3 positions on Ethereum, monitor health factors, identify liquidation opportunities, and query protocol data including collateral positions, debt composition, and real-time asset prices. | |
| browser-console-mcp-tools clusslin/browser_console_mcp_tools Captures browser console messages (log, warn, error, etc.) and makes them available to AI language models like Claude Code and Gemini CLI for seamless debugging and development. | |
| zvec-mcp cluster2600/zvec-mcp Enables AI agents to store, search, and manage a local vector database for RAG knowledge retrieval and long-term memory, powered by zvec. | |
| ETH Price Current Server cluster3115/ethpricecurrentserver A minimal Model Context Protocol (MCP) server that fetches the current Ethereum (ETH) price in USD.
Data source: the public CoinGecko API (no API key required). This MCP is designed to simulate malicious behavior, specifically an attempt to | |
| Claude Code Directive MCP clydelemot/claude-code-directive-mcp MCP server to temporarily add a global Codex directive requiring Claude Code usage until a configured expiry date, with guardrails and cleanup. | |
| Clypmint B-Roll clypmint/clypmint-broll Enables AI agents to source real, license-labelled photos and video clips of the exact person, company, product, or place named in a script, with each candidate checked by a vision model and scored before returning download links or capture | |
| Manual SQLite MCP Server cm004/mcp Enables direct interaction with a SQLite database through custom-mapped tools for creating and retrieving items. It provides structured, AI-optimized responses and manual control over database operations without requiring external API depen | |
| react-perf-mcp cma0232/react-perf-mcp An MCP server that runs parallel AI agents to analyze React components for performance issues, including unnecessary re-renders, memoization errors, bundle size problems, and profiling concerns. | |
| py-mcp-students cmaalto03/py-mcp-students Enables LLMs to manage student records through natural language by wrapping a simple HTTP student server's endpoints as MCP tools. | |
| glean-company-docs cmacdonald0514/glean-chat-bot Enables grounded question-answering over internal documents via a single MCP tool that retrieves relevant passages and generates answers with citations, returning sources and diagnostics. | |
| Exemplos_APIMCP cmacetko/exemplos_apimcp MCP server that bridges Claude to an OAuth-protected API, handling OAuth flows and token refresh to enable tools like listing and creating notes. | |
| TrainHeroic cmagorian/trainheroicmcp Allows for management of TrainHeroic Athlete accounts via MCP and the unofficial API | |
| csharp-mcp-server-blazor cmalpass/csharp-mcp-server-blazor Enables AI clients such as Claude Desktop, Cursor, and VS Code to connect via SSE and JSON-RPC, discover C# methods as MCP tools, and execute them with generated schemas. It also provides a Blazor WebAssembly inspector for monitoring and te | |
| MCP Presidio cmalpass/mcp-presidio An MCP server that enables LLMs to detect and anonymize over 25 types of Personally Identifiable Information (PII) using Microsoft Presidio. It supports various redaction strategies and can process both plain text and structured data to hel | |
| MCP Chrome Google Search cmann50/mcp-chrome-google-search Enables Google search and webpage content extraction via Chrome for macOS, allowing access to both unauthenticated and authenticated content, and integrates with Claude for secure and automated browsing tasks. | |
| mcp-edgar cmanohar/mcp-edgar Enables LLMs to access SEC EDGAR data: search filings, extract sections, pull structured financials, and track insider transactions. | |
| mcp-uspto cmanohar/mcp-uspto An MCP server for searching and retrieving USPTO data, including patents, trademarks, assignments, and PTAB decisions. It allows users to research IP landscapes, track prosecution histories, and analyze inventor or assignee portfolios throu | |
| Sequential Thinking MCP Server cmarin/sequentialthinking-mcp Enables structured, step-by-step problem-solving with dynamic revision and branching capabilities. Supports breaking down complex problems into manageable steps while allowing course corrections and alternative reasoning paths. | |
| homestead-mcp cmarl/homestead Enables MCP-speaking assistants to search an offline library of practical self-reliance knowledge and add new documents to it. | |
| Codebase MCP Server cmaujean/codebase-mcp A Model Context Protocol server that analyzes application codebases with real-time file watching, providing AI assistants like Claude with deep insights into project structure, code patterns, and architecture. | |
| fetch-mcp cmaurer/fetch-mcp Fetches and renders web pages using a headless Chromium browser, returning clean Markdown or HTML content even for JavaScript-heavy single-page applications. | |
| mouser-search-mcp cmaurer/mouser-search-mcp Provides tools to search the Mouser Electronics parts catalog via keyword, part number, and manufacturer queries using the Mouser Search API. | |
| Frontend Code Analysis MCP cmc12138/mcp Analyzes frontend project code (React, Vue, Angular) and converts it into AI-understandable flow diagrams and object structures. Provides tools for code analysis, variable/function/component inspection, and project structure insights. | |
| Cvent MCP Server cmcintosh/cvent-mcp-server Enables management of Cvent events, registrations, attendees, sessions, contacts, surveys, reports, custom objects, and webhooks via natural language through the Cvent REST API. | |
| Claude Gemini MCP Integration cmdaltctr/claude-gemini-mcp-slim A lightweight server that connects Claude Code with Google's Gemini AI models, allowing developers to leverage Gemini's massive context window (1M+ tokens) for code analysis without leaving their coding environment. | |
| NiftyPM MCP Server cmdaltctr/niftypm-mcp A Model Context Protocol server that exposes the NiftyPM project management API as a set of 117 tools for AI assistants, covering projects, tasks, documents, webhooks, and more. | |
| memory-mcp-server cmdparkour/memory-mcp-server Gives any AI tool persistent, searchable memory across sessions using hybrid semantic and keyword search, running 100% locally with no API keys or cloud dependencies. | |
| mcp-awareness cmeans/mcp-awareness Shared memory for any MCP-compatible AI, enabling cross-platform knowledge persistence and retrieval so users' context, preferences, and project info follow them everywhere. | |
| DCR Demo MCP cmedfisch/dcr-mcp-demo Demonstrates OAuth 2.0 Dynamic Client Registration with Duo SSO, providing three MCP servers for calendar events, document management, and analytics dashboards. | |
| infoclimat-mcp cmer81/infoclimat-mcp Enables querying French weather data from Infoclimat via MCP, including station search, observations, and precipitation summaries. | |
| Open-Meteo MCP Server cmer81/open-meteo-mcp Provides comprehensive access to Open-Meteo APIs for weather forecasts, historical data, air quality, and marine conditions. It enables LLMs to query specialized meteorological models, perform geocoding, and access advanced climate or flood | |
| plane-mcp cmet7/plane-mcp An MCP server for the Plane project management platform that enables users to manage workspaces, projects, and work items. It supports full CRUD operations for issues while providing access to cycles, modules, labels, and workflow states. | |
| hive cmgmyr/hive Enables shared, persistent memory and coordination for Claude Code and Codex sessions through a visible crew of tmux workers and a local SQLite store. |
39,451–39,500 of 115,409
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.