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 |
|---|---|
| Weblate MCP by usefulapi m190/usefulapi-mcp Read Weblate projects, strings, stats and changes; translate, suggest, comment and autotranslate. | |
| Webshipper MCP by usefulapi m190/usefulapi-mcp Read orders, shipments and tracking events; create orders and rate quotes in Webshipper. | |
| WeFact MCP by usefulapi m190/usefulapi-mcp Look up customers, invoices, products and subscriptions in WeFact. | |
| WeFile MCP by usefulapi m190/usefulapi-mcp Create and save CT600 filings, generate documents, submit to HMRC and check status in WeFile. | |
| Wellknown MCP by usefulapi m190/usefulapi-mcp Read venue, treatments, open times and bookings; set hours and blocked times in Wellknown. | |
| WhatConverts MCP by usefulapi m190/usefulapi-mcp Read WhatConverts leads, calls, forms, accounts and profiles; add leads and update lead value. | |
| When I Work MCP by usefulapi m190/usefulapi-mcp Check shifts, time clock entries, time-off requests, swaps and availability, and manage shifts. | |
| WHOOP MCP by usefulapi m190/usefulapi-mcp Read WHOOP recovery, sleep, cycles, workouts and body measurements. | |
| Wild Apricot MCP by usefulapi m190/usefulapi-mcp Look up members, events, registrations, invoices and payments, and add contacts or check in guests. | |
| Wincher MCP by usefulapi m190/usefulapi-mcp Read Wincher keyword rankings, SERPs, competitors and history; add keywords, groups and notes. | |
| Workfeed MCP by usefulapi m190/usefulapi-mcp Review staffing, availability and leave; create or update shifts with confirmation. | |
| Workiz MCP by usefulapi m190/usefulapi-mcp Manage Workiz jobs and leads: create, update, assign team members and convert leads to jobs. | |
| Workyard MCP by usefulapi m190/usefulapi-mcp Read Workyard employees, projects, time cards and geofences; approve time cards and add notes. | |
| WuBook MCP by usefulapi m190/usefulapi-mcp Read WuBook ZaK rooms, availability and reservations; manage inventory and guest check-in. | |
| Wufoo MCP by usefulapi m190/usefulapi-mcp Read forms, fields, entries, reports and comments by field title, and submit entries. | |
| YouCanBook.me MCP by usefulapi m190/usefulapi-mcp Manage YouCanBook.me bookings, booking pages, appointment types, team members and locations. | |
| YouTube Data MCP by usefulapi m190/usefulapi-mcp Search videos; read channels, playlists, comments and popular videos in YouTube. | |
| Yuki MCP by usefulapi m190/usefulapi-mcp Read Yuki administrations, open invoices, ledger balances, contacts and documents. | |
| Zadarma MCP by usefulapi m190/usefulapi-mcp Read balance, tariffs, SIP and PBX status and call logs; send SMS in Zadarma. | |
| Zammad MCP by usefulapi m190/usefulapi-mcp Search and read Zammad tickets, customers and organizations; add notes, replies and ticket updates. | |
| Zenamu MCP by usefulapi m190/usefulapi-mcp List classes, workshops and clients; grant passes or credits to clients in Zenamu. | |
| Zenbooker MCP by usefulapi m190/usefulapi-mcp Read Zenbooker jobs, customers, invoices and timeslots; add customers and job notes. | |
| Zendesk MCP by usefulapi m190/usefulapi-mcp Read tickets, users, orgs, macros and satisfaction ratings; create, update and comment on tickets. | |
| Zenfulfillment MCP by usefulapi m190/usefulapi-mcp Read Zenfulfillment orders and stock; import or cancel orders and mark returns done. | |
| Zenserp MCP by usefulapi m190/usefulapi-mcp Search Google, images, news, maps, shopping, YouTube, jobs, hotels, flights and trends with Zenserp. | |
| Zettle MCP by usefulapi m190/usefulapi-mcp Read sales, products, stock, balance and payouts; create products in Zettle. | |
| Ziflow MCP by usefulapi m190/usefulapi-mcp Search and read proofs, comments and activity, and add or resolve comments in Ziflow. | |
| Zigaflow MCP by usefulapi m190/usefulapi-mcp Read clients, quotes, jobs, invoices, products, stock, suppliers and tickets in Zigaflow. | |
| Zylvie MCP by usefulapi m190/usefulapi-mcp Review Zylvie coupons, sales transactions and subscriptions. | |
| TEK BOSS Small Business AI Strategy Assessment m2201/tekboss AI strategy, workflow automation, and process-improvement assessment for small businesses. | |
| io.github.m2ai-mcp-servers/mcp-dyson-appliances m2ai-mcp-servers/mcp-dyson-appliances MCP server for controlling Dyson air purifiers and fans | |
| io.github.m2ai-mcp-servers/mcp-philips-hue m2ai-mcp-servers/mcp-philips-hue MCP server for Philips Hue smart lighting control | |
| io.github.m2ai-mcp-servers/mcp-ratchet-clinical-charting m2ai-mcp-servers/mcp-ratchet-clinical-charting MCP server for clinical charting with Claude - document patient visits to EMR | |
| m2ml — AI-to-AI Knowledge Network m2ml/m2ml AI-to-AI knowledge network. Agents share insights, ask questions, build reputation over MCP. | |
| m2m.monster Arena m2mmonster/m2m-arena Signed, chained trading-strategy signals for Pacifica perps: records, rankings, creator tools. | |
| Energy Podcast Digest m4rz910/podcast-toolkit Read energypod.io's weekly energy digests, episode summaries, and transcripts. Read-only. | |
| Contexter maaakso/contexter-mcp Share one project context across ChatGPT, Claude, Telegram and any MCP client. | |
| io.github.mac146/issuewatcher mac146/issuewatcher Ranks new GitHub issues for your AI assistant: what to pick up, what may break your projects. | |
| Spann Stays machiasturner/simmon-core Read-only sample stays, booking constraints, and staged reservation actions for review. | |
| Jaxonomy — hybrid dynamical systems on JAX machinavitalis/jaxonomy Build, simulate and calibrate JAX block-diagram models of hybrid dynamical systems. | |
| Pipe (SPR) MCP Server machuraharry/pipe AI-native runtime with built-in MCP server. 232 builtins, AI pipelines, RAG, single ~8 MB binary. | |
| Maci maci-intelligence/developers Read refrigeration units, service history, F-gas logs and alarms in Maci. Read only. | |
| IRL Gateway macropulse-lab/irl-gateway An AI agent's trading mandate it can't break: checked before every order, reasoning sealed in IRL. | |
| comdirect mad4ms/comdirect-mcp Read-only access to comdirect accounts, transactions, depots, orders and postbox documents. | |
| art.maddegen.agent/solsnap maddegenog/solsnap-mcp Solana token/wallet rug-risk scoring. Free scan; $2 SOL unlocks full wallet report. No signup. | |
| finance.maddog/mcp maddogfinance/maddog-mcp Price-action reads with measured accuracy: day-type odds, breakouts, public scoreboard | |
| io.github.MadeByFYI/madeby madebyfyi/madeby Disclose AI authorship of code per the ACO standard — tools for AI coding agents. | |
| io.github.madezmedia/acmi-mcp madezmedia/acmi Persistent agent memory via ACMI — Profile/Signals/Timeline. 16 tools on Upstash Redis. | |
| PropXchain madhatt4/propxchain-mcp-server UK property transactions: status, checklists, documents, HM Land Registry intel. | |
| Bug Detector madhavi-opsera/bug-detector Analyzes code for bugs, security vulnerabilities, and code smells |
26,051–26,100 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.