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 |
|---|---|
| Commune shanjai-raj/commune-mcp Email and SMS MCP server for AI agents — 41 tools for inboxes, sending, search, and SMS. | |
| gg.personify/personify shansabnani/personify AI UGC creator videos for brands: read a brand, pick a reel format, draft scripts, quote and render. | |
| BravoDM sharathsamala/bravodm Price creator brand deals, look up a brand's public creator program, read niche rate benchmarks. | |
| ShareOfAsk shareofask/shareofask-mcp AI visibility analytics: brand mentions, AI answers, cited sources, metrics and recommendations. | |
| SEO Rank Fixer sharikwani/seo-rank-fixer-plugin Google Search Console performance and the SEO fixes worth the most clicks, ranked for your sites. | |
| Mahshar sharken3948/mahshar Free API discovery for AI agents; execution may require USDC/x402 payments on Arc Mainnet. | |
| Drengr sharminsirajudeen/drengr-community Eyes and hands for AI agents on Android and iOS devices. | |
| The Agora shashwat-kumar/agora Read and join AI-agent discussion threads on readsigil.com; replies become moderated GitHub issues. | |
| io.github.shashwatgtm/gtm-alpha-consultant shashwatgtm/gtm-alpha-secure GTM Alpha: go to market consultation (EPIC) by Helix GTM Consulting | |
| io.github.shashwatgtm/gtm-alpha-mcp-server shashwatgtm/gtm-expert-schema Professional GTM consultation MCP server with EPIC framework | |
| Banjo shatch/banjo Self-hosted AI assistant that places real phone calls for you: bookings, reservations, errands. | |
| Hollerdex: Website Contact Finder (Emails, Phones & Socials) shawmena-dotcom/product-factory Hollerdex: a domain's public emails, phones and social profiles as one ranked contact card. | |
| io.github.shawn1905/generation-ship shawn1905/generation-ship Generation Ship MCP — multi-AI future world. Read blank cells, read canon, submit artifacts. | |
| io.github.Shawn5cents/agentskin shawn5cents/agentskin The Semantic Layer for AI Agents. Prunes noisy API data by 70%+ for token-efficient reasoning. | |
| Forkmate shawnazar/forkmate-mcp Free AI calorie & macro tracker: tell your AI what you ate and it logs it to your private food diary | |
| io.github.shawndei/glimind shawndei/mcpinfrastructure Live reliability for AI agent tools: is it working right now, and how do I call it correctly? | |
| io.github.shawnwollenberg/walletlens shawnwollenberg/web3_portfolio EVM wallet reports and Robinhood Stock Token intelligence paid with USDC over x402. | |
| RFC lookup shbernal/rfc-ai-tooling 40x fewer tokens while reading the RFC corpus and flag obsoleted specs. | |
| Casona Hoteles Boutique — Live Hotel Rates sheikrojasarce-art/casona-digital-operations Live room rates and direct booking links for two boutique hotels in Cartagena, Colombia. | |
| com.quantstark/quantstark shekhawat2407/quant_framework Quantitative equity toolkit: factor data, backtests, risk model, attribution, optimizer. | |
| io.github.SheldonZhuang/spacesentinel-mcp sheldonzhuang/spacesentinel Conversational Windows disk cleanup (whitelist-only) + device cleanup guides in 7 languages. | |
| io.github.SheldonZhuang/stock-sentinel sheldonzhuang/stocksentinel US stock attack/defense macro signals: 4-dimension framework, 26-year backtested. Research only. | |
| Sinter shellfu/sinter Persistent, evidence-backed code graph for coding agents. | |
| io.github.shemshallah/qtcl-mcp-server shemshallah/qtcl-mcp-server Agent-native post-quantum blockchain. 11 tools: send, balance, quantum oracle metrics. Flat fee. | |
| Horizon Insights MCP shentao12022-cmyk/horizon-insights-mcp Market data, financial statements, valuation, research, and news for investment workflows. | |
| io.github.shephouse-actors/shephouse-yt-mcp shephouse-actors/shephouse-yt-mcp YouTube transcripts for agents on cloud servers, via an Apify Actor. By ShepHouse (AI-operated). | |
| Sherweb Platform MCP Server sherweb/platform-mcp Sherweb Platform MCP server to manage subscriptions and orders. Use OpenID Connect to authenticate. | |
| MCP fork of Google Workspace CLI shigechika/gws-mcp MCP fork of Google Workspace CLI (Gmail, Drive, Calendar, and more) | |
| MCP Stdio shigechika/mcp-stdio Stdio-to-HTTP gateway — connects MCP clients to remote HTTP MCP servers | |
| TaskLite shimon-ks/tasklite-mcp tasklite.net: hosted backend, REST API and admin for apps built by AI agents | |
| io.github.shin-bot-litellm/litellm-mcp shin-bot-litellm/litellm-agent-mcp Give AI agents access to 100+ LLMs. Call any model, compare outputs. | |
| Godot MCP shin2344234/godot-mcp Edit Godot 4 scenes, nodes and scripts; run, test and debug games live in the editor or headless. | |
| Shinjuku Shield shinjukustaition/shinjuku-shield Private x402 payments on Solana: shield, pay, and unshield USDC under caps you set. | |
| io.github.ship24-official/ship24-tracking ship24-official/ship24-tracking-mcp Track any parcel by tracking number — real-time status, event history, and carrier detection. | |
| ai.shipeasy/mcp shipeasy-ai/shipeasy Feature flags, A/B experiments, kill switches, dynamic config & i18n — Shipeasy MCP server. | |
| Shipfound shipfound/shipfound Growth engineer for your coding agent: site fixes, content PRs, indexing and AI search tracking. | |
| Conqueror shipper-dot-now/conqueror-skills Turns SEO insight into page changes: keyword research, SERP and rank data, rewrites you approve. | |
| Shipshape Data shipshapedata/agent-tools Services, case studies, 169 data and AI guides, and AI readiness scoring. Read-only, keyless. | |
| Shipvo shipvo/shipvo Open a React Native app in a simulated phone: read the screen, tap, type, set device state. | |
| Oh My Share shisongsong/oh-my-share Publish HTML/code from your agent to openanthropic.com and get a shareable link. | |
| DevOps Agent shittuay/devops-agent Manage AWS, Azure, GCP, Kubernetes, CI/CD, Docker, Terraform and more. 704 tools. | |
| app.tinkrr/intelligence shivaltailor/tinkrr Bitcoin and YouTube video intelligence for AI agents. Pay-per-call via x402 USDC on Base. | |
| Seminara shivamselam/seminara-agentic-suite Digital Teammate (Aura) hosting live interactive presentations, demos, and audience Q&A 24/7. | |
| Qampi shivasingh9927/linkedin-camp LinkedIn outreach from your agent: find prospects, add leads, run campaigns, read results. | |
| Sutra shivnathtathe/sutra-mcp-integrations Private, portable memory and reusable skills for AI agents. | |
| io.github.shiyue1250/nuttle shiyue1250/nuttle Query the posts, comment trees and videos you've browsed, saved locally by the Nuttle app. | |
| io.github.shizl918/opneclaw shizl918/opneclaw AI Agent task ecosystem platform with marketplace and community | |
| Mi Fitness Data Bridge shkyyy18/mi-fitness-data-bridge Local-first bridge: export your own Mi Fitness (Xiaomi) health data to SQLite/JSON/CSV and MCP. | |
| Basis Protocol shlok-lgtm/basis-mcp Stablecoin risk scores, wallet risk profiles, and transaction risk assessment. | |
| Shlok Bam's portfolio shlokbam/portfolio Ask about Shlok Bam, AI engineer: projects, experience, skills, patents. Live, read-only. |
48,851–48,900 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.