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 |
|---|---|
| Singapore Bus MCP Server agrimsingh/sg-bus-mcp-server Provides real-time Singapore bus information, including arrival times, routes, and stop details via the LTA DataMall API. | |
| Telegram MCP Chigwell agroznykh/telegram-mcp-ag Read-only MCP server for Telegram that enables reading messages and transcribing voice, audio, and video notes via the Telegram API for use with Codex and Claude Code. | |
| BOM-MCP agsinghmac/bom-mcp Provides access to an Electric Submersible Pump (ESP) parts and Bill of Materials database via an MCP server. It enables AI assistants to manage pump models, retrieve assembly components, and analyze BOM summaries including part weights and | |
| autocad-mcp agtmwebtoon/autocad-validation-mcp Enables LLMs like Claude to create and edit AutoCAD drawings via natural language, supporting both headless DXF generation and live AutoCAD LT connection through file-based IPC. | |
| database-remote-mcp agts86/database-remote-mcp Enables remote database access (RDBMS and MongoDB) through MCP tools, supporting read/write queries, schema management, and more. | |
| scamdown agtt/scamdown Enables AI assistants to turn a link, screenshot or phishing message into takedown action: extract links, check redirects and hosting/registrar details, plan and confirm sending of abuse reports to blocklists, hosts, CDNs, registrars and ne | |
| MCP Latin Tools Server agu-oli/mcp-latin-tools Provides Latin NLP tools for tokenization, lemmatization, POS tagging, reported speech detection, and LiLa Knowledge Base querying via MCP. | |
| gaea-mcp aguai2018/gaea-mcp Enables users to author buildable QuadSpinner Gaea 2 .terrain projects, turn real DEM or synthetic elevation into Gaea-ready heightmaps and 16-bit erosion masks, have Gaea itself validate and build the project, and read back the exported he | |
| Elementor MCP Server aguaitech/elementor-mcp A simple server that enables CRUD operations on Elementor data for WordPress pages, requiring WordPress authentication credentials to interact with a target website. | |
| Escalidrau MCP Server aguara-guazu/escalidrau MCP server for Escalidrau, a collaborative macOS whiteboard. Lets AI agents read, draw, edit, rearrange, and export diagrams on a shared canvas in real time. | |
| Infomate MCP agudulin/infomate-mcp Fetches and provides curated tech news, trending topics, hot GitHub projects, and industry updates from infomate.club/vas3k. Enables users to stay updated with the latest developments in technology and programming through natural language q | |
| Instagram MCP Server aguilar1019/ig-mcp Enables AI applications to work with Instagram Business accounts through the Graph API, retrieving profile details and media, pulling engagement insights, publishing images and videos, and reading or replying to direct messages. It also exp | |
| WooCommerce MCP Server aguilar545/woocommerce-mcp-server Enables AI assistants to manage an online store's products, variations, orders, refunds, customers, coupons, shipping, taxes, payment gateways, reports, and settings through the WordPress REST API. It also supports WordPress content operati | |
| baselayer agulaya24/baselayer Serves portable behavioral identity models via MCP.
Extracts how a person thinks, communicates, and makes decisions from text, then provides always-on identity context, semantic fact retrieval, keyword search, and provenance tracing throug | |
| FastAPI + MCP Greeting Template aguliyev/template_fastapi_mcp Enables creating and listing greetings through MCP tools over Streamable HTTP, backed by FastAPI REST endpoints and PostgreSQL persistence. | |
| Agundur GEO Scanner agundur-kde/geo-scanner-mcp Checks whether a website is readable and citable by AI search engines — llms.txt, Schema.org structured data, AI-bot access in robots.txt, content freshness, answer directness, E-E-A-T signals, plus a LocalBusiness Rich Results validator. F | |
| EvoMem-MCP agunet/evomem-mcp Enables AI agents to store decisions as a versioned history, linking each new decision to the one it replaces so that recall always resolves to the decision currently in force instead of obsolete ones. It runs fully locally on a single SQLi | |
| Logtime Summarizer agungadipurwa/mcp-client-server Enables AI assistants to analyze log time data from various sources to summarize project health, employee performance, and client status. | |
| Meta Ads MCP Server agus1k/mcp-meta Connects Claude with the Meta Marketing API to analyze and manage Facebook/Instagram ad campaigns, including retrieving insights, updating campaign status, and listing accounts. | |
| EduChain MCP Server agusain2001/educhain-mcp-assignment Enables AI-powered generation of educational content including multiple-choice questions, lesson plans, and flashcards on any topic through integration with the EduChain library and DeepSeek model via OpenRouter. | |
| Agent MCP agussaputrasijabat/agent-mcp Connects ChatGPT and Claude to your own machine so they can read and edit files, search paths and text, run shell, Git, build and test commands, and keep cross-conversation memory and reusable skills. It exposes these capabilities as 14 Mod | |
| unityxclaude agustedire542/unityxclaude A local MCP server for Unity Editor that provides 20 editor tools to control scripts, scenes, components, assets, and builds. | |
| zoho-mail-mcp agustif/zoho-mail-mcp An MCP server that connects AI assistants to Zoho Mail, enabling reading, searching, sending, scheduling, organizing, and downloading emails through the official Zoho Mail REST API. | |
| fiuba-mcp agustinbn/fiuba-mcp Provides read-only access to a university's Moodle virtual campus, letting an AI assistant browse courses, sections and files, check upcoming deadlines, view assignment status and grades, and read forum announcements and threads. Authentica | |
| Arcade1v1 agustincf/arcade1v1 Let AI agents play ranked 1v1 arcade games (2048, Tetris, Snake, Flappy, Racing, Space Invaders) against humans and other agents — replay-verified scores, public ELO ladder. | |
| projectx-mcp agustindiezdb/projectx-mcp Enables users to manage time entries and log hours on the ProjectX platform using natural language. It provides tools for creating, viewing, and deleting entries, as well as retrieving a list of available projects. | |
| notebooklm-mcp agustinfacu01/npx-notebooklm-mcp-latest An MCP server that enables Claude to interact with Google NotebookLM via browser automation, allowing management of notebooks, adding sources, and querying information. | |
| Spotify MCP Server agustinhopneto/spotify-mcp-server A lightweight MCP server that enables AI assistants to control Spotify playback and manage playlists. | |
| monitor_flota agustinleandrolopez/proyecto-prograconiagen-flota Enables an AI agent to query and update a vehicle fleet stored in SQLite, including retrieving vehicles and alerts, adding vehicles, and modifying their speed or stopped time. | |
| Server MCPS2 agustinrt/mcps2 Enables agents to query dynamically updated real-time context, with asynchronous Kafka-based communication with other servers and auditing of usage metrics. | |
| questrade-mcp agustinsacco/questrade-mcp Enables read-only access to Questrade accounts, portfolios, market data, transactions, technical analysis, and order history through MCP. | |
| ultrahuman-mcp agustinsacco/ultrahuman-mcp Read-only MCP server that enables access to Ultrahuman health data, including daily summaries, sleep, recovery, activity, glucose, and time-series metrics via the Partner API. | |
| markdown-vault-mcp agustinvalencia/markdown-vault-mcp Python MCP server for programmatic access to markdown-based knowledge vaults, enabling AI assistants to browse, read, search, update, and manage notes, tasks, and projects. | |
| doc-redactor agxhub/doc-redactor Provides a local-first MCP server for multi-format document redaction, enabling detection of sensitive content, physical removal from PDFs, DOCX, XLSX, PPTX, and text files, and forensic audit with zero network calls. | |
| loom agxmeister/loom Enables agents to validate, render preview (PNG), and export OpenSCAD models to various formats using the openscad CLI. | |
| agz-memory agzyazilim/agz-memory Enables project-scoped persistent linked memory for OpenCode V2, providing nine MCP tools for recall, update, pin, link, and read operations on notes within isolated projects. | |
| MCP Vision Relay ah-wq/mcp-vision-relay Wraps local multimodal CLIs (Google Gemini CLI and Qwen CLI) as MCP tools, enabling text-only AI assistants like Claude to analyze images through relay calls. Supports local paths, URLs, and base64 image inputs with configurable models and | |
| Expo Docs MCP Server ah2-io/expo-docs-mcp Provides access to Expo documentation with advanced search, full content retrieval, section browsing, API references, and quick start guides. | |
| Advanced MCP Platform ahaakash/own_mcp_server Enables authenticated clients to discover and call tools for scoped file listing/searching, request client-side LLM sampling, and receive real-time progress/log notifications over stdio or secure Streamable HTTP, with tenant/user workspace | |
| PSX MCP Server ahad-raza24/psx-mcp-server Provides 12 tools to scrape and access Pakistan Stock Exchange market data, including current prices, historical data, intraday, sector search, and volume analysis. | |
| AppScope MCP Server ahad690/open-app-intel Self-hosted MCP server for app market intelligence, enabling tools to query app download/revenue estimates, ad intensity proxies, creator mentions, and rank history from local collected data. | |
| ahaft ahaft/ahaft Enables AI agents to safely operate Express applications through a permission-scoped MCP server, with static analysis and audit logging. | |
| cross-shop ahalekelly/cross-shop Batch-first MCP server for product search, product detail, and anonymous shipping quotes across public storefronts and marketplaces, exposing search, product, quote, and images commands with compact JSON output for AI agents. | |
| mintsoft-mcp ahamadfalah/mintsoft-mcp A Model Context Protocol server for the Mintsoft warehouse management system, enabling LLM clients to look up orders, products, stock, inbound, returns, and reports, with guarded write capabilities. | |
| vtop-mcp-server ahamed-2008/vtop-mcp-server Enables an AI assistant to securely access a student's own VIT VTOP account through a read-only, structured MCP interface, providing academic summaries, CGPA, courses, attendance, assignments, events, feedback, and session status. | |
| text-to-speech ahamed-kashif/tts-mcp-server Enables text-to-speech conversion using Google Translate's TTS, supporting many languages and accents, and saving MP3 files. | |
| IBM Content Services MCP Server ahamedfo/ibm-content-services-mcp-server Enables AI models to access IBM FileNet Content Manager capabilities including document management, property extraction, legal holds, and AI-powered document insight through standardized MCP interfaces. | |
| DeepSIFT ahammadshawki8/deepsift DeepSIFT is an MCP server that wraps SANS SIFT Workstation forensic tools with structured JSON output and RAG threat intelligence, reducing LLM hallucinations in autonomous incident response. | |
| Debug MCP ahao0150/debug-mcp An intelligent debugging assistant that automates the debugging process by analyzing bugs, injecting HTTP-based debug logs into code across multiple environments (browser, Node.js, mobile, etc.), and iteratively fixing issues based on real- | |
| AI Knowledge Center MCP ahappyatlas/ai-knowledge-center Local-first MCP server that provides project context, verification gates, and structured tools for coding agents to discover knowledge, run diagnostics, and execute allowlisted commands within a repository. |
24,651–24,700 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.