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.lazymac2x/code-pattern-risk-scanner lazymac2x/code-pattern-risk-scanner-api Cloudflare Workers MCP server: code-pattern-risk-scanner | |
| io.github.lazymac2x/color-palette lazymac2x/color-palette-api Cloudflare Workers MCP server: color-palette | |
| io.github.lazymac2x/cron-collision-detector lazymac2x/cron-collision-detector-api Cloudflare Workers MCP server: cron-collision-detector | |
| io.github.lazymac2x/cron-monitor lazymac2x/cron-monitor-api Cloudflare Workers MCP server: cron-monitor | |
| io.github.lazymac2x/cron-parser lazymac2x/cron-parser-api Cloudflare Workers MCP server: cron-parser | |
| io.github.lazymac2x/data-transform lazymac2x/data-transform-api Cloudflare Workers MCP server: data-transform | |
| io.github.lazymac2x/diff-patch-tools lazymac2x/diff-patch-tools-api Cloudflare Workers MCP server: diff-patch-tools | |
| io.github.lazymac2x/domain-intel lazymac2x/domain-intel-api Cloudflare Workers MCP server: domain-intel | |
| io.github.lazymac2x/embedding-search lazymac2x/embedding-search-api Cloudflare Workers MCP server: embedding-search | |
| io.github.lazymac2x/env-blueprint-validator lazymac2x/env-blueprint-validator-api Cloudflare Workers MCP server: env-blueprint-validator | |
| io.github.lazymac2x/font-metadata lazymac2x/font-metadata-api Cloudflare Workers MCP server: font-metadata | |
| io.github.lazymac2x/form-backend lazymac2x/form-backend-api Cloudflare Workers MCP server: form-backend | |
| io.github.lazymac2x/govdata-korea lazymac2x/govdata-korea-api Cloudflare Workers MCP server: govdata-korea | |
| io.github.lazymac2x/graphql-dos-shield lazymac2x/graphql-dos-shield-api Cloudflare Workers MCP server: graphql-dos-shield | |
| io.github.lazymac2x/graphql-rest-bridge lazymac2x/graphql-rest-bridge-api Cloudflare Workers MCP server: graphql-rest-bridge | |
| io.github.lazymac2x/interactive-api-playground lazymac2x/interactive-api-playground-api Cloudflare Workers MCP server: interactive-api-playground | |
| io.github.lazymac2x/llm-output-quality-monitor lazymac2x/llm-output-quality-monitor-api Cloudflare Workers MCP server: llm-output-quality-monitor | |
| io.github.lazymac2x/smart-data-extractor lazymac2x/smart-data-extractor-worker smart-data-extractor MCP server on Cloudflare Workers · REST + MCP JSON-RPC · free tier | |
| Lazynext Accessibility Checker lazynext-ai/accessibility-checker Scan URLs or HTML for WCAG 2.2 violations. 75-rule manifest, weighted score, shareable reports. | |
| io.github.lazytitan30/billing-doctor lazytitan30/billing-doctor Diagnose Google Play Billing incidents locally, with evidence. Not affiliated with Google. | |
| WhiteMagic — governed local memory for agent continuity lbailey94/whitemagic Governed local-first memory and continuity for AI agents — signed receipts, optional hosted lane. | |
| Metroidvania Studio lbarimi/metroidvania-studio Create and edit connected 2D maps with a local, workspace-scoped MCP server and Lua scripts. | |
| MCP Registry Search: Find, Discover & Install MCP Servers & Tools | Directory, Catalog, Marketplace lbesecker195/mcp_registry MCP registry & directory: search, find & install 31k+ MCP servers & tools. Catalog and marketplace. | |
| Proofsource lcbasu/proofsource-plugins AI visibility: which buyer questions name your brand in ChatGPT, Perplexity, Claude, AI Overviews. | |
| io.github.ldclabs/KIP ldclabs/kip Knowledge Graphs to enable memory persistence, knowledge evolution, explainable interaction. | |
| io.github.ldshaf/daily-scripture-mcp ldshaf/daily-scripture-mcp Daily Bible verse and reflection for morning briefs. Conservative evangelical perspective. ESV. | |
| io.github.LdwS123/oqro ldws123/oqro-mcp Insider, Congress, 13F and federal contract filings for US stocks, each linked to its source. | |
| Leadbay leadbay/mcp AI lead discovery, qualification, and outreach prep on your Leadbay account. | |
| SpecForge leaderiop/specforge Turn your team's rules into checks your AI agent can't skip. Deterministic, no AI inside. | |
| LeadFoxConnect leadfox-shay/leadfoxconnect Marketo MCP server for AI. 130 tools to operate Marketo from Claude, Cursor, or ChatGPT. | |
| LeadMagic leadmagic/leadmagic-openai Research B2B accounts, enrich contacts, and clean and enrich your LeadMagic sheets through OAuth. | |
| LeadMagic Sheets — AI Spreadsheet with Live Enrichment Columns leadmagic/lm-tui AI spreadsheet with live enrichment columns — emails, mobiles, firmographics. | |
| io.github.yvonne-chow/htmlpub-mcp leadpages/htmlpub-mcp Publish AI-generated HTML to a live page on your own domain — from Claude, ChatGPT, or Cursor. | |
| io.github.LeandroPG19/cuba-memorys leandropg19/cuba-memorys Persistent memory MCP server. 28 tools, BM25+MMR+OOD retrieval, tamper-evident audit, code graph. | |
| LeanrIQ leanrads/leanriq Creative-intelligence MCP for campaign strategy, ad builds, QA, and reporting. | |
| dev.leanroute/mcp-server leanroute/ai-gateway Leanroute MCP: route to 13 LLM providers, check pricing/usage/credit, manage keys from any agent. | |
| LeanScale GTM Knowledge leanscaleteam/ls-gtm-brain GTM operations knowledge: delivery playbooks, field studies, benchmarks and operator interviews. | |
| LeanTrading MCP leantrading/leantrading-mcp OAuth LeanTrading tools for eligible Pro, Elite, Blueprint, and Admin users. | |
| com.learningnodes/elen learningnodes/elen Records coding-agent decisions with their limits and marks old ones superseded. Local SQLite. | |
| io.github.LeassTaTT/servicenow-mcp-ai leasstatt/servicenow-mcp-ai ServiceNow MCP server — 67 tools over the full REST surface, every auth method, flows, diagrams. | |
| HitApply lecegues/hitapply-plugin Find jobs, then get a tailored résumé and cover letter for each one. Tracks your applications too. | |
| io.github.leejpsd/nextjs-cache-handler-mcp leejpsd/nextjs-cache-handler Inspect and operate Next.js Redis caches: health, tag state, SWR simulation, safe invalidation. | |
| io.github.leekung125/web-data-toolkit leekung125/web-data-toolkit-mcp YouTube transcripts (video, channel, search), Google Trends, Google Play and App Store reviews. | |
| SPXI-gnΩsis leesharks000/spxignosis Opens Wikipedia sentences against their cited sources; builds sourced knowledge objects into /non. | |
| Oxaide — Singapore company research for AI agents leewenjie/oxaide-mcp Agent-buys cited Singapore company research: ACRA/URA/GeBIZ packs, S$49/390/1500 per job. | |
| Comitelligence — EU Comitology Register left-handed-grannies/comitelligence-v4 Agent-native search of EU comitology: committees, votes, dossiers, and implementing-act documents. | |
| ShareGrokBots legacyinmotion/sharegrokbots-examples Search shared Grok Bots by what they do. Credit the creator. No prompt text. | |
| io.github.legalithm/legalithm-mcp-server legalithm/legalithm EU AI Act compliance in your editor: classify risk, cite obligations, draft Article 50 text. | |
| Legesher legesher/legesher Translate Python between English keywords and your language, with round-trip verification. | |
| ljos leidarljos/ljos Local memory, a work tracker and a shell-command guard shared by coding runners on one machine. |
25,051–25,100 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.