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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| io.github.SAP/mdk-mcp-server sap/mdk-mcp-server Model Context Protocol (MCP) server for AI-assisted development of MDK applications. | |
| io.github.sapientsai/dokploy-mcp-server sapientsai/dokploy-mcp-server Dokploy MCP server: manage apps, Docker Compose, databases, domains, backups, and servers. | |
| io.github.sapientsai/power-automate-mcp-server sapientsai/power-automate-mcp-server Inspect, operate, and author Microsoft Power Automate cloud flows from an agent context. | |
| Feedback Synthesis MCP sapph1re/feedback-synthesis-mcp Synthesize GitHub Issues, HN and App Store reviews into ranked pain clusters. Pay-per-call x402. | |
| Oraclebone sapuyou45-bit/oraclebone Audited tarot, I Ching, Xiao Liu Ren, Bazi (Four Pillars). Model never invents results. | |
| io.github.sara-star-quant/presence-mcp sara-star-quant/presence-mcp Read-only MCP access to presence: living project model and outcome telemetry. | |
| io.github.sarahpark/google-search-console sarahpark/google-search-console-mcp Google Search Console MCP server — search analytics, URL inspection, and sitemaps | |
| io.github.sarath-451/tomcat sarath-451/tomcat-mcp Local MCP server for AI-assisted Apache Tomcat management and diagnostics | |
| io.github.SardorbekR/appstore-connect sardorbekr/appstore-connect-mcp MCP server for Apple's App Store Connect API. Manage apps, TestFlight, and more. | |
| GitHub Issue MCP sarim-aliii/github-issue-mcp AI-powered MCP server for generating GitHub issues and detecting semantic duplicates. | |
| io.github.sarisen/ascope-mcp sarisen/ascope-mcp Daily App Store keyword ranks, popularity and difficulty, from Ascope for Mac | |
| AAJ Marketing Engines sarojkjha/aaj-marketing-skills Deterministic marketing math for AI agents: LTV:CAC, pipeline coverage, A/B tests, pricing. | |
| MCP Event Intelligence sarooo17/event-intelligence MCP-native CEP for durable agents: event-time patterns, semantic predicates, derived events. | |
| Agent Handoff MCP sarutobisasuke8/agent-handoff-mcp Bounded, auditable handoffs between AI agents through a local MCP server. | |
| Aseprite Agent MCP sarutobisasuke8/aseprite-agent-mcp Create and verify pixel-art assets with atomic Aseprite edits and Phaser export. | |
| GIMP Agent MCP sarutobisasuke8/gimp-agent-mcp Edit in GIMP 3 with AI agents: live previews, grouped edits, pixel measurements and recipes. | |
| JobScout MCP sarutobisasuke8/jobscout-mcp Multi-source job discovery, deduplication and AI/Web3 classification for AI agents. | |
| Obsidian GitHub MCP sarutobisasuke8/obsidian-github-mcp A permissioned MCP gateway for agent proposals to a Git-backed Obsidian vault. | |
| io.github.sarveshtalele/personal-finance sarveshtalele/personal-finance-mcp 54 robust financial calculators based on deterministic mathematical principles. | |
| SAS Viya sassoftware/sas-mcp-server Execute SAS code and query Compute, CAS, and model APIs on SAS Viya via OAuth 2.0. | |
| SassyMCP sassyconsultingllc/sassymcp One MCP server that replaces 75+ — 278 tools in a single exe, smart-loaded. | |
| Godot MCP satelliteoflove/godot-mcp Agent-driven Godot playtesting: editor control, input injection, game-time stepping, live state. | |
| DidYouSEO sathish27/didyouseo-mcp SEO audits, Search Console, GA4, keyword and backlink data for Claude, ChatGPT and Cursor. | |
| Data-grounded sprint retro sathvic-kollu/retro-mcp Data-grounded sprint retrospectives from your Jira, GitHub, and Slack activity. | |
| Standup from your activity sathvic-kollu/standup-mcp Generate your daily standup from real GitHub, Jira, Linear, and Slack activity. | |
| io.github.sathvic-kollu/techtenstein-bg sathvic-kollu/techtenstein-bg-mcp AI background removal for images. Modes: auto, product, portrait, car. Transparent PNG. | |
| io.github.sathvic-kollu/techtenstein-linkedin sathvic-kollu/techtenstein-linkedin-mcp Enrich LinkedIn profiles, companies, and prospect searches. For sales, recruiting, B2B. | |
| io.github.sathvic-kollu/techtenstein-pdf sathvic-kollu/techtenstein-pdf-mcp PDF text and table extraction plus metadata. Supports OCR for scanned documents. | |
| io.github.sathvic-kollu/techtenstein-seo sathvic-kollu/techtenstein-seo-mcp On-page SEO audit for any URL. Titles, meta, headings, links, score, and fix recommendations. | |
| Graph-Mem sathvik-1007/graphmem-mcp Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys. | |
| io.github.satoshkin-dev/satoshkin-aml-mcp satoshkin-dev/satoshkin-aml-mcp AML/KYT crypto wallet risk screening (BitOK data) for Claude, ChatGPT and any MCP client. | |
| io.github.saucelabs-sample-test-frameworks/sauce-api-mcp saucelabs/sauce-api-mcp An open-source MCP server that provides LLM access to the Sauce Labs API | |
| 内容路由器 · 素材该做成什么 savantcat/content-router 给素材做 11 维内容画像，推荐跨媒介输出形态（PPT/信息图/短视频/漫画等 6 种）并给出可执行调度提示词 | |
| 中文 AI 可引用性（GEO/AEO）体检 savantcat/mcp-geo-cn 中文站能否被豆包/DeepSeek/文心/Kimi 抓取、读懂、引用：可引用性审计、信源池占位探测、五大指标测量、修复计划、观测时序追踪 | |
| 记忆梦境引擎 · AI 的睡眠系统 savantcat/memory-dream-engine 零 LLM 事实提取 + 三维信号评分 + 艾宾浩斯衰减 + 五阶段梦境流水线与内容发芽检测，纯计算零依赖 | |
| 中国 AI 合规与备案（条文级自查） savantcat/savantcat-ai-compliance-mcp 生成式AI备案、AI生成内容标识、深度合成、算法备案：条文级问答 + 按条号取法规原文 + 应办清单（中文） | |
| AI 客服国标合规知识库 (GB/T 47746—2026) savantcat/savantcat-answers-mcp 中国 AI 客服国标 GB/T 47746—2026 合规知识库：条款级问答 + 全部 61 项达标自查清单（48 应 + 4 宜 + 9 可，含 5 项一票否决），答案标注条款依据。 | |
| io.github.SavantoAI/mcp-server savantoai/mcp-server Manage your Savanto store from your AI: catalog, content, prompts, and analytics, by chat. | |
| io.github.savecharlie/almanac savecharlie/almanac Verified ephemeris & WMM2025 geomagnetic compute: the physical numbers LLMs hallucinate, done right. | |
| io.github.savecharlie/touchstone savecharlie/touchstone Verifiable text/code/measurement tools for agents, each reproducing a named authority. | |
| Savee saveeit/savee-mcp-server Read your Savee saves, boards and home feed, and search its public library. Read-only. | |
| io.github.savhascelik/meta-api-mcp-server savhascelik/meta-api-mcp-server You can connect any API to LLMs. This enables AI to interact directly with APIs | |
| io.github.saviodamato/agentrank-mcp saviodamato/agentrank-mcp Find real, verifiable businesses with provenance and source URLs - for AI agents. | |
| Sayba AI Agent Social Platform saybanet/sayba-platform-mcp-server AI Agent social network with 23 MCP tools for social, tasks, skills, and XC token economy. | |
| Sayba Skill Market saybanet/sayba-skill-mcp-server Discover, invoke, publish, and rate AI Agent skills on Sayba platform | |
| io.github.kcw2034-sayouzone/mcp-opendart-server sayouzone/mcp-opendart-server An MCP server that provides OpenDart API | |
| io.github.kcw2034-sayouzone/sayou-opendart-mcp sayouzone/sayou-opendart-mcp An MCP server that provides OpenDart API | |
| FPL Context sbanthia92/fpl-context-mcp Live Fantasy Premier League data for AI agents: fixtures, players, squads, injuries. No setup. | |
| Second Read sbanthia92/second-read Reviews drafts: fact-checks claims against web sources and builds the strongest counter-case. | |
| whosaid sblattj/whosaid Local speaker-attributed transcription and meeting search for Apple Silicon. Audio stays on the Mac. |
16,451–16,500 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.