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 |
|---|---|
| UsageMax public observability symbaiex/usagemax Read-only MCP for AI usage profiles, leaderboards, stats, and docs; no writes or private data. | |
| AirStrings symbionix-sl/airstrings-cli Manage AirStrings localization strings and publish signed bundles from your workspace. | |
| Symbioza symbioza/claude-plugin Run a GPU job under a hard dollar cap and collect the files it writes. | |
| Symvanta symvanta/claude-plugin Hosted code graph over MCP: exact callers, dependencies, and cross-repo blast radius for AI agents. | |
| LensHH-LT Optical Design synapseoptics/lenshh-lt Drive real optical lens design: ray tracing, optimization, MTF and aberration analysis. | |
| GhostQA synctek-llc/ghostqa AI personas navigate your web app in real browsers, find bugs and UX issues. No scripts needed. | |
| Research Scan synectic-research/research-scan Finds and ranks recent scientific papers that matter most for a research question or project. | |
| OpenGMB synectus/opengmb Manage Google Business Profiles: reviews, posts, hours and rankings, with human approval. | |
| SynergyBoat synergyboat/landing-webapp SynergyBoat's public company data — services, case studies, AI use cases, team — and lead capture. | |
| io.github.imgul/notion-arena synergyflowlabs/notion-arena MCP server for Notion Arena — 143 Notion components: 132 widgets + 11 recipes | |
| Nodiom Cloud synexiom-labs/nodiom Review your AI agents' work in minutes, not hours of chat. Approve it or send it back. | |
| Synmerco synmerco/synmerco Escrow, trust scores, and marketplace for AI agent commerce on 5 chains. 41 tools, 8 free. | |
| Hanging Context: News For Agents synorb/hanging-context Fresh context for agents. Ask, search or follow stories. Each fact cites a Synorb Manifest. | |
| Synorb: News & Context for AI Agents synorb/synorb-mcp Cited news for AI agents from AI companies, VC firms, private companies and business podcasts. | |
| ContHunt synthenova/conthunt Discover and research viral social content on TikTok, Instagram Reels, and YouTube Shorts. | |
| ai.syntheticbrew/syntheticbrew syntheticinc/syntheticbrew Embed an AI chat widget on your website from your coding agent: provision, configure, get snippet. | |
| Algeria syscli/algeria-mcp Algeria's 69 wilayas and 1541 communes, GPS lookups, and checks for Algerian formats. | |
| ArtistAlly system-alchemist/artistally-mcp Free fan-convention data for AI agents: dates, registration windows & table costs, US & Canada | |
| DeadCat: Reaper systemblueio/deadcat Operate a REAPER session in plain language, with writes verified against REAPER feedback. | |
| lovefengis systemonster/lovefengis-agents Services and prices of lovefengis, a software studio in Izmir, Turkey. Read-only, no auth. | |
| io.github.syvb/publish-access-test-1778815297 syvb/hello-world This is just a test :)) ignroe me | |
| ai.smithery/szge-lolwiki-mcp szge/lolwiki-mcp Generate friendly greetings for any audience. Toggle Pirate Mode for a playful, swashbuckling styl… | |
| Gumiidő – gumicsere-sürgősség szikoramarci/gumicsere Winter/summer tyre change urgency for Hungarian towns from the local 14-day forecast. No auth. | |
| Menlo Labs Shopping MCP t-khush/shopping-mcp Search Amazon products by price and rating, or build curated shopping kits for any goal. | |
| Toll — coin and product checks on Robinhood Chain, Solana, BSC t0ll-xyz/toll-mcp Is there a real product behind a coin? LARP checks plus bundles, snipers and dev records. | |
| Transfers & Car Rentals t1mom777/fiji-agent-api Discover transfers, private drivers, and Fiji rentals with non-persisted quote previews. | |
| Table, Bro table-bro/table-bro Pixel-perfect Material (M3) data tables for your app in one prompt: Claude Code, Cursor, Codex. | |
| TabRunner tabrunner/tabrunner Give browser tasks to TabRunner, an agent in your own Chrome that uses your logins. | |
| co.leafwright/leafwright tactic-systems/leafwright Render HTML, URLs, and templates to PDF. AI drafts templates and fixes them from logs. | |
| io.github.tacticalnoot/agent-embassy tacticalnoot/agent-embassy Agents pay for work and prove it. Verified checks $0.15, recovery $1.00. USDC on Base via x402. | |
| TAG IT Verify tag-it-network/tagit-dashboard Verify on-chain lifecycle state and provenance of NFC-tagged physical products. | |
| Tag Pilot GA4 tagpilot/ga4-mcp Free, read-only Google Analytics 4: reports, funnels, realtime. Sign in with Google, no GCP setup. | |
| Tag Pilot Search Console tagpilot/ga4-mcp Free, read-only Google Search Console: performance, opportunities, URL inspection. No GCP setup. | |
| Japan Public Data (法人番号・登録支援機関・官公需入札) takaratomita/mcp-tools Japan public data: corporate numbers, registered support organizations, government bid notices. | |
| GameFork MCP takayukikomada/gamefork-mcp Publish, fork, improve browser games. No-auth reads; OAuth to post. Wheel: verified ops knowledge. | |
| io.github.takiguchi-yu/google-workspace-mcp takiguchi-yu/google-workspace-mcp An MCP server for Google Workspaces. | |
| Talent Summoner talent-summoner/agent-skills AI candidate sourcing: find, review and shortlist talent worldwide from your AI assistant. | |
| TalkPix talkpix-ai/talkpix-mcp AI product ads, talking-photo and AI videos from chat. Price shown before credits are spent. | |
| SAGE Infinite Search talktosims/sage Find fresh, source-backed rare and one-of-one products at independent retailers. | |
| VolunteerReminder talltimbersgroup/volunteerreminder Import a volunteer roster and preview shifts. Test-mode until a human enables live SMS. | |
| WORKMINE tamerlan0606/dealfinder x402 pay-per-call APIs over MCP, settled in USDC on Base for autonomous agents and developers. | |
| Sovereign Identity Wallet tamtunnel/si-wallet-mcp Self-hosted signing wallet: DIDs, agency grants, and task mandates for AI agents. | |
| willmehr taneron/willmehr Search willhaben.at for second-hand listings and rank the underpriced ones | |
| io.github.tang-vu/keryx tang-vu/keryx Budgeted research with cited evidence and visible payment state on the selected Arc network. | |
| Astrodai Vedic Astrology & Ephemeris Engine tanudai/astrodai Vedic astrology and ephemeris engine calibrated to Swiss Ephemeris and Jagannatha Hora. | |
| my.taokeh/mcp taokeh/taokeh-mcp Malaysian SME accounting, e-Invoice and payroll for your AI. 77 tools; writes are approved drafts. | |
| Taplid taplid/taplid Audit AI responses and artifacts with ALLOW, REVIEW, or BLOCK decisions and trust scores. | |
| io.github.tarang8811/getintel tarang8811/getintel-mcp Manage GetIntel AI visibility (GEO) from your own AI agent. | |
| FootVal target1m/footval-mcp Football match predictions, title race chances, player valuations, live scores, tables and news. | |
| TDA Discord Reader targeted-design-agency/mcp-discord-reader Discord channel operations for AI agents. Fetch, search, mentions, post. 4 tools. |
49,401–49,450 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.