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 |
|---|---|
| Trading Analysis MCP febrifaresi/trading-mcp An MCP server that gives Claude the ability to analyze trading setups across IDX, Forex, and Crypto markets without executing trades. | |
| mcp-readonly-gateway fechegarzon/mcp-readonly-gateway Enables LLM agents to access third-party APIs through a least-privilege set of audited tools with allowlists, per-caller scopes, label gates, write confirmation, limits, and PII-masked logging. It restricts reads to labeled data, prevents s | |
| ragflow-kb-mcp feci/ragflow-mcp-server Enables agents to manage RAGFlow knowledge bases through the HTTP API, including creating datasets, uploading and parsing documents, editing chunks and metadata, and searching. | |
| actors-mcp fecklesspleb/actors-mcp MCP server that exposes 14 fecklesspleb Apify Actors (job boards, Hacker News, SEO audit, metadata, web tools) as tools; runs bill per result to the caller's own Apify account. | |
| TAS/CAS Jurisprudence MCP Server fedec65/tas-jurisprudence-mcp Enables searching and retrieving arbitration decisions from the Court of Arbitration for Sport (CAS/TAS) for sports law research. | |
| Mercado Libre MCP fedeclavero/mercadolibre-mcp Enables Mercado Libre sellers to manage listings, catalog, stock, questions, and promotions through natural language using Codex and other MCP clients connected to the official API. | |
| tiendanube-mcp fedeclavero/tiendanube-mcp A free, open-source MCP server that connects AI assistants to the Tiendanube/Nuvemshop API so they can manage products, variants, stock, orders, fulfillment, customers, coupons, shipping, payments, content and webhooks from plain-language r | |
| Weather MCP Server fedekrenn/mcp-server-test Enables users to get current weather information for any city using the Open-Meteo API. Provides detailed meteorological data including temperature, precipitation, day/night status, and hourly forecasts through natural language queries. | |
| AIHawk feder-cr/invisible_dots Enables assistants such as Claude Code, Codex, and Gemini CLI to drive a real browser over MCP — navigating, clicking, typing, and reading live pages from plain-English instructions. Supports optional proxy routing, persistent profiles for | |
| invisible-playwright-mcp feder-cr/invisible-playwright-mcp A stealth Firefox browser exposed as an MCP server that lets AI agents browse and interact with real websites without being blocked by anti-bot systems. | |
| MCP TypeScript SDK federated-alpha/mcp A toolkit for building Model Context Protocol servers and clients that provide standardized context for LLMs, allowing applications to expose resources, tools, and prompts through stdio or Streamable HTTP transports. | |
| MCP Server federicazuccarello/mcp-server Minimal MCP server in TypeScript with a LangChain/OpenAI assistant (assist tool) and tools for weather, math, and text-to-speech. | |
| mail-mcp-suite federicokalik/mail-mcp-suite A self-hosted mail bridge for MCP clients that provides read-only IMAP access and approval-gated sending, scheduling, and mailbox management. | |
| tradingview-mcp federicopigozzi/tradingview-mcp Connects Claude Code to your local TradingView Desktop app via Chrome DevTools Protocol, enabling AI-assisted chart analysis, Pine Script development, and workflow automation. | |
| Product MCP Server fedilahbib/mcp-server-using-fastmcp Enables AI agents to manage an in-memory product catalog with tools to add products, search by name or category, and retrieve product details by ID. | |
| keyboard-layout-mcp fedor-help/keyboard-layout-mcp Enables recognizing and converting between keyboard layouts (QWERTY, ЙЦУКЕН, QWERTZ, AZERTY), auto-correcting text typed in the wrong layout, and predictive T9 input from numeric sequences. | |
| Copr MCP fedora-copr/copr-mcp Provides tools to interact with Fedora Copr, enabling users to manage projects, builds, and packages through natural language. | |
| fritzing-mcp fedoragobrowse-design/fritzing-mcp Enables AI agents to search a 2663-part library, place and wire components, validate and headless-render .fzz sketch bundles, generate custom .fzp parts with view SVGs, and hand sketches off to the Fritzing GUI for human review. | |
| kicad-mcp fedoragobrowse-design/kicad-mcp Enables creating and editing KiCad projects through natural language, including scaffolding projects, placing schematic symbols, wires and labels, and adding PCB footprints, tracks and nets. It also runs ERC/DRC checks and exports to PDF, S | |
| ScrapeGraph MCP Server fedorov2912/scrapegraph-mcp Enables AI assistants to perform AI-powered web scraping, structured data extraction, web search, multi-page crawling, JSON Schema generation, and scheduled monitoring through the ScrapeGraph API. It also exposes account credit and job hist | |
| Composite Memory MCP Server fedosis/composite-memory-mcp-server An independent memory service for AI agents that stores and retrieves facts with keyword and semantic search, context management, and a plugin-based architecture. | |
| chameleon fedroraddict/rango Enables AI agents to control and analyze RFID hardware through natural language: read, crack, emulate, and clone cards via MCP tools, with safety gates, offline dump analysis, and a host-side card library. | |
| qsmcp fedsfarm/qsmcp MCP server for developing Quickshell widgets that lets AI agents render individual widgets to PNG previews offscreen, without screen capture or affecting the live shell. | |
| Federated Directory MCP fedwiebe/mcp Enables contact searches within the Federated Directory system by name or email address. Provides comprehensive logging and automatic query type detection for seamless contact lookup integration. | |
| mcp-ory-kratos feedback-loop-ai/mcp-ory-kratos MCP server for managing Ory Kratos identities, sessions, and authentication flows, enabling AI assistants to perform identity management tasks via natural language. | |
| Feedico AI Coupon Agent feedico-io/feedico-ai-coupon-agent MCP server that turns AI IDEs into a Feedico coupon agent, enabling natural language queries for live affiliate coupons and merchants across multiple languages. | |
| cosyvoice-ko feedingstick321-maker/cosyvoice2-ko-sft-mcp Local Korean text-to-speech MCP server using a fine-tuned CosyVoice2 model, enabling voice synthesis directly from Claude or Codex with privacy and no API costs. | |
| Browser MCP Server feedmepos/browser-mcp Enables AI agents to operate a real, anti-bot-aware browser through Zyte API for navigating pages, clicking, typing, scrolling, taking screenshots, searching, and extracting structured data, with automatic proxy rotation and ban avoidance. | |
| FeedOracle Compliance MCP Server feedoracle/feedoracle-mcp 53 regulatory compliance evidence tools across 3 MCP servers for AI agents. MiCA authorization status, DORA evidence packs, stablecoin risk scoring (105+ tokens), macro intelligence (86 FRED series). Every response ECDSA-signed (ES256K), bl | |
| T-IA Connect (Siemens TIA Portal) feelautom/tia-copilot-genai-bridge Industrial-grade MCP server for Siemens TIA Portal (V17–V21). 120+ tools for PLC programming: create blocks (FB/FC/OB/DB), manage tags, compile, download, and simulate with PLCSim Advanced. On-premise, sovereign-AI compatible. | |
| Ask-My-Data MCP feelgom/ask-my-data-mcp Automatically routes natural language questions to RAG or Text2SQL paths to answer queries about virtual construction site data, supporting semantic search and structured aggregation. | |
| career-mcp feelgom/career-mcp Enables recruiters to query a person's career, projects, and impact using natural language, acting as a living resume. | |
| PointCloud MCP feelgom/pointcloud-mcp Enables querying 3D point cloud files (PLY/PCD) using natural language. Provides tools for point cloud description, plane detection, and ICP alignment. | |
| mcp-gateway feelyourprotocol/mcp-gateway MCP server that enables AI agents to simulate EVM bytecode and probe capabilities, serving as a gateway to an Ethereum execution engine. | |
| Salt MCP feesch/salt-mcp Enables AI agents to build React applications using JP Morgan Chase's Salt Design System by providing real-time access to component APIs, documentation, and accessibility guidelines. It supports tasks such as scaffolding new projects, build | |
| vHal MCP Server feevlic/vhal-mcp-server Enables Android Automotive developers to explore and implement Vehicle Hardware Abstraction Layer (vHAL) properties with intelligent tools for property analysis, source code lookup, implementation guidance, and automated code generation for | |
| Cloudflare API MCP fefergrgrgrg/coinspace A lightweight MCP server that enables agents to interface with Cloudflare's REST API, allowing management of DNS records and other Cloudflare services. | |
| Create MCP fefergrgrgrg/create-mcp A CLI tool that sets up a Model Control Protocol server and deploys it to Cloudflare Workers, allowing you to quickly create custom tools for your Cursor Agent just by writing TypeScript functions. | |
| WorkOS MCP Server fefergrgrgrg/cs-insight A lightweight MCP server that enables Cursor Agents to interact with the WorkOS API, providing access to WorkOS functionality directly from within the editor. | |
| Frontend Review MCP fefergrgrgrg/cs-wallet An MCP server that reviews UI edit requests by comparing before and after screenshots, providing visual feedback on whether changes satisfy the user's requirements. | |
| Neon MCP Server fefergrgrgrg/insight A lightweight Model Control Protocol server that allows agents like Cursor to interface with the Neon database REST API through Cloudflare Workers. | |
| Vercel MCP fefergrgrgrg/smileyco.in An MCP server that provides various tools for interacting with the Vercel API, enabling management of deployments, DNS records, domains, projects, and environment variables through natural language commands. | |
| webdev-mcp fefergrgrgrg/smileycoindev An MCP server providing web development tools such as screen capturing capabilities that let AI agents take and work with screenshots of the user's screen. | |
| governance-mcp-server fefogarcia/dodaone-mcp-server MCP server for querying the DodaOne governance framework, enabling users to retrieve governance information and evaluate proposed actions. | |
| goai_tools_mcp feghal/goai_tools_mcp 31 deterministic utility tools over one public endpoint: image conversion and lossless EXIF/metadata stripping, App Store screenshot/icon/favicon generation, WCAG and OKLCH colour maths, .strings and provisioning-profile checks, plus TDEE, | |
| Semantic Scholar MCP Server fegizii/semanticscholarmcp Enables access to the Semantic Scholar Academic Graph API for searching and retrieving detailed information about academic papers, authors, citations, and references. | |
| claude-code-delegate-local fegone/claude-code-delegate-local MCP server that delegates Claude Code subagents to alternative backends such as local models, DeepSeek, or AWS Bedrock, while keeping your Claude Code orchestrator session intact. | |
| Multi Cluster Kubernetes MCP Server feibai406/k8s-multicluster-mcp An MCP server that enables interaction with multiple Kubernetes clusters simultaneously, providing comprehensive tools for cluster management, resource operations, and diagnostics across different environments. | |
| feishu-mcp feifan2024/feishu_mcp Enables AI clients to read, write, and search Feishu (Lark) documents, wiki pages, spreadsheets, and bitable records over MCP, with stdio or authenticated HTTP(S) transport. | |
| code-sandbox-mcp feifeigood/code-sandbox-mcp MCP server for E2B code sandbox, enabling creation, management, and execution of code in secure sandboxes using Python and shell commands. |
49,951–50,000 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.