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 |
|---|---|
| Fairly Cheapest way to play a PC game: real checkout prices, Game Pass and a buy-vs-subscribe planner. | |
| GAMES.GG Game guides, reviews, news, deals and release dates, plus saved games and redeem code alerts. | |
| Machina World Cup Intelligence World Cup 2026 match, team, player and market context from Machina Sports, the sports AI platform. | |
| Remix Games Find and play free games made by creators on Remix: puzzle, arcade, racing, sports and more. | |
| Scrappy Cloud Browser Cloud browsers for AI agents: saved logins, residential IPs, live human takeover, 57 browser tools. | |
| var.gg Naming Memory Curated multilingual dictionary that names code identifiers from domain concepts (KO/JA/ZH/VI/EN). | |
| Worldtable Play and build AI RPG worlds: your agent tells the story, Worldtable keeps HP, items and the map. | |
| Cocktail Glass Search 500 cocktail recipes, get full recipes, find drinks by ingredient, suggest random picks. | |
| Insurers Global Search the world's licensed insurers by country, class, group and regulator. Read-only, no auth. | |
| global.rootz.cars/marketplace AI-native used car marketplace. 145K+ vehicles, 4300+ dealers, 13 US states, 20 MCP tools. | |
| global.rootz.companies/companies Verify a US company: officers, agents, motor carriers. Flags when our status disagrees with state. | |
| global.rootz.dtv/broadcast Which TV transmitters actually reach an address, terrain-graded, and what is on now. | |
| global.rootz.private/companies Confirm a US business is real and find who controls it. 32.6M official registry records. | |
| EmailVerify by Techforce Global Verify email addresses: syntax, MX, disposable, role, SMTP mailbox, catch-all and typo checks. | |
| United AI Network Inspect public research tasks. Published by UAIN’s AI-operated campaign; joining needs permission. | |
| Caddence Live UK golf equipment prices: retailer offers, price history and deal ratings in GBP. | |
| Morris Golf Your golf coach in your AI: handicap, rounds, reports and swing analysis from your own account. | |
| goog.workspace-developer/developer-tools Provides tools for searching Google Workspace documentation and much more. | |
| Jobily Jobs Search Greek job listings on Jobily.gr by role, location, sector or company. Anonymous, read-only. | |
| Leeveel Company facts about Leeveel: general info, ideology, contact details, company and tools. | |
| Time.Graphics Interactive timelines on your Time.Graphics account: events, periods, BC dates, sharing, export | |
| 艾达 ADA Free APIs for AI agents: web reading, text slicing, clock, ID keys, 1MB memory. No signup or fees. | |
| Highland Intel APIs 70 pay-per-call APIs: DNS, email auth, security headers, web search, scraping, AI. x402 USDC/Base | |
| TCC Group website Read-only tools for tcc.group: contact card, documents, page search and page content. | |
| guide.capitol/capitolguide Navigate the U.S. Capitol complex: decode room codes, route buildings, check access, amenities. | |
| Easy Scribe Turn screen recordings into step-by-step guides, SOPs and user docs with screenshots. | |
| smm.guide SMM panel catalog: cheapest services across panels, Trust Scores, reviews, comparisons, panel tools | |
| What's Cooking Ask Gusto what to cook tonight from what you have. One full dinner: recipe, steps, shopping list. | |
| bordeaux.guru — Bordeaux en primeur & terroir First-hand Bordeaux en primeur tasting notes, appellation climate, phenology and terroir. | |
| guru.goanywhere/storefront US college admissions fit (College Scorecard bands) + verified admitted-student mentor search. | |
| guru.junkyard.botfeeder/the-junkyard Parsed public-domain market data for AI agents, priced below DIY inference cost, paid via x402. | |
| Krew Guru Maritime vacancies for seafarers and CV import into a Krew Guru profile. | |
| Lumin guru The calculation and trust layer for astrology agents. Every value returns with its rule and source. | |
| Agent Verifier Test and debug your AI agent's Web Bot Auth (RFC 9421) signature: is it valid, and what to fix? | |
| Rung public career guides Find public career guides, explore grounded occupations, and open Rung for private resume work. | |
| Register.gy Check, register and manage .gy (Guyana) domains, and connect AI-built websites with preview + undo. | |
| health.anomaly/physician-review Physicians for the agentic era. Book a US-licensed doctor: orders, prescribes, 90-day plan. | |
| Libby Health Read-only access to your own lab markers, trends, and reports. | |
| Picardo Find Picardo's clinician-designed blood test panels and Labcorp tests, and get an order link. | |
| Picardo Supplements Turn a list of supplements into one custom daily supplement from Picardo, with a link to buy it. | |
| Splot Persistent food journal for AI assistants. Log meals, save recipes, plan meals and track nutrition. | |
| Verzi Health Medicare DME coverage by HCPCS code and date of service, with CMS citations and signed receipts. | |
| Voa Access Voa patient records and prepare clinical documents for review and confirmed saving. | |
| 1031.help: exchange deadlines, tax math and DST filings 1031 exchange 45/180-day deadlines, sale vs. exchange tax and boot, DST Form D filings. | |
| 501c3.HELP nonprofit compliance Nonprofit compliance rules for all 50 US states, each with its official citation and status | |
| help.agentmesh/agentmesh Open-race task marketplace: AI agents post tasks, deliver, and settle in escrowed credits. | |
| AgentPay — Pay-per-call AI Microservices 34 pay-per-call AI and data tools over x402; USDC on Base; no API keys. | |
| Alcohol.help: medication treatment finder US alcohol use disorder programs that prescribe medication, by ZIP, state or city (SAMHSA data). | |
| Awning Find and book local services, classes and rentals; businesses set up and manage their pages. | |
| BioRobot Human for hire by AI agents: ground-truth checks, photo evidence, errands near Crystal Lake, IL |
37,801–37,850 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.