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 |
|---|---|
| orm-preflight sikandar100/orm-preflight Checks TypeORM migrations for data loss, table locks, and deploy problems before they run. | |
| KeyReady — Australian home loan readiness silas-dsc/keyready Australian home loan readiness: ~90 lenders' rules, stamp duty, grants, 5% Deposit Scheme, rates | |
| io.github.silex-tec/silex silex-tec/silex Local-first MCP server that reconstructs architecture, workflows and business rules from your code. | |
| io.github.SiliconRoshiBill/heropedia siliconroshibill/heropedia-plugin Consult 324+ expert personas (Buffett, Jobs, Munger, Torvalds, ...) via 4 read-only registry tools. | |
| Speak To Your Database silkflo/speak-to-your-database Odoo MCP server, plus PostgreSQL and MySQL: ask your business data in ChatGPT or Claude. Read-only. | |
| Silvanexum silvanexum/silvanexum-sdk Spend control for AI agents - cost attribution, budget caps, and signed runs as MCP tools. | |
| io.github.silverstein/minutes silverstein/minutes The private, owned conversation-memory layer for AI. Record, transcribe, and search every meeting. | |
| SlopIt: blogs for AI agents simbastack-hq/slopit Blog MCP server: your agent signs up itself, publishes markdown posts, and gets a live blog URL. | |
| SimianX AI simianx-ai/simianx-skills 8-agent research committee, live analysis and scored news on US stocks and crypto, for any agent. | |
| Toronto Tech Week 2026 Events simistern/ttw-chat Search 500+ Toronto Tech Week 2026 events by date, theme, audience, format, and neighborhood. | |
| Coach Icarus simkessy/icarus Adaptive running coach MCP server — training data, plans, and recovery for AI assistants. | |
| io.github.simlir/simlir-mcp-server simlir/simlir Simlir MCP server for semantic product search, visual search, and exact product lookup. | |
| Pressbox News Wire simms2/pressbox-ai-integrations Search published Pressbox press releases and newsrooms with original source links and dates. | |
| com.ascent-partners/coso-mcp simonmak-ascent/coso-mcp Open COSO internal-control review MCP: scope, risk, controls, sampling, testing, workpapers. | |
| Vision Driven Design (VDD) MCP Server simonmak-ascent/vision-driven-design Spec-driven development MCP server: 8 phases, bi-directional traceability, 7 quality gates. | |
| ReadingRate simonsbookclub/readingrate-plugin Book difficulty, reading times and ranked lists, plus your reading log, quotes and clubs. | |
| Fundamentals MCP simontarara62/fundamentals-mcp Unofficial read-only MCP for fundamentals, macro & news (EDGAR + FRED + Tavily, BYO-key). | |
| RoamWorthy simonwbird/caravan-dream-finder Live UK caravan, motorhome and campervan search, matching, dealer stock and model research. | |
| Email Verify simplebusinesssuite/email-verify Verify email addresses in chat: real-time deliverability checks with a clear verdict. | |
| io.github.simplemindedbot/mnemex simplemindedbot/mnemex Temporal memory for AI with decay and reinforcement. Two-layer storage (JSONL + Markdown). | |
| Simplifyd Cloud simplifyd-systems/cloud-mcp Deploy and manage services, databases, domains and DNS on Simplifyd Cloud. | |
| SimplyPrint: 3D Print Farm Management simplyprint/simplyprint-claude-plugin 3D print farm management for AI. Monitor, queue, and control prints on your SimplyPrint account. | |
| KDP Niche Research simul813/kdp-intelligence-api Kindle niche intelligence (demand/competition/BSR/revenue) gated by x402 USDC on Base. | |
| verifyfirst simulacra/verifyfirst Look up what your verification method cannot see: 48 failures that report success. | |
| box by Simular simular-ai/box-plugin A cloud Linux desktop for your AI: browse, click, type, read the screen and run commands. | |
| com.spacemushroom/materials simulsarker007/space-mushroom-mcp Read-only sourced engineering materials data: every value with unit, conditions and source. | |
| Since.dev since-dev/mcp Watch dependencies, verify facts, inspect coverage, and catch up on changes with durable cursors. | |
| io.github.sincekmori/negirau sincekmori/negirau Read-only, anonymous access to the Negirau public API: subjects and their reaction counts. | |
| io.github.singhpratech/notepatra-mcp singhpratech/notepatra Notepatra editor MCP server — 35 tools; every write human-approved in the editor; local-only. | |
| com.singularity-app/mcp singularityappllp/singularity-app-mcp-plugin Manage tasks, projects, habits, Kanban boards, and time tracking with SingularityApp. | |
| Nonlinear Calendar singularitybpjade/balance-engine Nonlinear Calendar: this year’s months fold onto the previous 12 years. No key to try. | |
| agent.social singularitystudiosdev/agent-social Free social platform for AI agents — boards with tool-call receipts; MCP server + REST API. | |
| AIYuCha Domain Intelligence sinianchu9/aiyucha-mcp-server Analyze public domain names: naming features, structural value, RDAP/ICP evidence, and comparisons. | |
| MetaMesh-UGA siouxtxt/metamesh-uga Serverless edge control plane to discover, route and monetize 14,982+ MCP tools. | |
| AgentBuilders sirarchiemccarthy-oss/clawd Deploy full-stack web apps with database, file storage, auth, and RBAC via a single API call. | |
| Custom Domain API sireto/custom-domain Register a SaaS app's customer hostnames, show their DNS records and checks, recheck or delete them. | |
| UniFi Access MCP sirkirby/unifi-mcp Manage UniFi Access doors, credentials, policies, visitors, and events via MCP. | |
| UniFi Network MCP sirkirby/unifi-mcp Manage UniFi Network devices, clients, firewall, VLANs, VPNs, and more via MCP. | |
| UniFi Protect MCP sirkirby/unifi-mcp Manage UniFi Protect cameras, events, recordings, and smart detections via MCP. | |
| AdminHub for Telegram siteboss777-lgtm/telegram-admin-hub Run a Telegram channel from your AI agent. Posts go out through your own bot, not your account. | |
| SiteGPT Docs sitegpt/agent-skills Search the SiteGPT documentation: setup, features, API reference, troubleshooting. | |
| BackendGen sitouhemi/backendgen Validate compact backend specs and generate tested NestJS, Prisma, and PostgreSQL repositories. | |
| 큐넥터 sj-park-yesnet/qnector 큐넥터 계정으로 품목·재고·주문·견적·정산을 조회하고, 확인 후에만 변경합니다. | |
| io.github.sjh9714/journal sjh9714/journal Personal journal kept as Markdown files: search, On This Day, append to today, Day One import. | |
| io.github.sjh9714/mergewarden sjh9714/mergewarden Check whether a coding agent's changes stayed inside the scope it was given. | |
| com.skopik/mcp skalerlabs/skopik Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources. | |
| SkanQRCode skanqrcode/sdk-examples Check whether a URL or IP is safe before an AI agent fetches or opens it. | |
| Skarn skarn-security/skarn-dist Scans AI coding sessions and assistant configs for leaked secrets and risky hooks; local, redacted | |
| DMARC Shark — Email DNS Checker skatkov/dmarcshark Check a domain's public SPF, DMARC, MX and DKIM DNS records on demand. No account required. | |
| Skavio USDC Payment Verification & Proof MCP skavio-eu/skavio-agent-tools 18 tools: USDC verification, matching, evidence PDFs, DNS/TLS and authenticated company processing. |
48,951–49,000 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.