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 |
|---|---|
| io.github.mbeato/apimesh mbeato/conway 74 paid web-analysis APIs (SEO, security, TLS, DNS, email) as MCP tools. USDC via x402. | |
| UserTapes mcdca/usertapes-mcp Query real user session replay data: tapes, transcripts, error/rage-click filters, alerts. | |
| Wild Wallet — where agents get a body mcflamingo/wildwallet Agents browse Wild Wallet bodies + closets and file human-approved merge requests. | |
| Noogat mcfredrick/noogat Voice notes that organize themselves. Capture by Siri, AI auto-tags, semantic search retrieves. | |
| io.github.mcfredrick/tenkai-mcp mcfredrick/tenkai Search Tenkai Daily AI news for open-source releases, papers, and tools. Updated daily. | |
| Virga Weather mcmurrym/virga Weather API tools — current, hourly, daily forecasts, and historical data. | |
| Pikelet mcn92/pikelet Search self-contained .pikelet knowledge artifacts over MCP — no vector DB, no embedding API. | |
| Capivara: Investigação Cadastral mcp-dir/capivara-mcp 360º background dossier on a person (or company) from name + CPF: identity, contact, money-to-claim | |
| Segfy mcp-dir/segfy-mcp Segfy, multi-quote and management platform for insurance brokers. Connect your account with your Seg | |
| Tesla mcp-dir/tesla-mcp Tesla Fleet API for AI: send navigation destinations, read battery and location, run car commands. | |
| io.github.mcp-protocol/node-runtime mcp-protocol/node-runtime This package is intended for demonstration only. Maintained by JFrog Security. | |
| inference.sh run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run. | |
| ac.snag/snag Gives your coding agent the captured console, network, replay and screenshot evidence for a bug. | |
| Agentic Engineering Periodic System Practices for building software with coding agents, each with a test you check on your repo. | |
| Inside Ads Telegram ad exchange: estimate reach and cost with no account, then create and run campaigns. | |
| Pantheon Meta ads library, competitor ads, brand voice, avatars and offer briefs from your Pantheon account. | |
| BeachClubs.ae Search UAE beach clubs, day pass prices, amenities, opening hours and events across all 7 emirates. | |
| Brainy Prices — UAE Cost of Living Source-backed UAE costs: groceries, schools, housing, transport, utilities, telecom and relocation | |
| EasyVoice text to speech Hosted text-to-speech MCP server: 66 voices in 9 languages, long-form narration, podcasts. | |
| GENOSYS UAE Shop GENOSYS Korean skincare in the UAE from chat: find products, AED prices, order and pay. | |
| groTAX by Grovisor UAE Corporate Tax: CT computation, SBR, penalties, free zone test, TP and health-check. | |
| Plant Guide: Dubai gardening research What to plant in Dubai, indoor plants, plant care in the heat, garden styles and Garden Care prices. | |
| Projectory Find UAE off-plan developments, registered residential sales and research reports. | |
| Propick Integration MCP Manage your real-estate stock on Propick (Dubai): bulk listing sync, lookups and run reports. | |
| Fenlight Google search results, forum threads, local and shopping data, keyword ideas, AI answer tracking. | |
| Vera Scrape, search and extract the public web. 3,000 free credits at https://vera.waggle.ae/signup | |
| Events.Aero Find aviation events: airshows, fly-ins, workshops and club meets. Public and read-only. | |
| UGC, the Human Ad Network The Human Ad Network. Campaigns, clipping, and Clip Studio from chat. | |
| hood. — .hood name service Resolve .hood names on Robinhood Chain — forward/reverse, text records, availability & pricing. | |
| JustIdea Agency Services, prices, inquiries and free analytics, AI and Google visibility scans by JustIdea, Poland. | |
| Bureau public reader Bureau-operated public read-only MCP service for public Context Packets and Cases. | |
| Third Hemisphere AI Authority Index Read-only CRISP scores and AI visibility data from Third Hemisphere's AI Authority Index. | |
| zoll.agency Regeln und Suchen zur Ausfuhr aus der EU: Kumulierung, Präferenznachweis, Incoterms, Warennummer | |
| 0si.ai Disclosures Korean (DART/KIND) and US SEC filings with AI summaries, direction labels and market reaction. | |
| 1ClickWebsite Build and edit WordPress websites for local service businesses and run Lead Gen demo-site batches. | |
| 1Court Directory US county court directory: clerk, courthouse address, e-filing, filing fees, and case lookup. | |
| 4ai – premium .ai domains for sale Search 254 premium .ai domains for sale, get free .ai value estimates and real .ai sales data. | |
| 69.ai Relationship network for AI agents and people: register, match, chat, dinner ideas, virtual gifts. | |
| Aard Official statistics from 170+ publishers, resolved from natural language with provenance. | |
| aTars MCP Crypto market signals, technical indicators, and sentiment analysis for AI agents. | |
| ai.actwise/ideation Actwise Ideation helps founders benchmark startup and product ideas before they build. | |
| AdAdvisor MCP Server Query Meta Ads performance data — accounts, campaigns, ad sets, ads, metrics & settings. | |
| adkix Turn a website into a short 9:16 video ad: script, cast, voice, shots, music. Asks before spending. | |
| adplane Google, Meta, Microsoft and TikTok Ads in Claude or ChatGPT: reports and changes, created paused. | |
| ai.adramp/google-ads Google Ads MCP server — manage campaigns, keywords, and metrics. | |
| Adrio Create Meta (Facebook and Instagram) ad creatives with AI and research competitor ads. | |
| Adsap Launch and manage Meta and Google Ads from your AI assistant. You approve every change first. | |
| ai.adside/adside AI agents that manage paid ads on Meta, LinkedIn, and Google Ads from any MCP client. | |
| Advisors AI — Route a Store Need to a Service Describe a store's problem: get the matching service, its fixed price, and a request link. | |
| One-Page Readiness Check — 10 Signals, Arabic or English Ten machine-readable signals on one public page: the top miss if any, and a receipt we re-verify. |
26,401–26,450 of 50,909
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.