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 |
|---|---|
| OpenOak theopensorcerer/open-oak Secure AI access to OpenOak tasks, notes, and Kanban boards. | |
| HumanOps thepianistdirector/real-auto-code MCP server for AI agents to dispatch real-world tasks to verified human operators | |
| ru.activatedai/activated-ai thepisarev/activated-ai Советники по бизнес-методикам: подбор эксперта-методики под задачу и консультация. | |
| io.github.theprodsde/agent-memory theprodsde/agent-memory-sdk Persistent agent memory with a decision layer: replay, restore, verify, or none — explainable. | |
| vaultit therealdataboss/vaultit Zero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM. | |
| contextkeeper therealdataboss/workbench Zero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM. | |
| mythOS.vision therealityengineer/mythos A living memory and world-building layer for your AI: cards, worlds, personas and agent dispatch. | |
| The Clubhouse therealmrfunguy/clubhouse-agent-protocol Play chess, pool and poker for real money against AI agents and humans on Base. Pays via x402. | |
| io.github.therealtimex/browser-use therealtimex/browser-use AI browser automation - navigate, click, type, extract content, and run autonomous web tasks | |
| io.github.therealtimex/un-datacommons-mcp therealtimex/un-datacommons-mcp MCP server to query Data Commons indicators and observations (base or custom). | |
| FEA (finite element analysis) therobomaster123/mcp-fea Real FEA on CAD parts: validated setups, stress, safety factor, natural frequencies | |
| Cursio theroer/cursio Control trusted computers, apps, files, and developer tools across your Cursio mesh. | |
| TheRundown Documentation MCP therundown/documentation-mcp Official TheRundown API documentation search. No live data or authenticated Product API calls. | |
| Kaito Query Service thesandemon/sand-gallery AI LLM with Gemini, MiniMax, Replicate, OpenRouter. Vision, search, code review. USDC on Base. | |
| FrameOS thesatvik/frameos-plugins Turn long videos into captioned, reframed short clips, thumbnails, and social posts. | |
| SocialSpool thesethrose/socialspool Create, schedule, and publish social posts through the hosted SocialSpool MCP connector. | |
| GetQueryly — AI Data Analyst thesinbin12-jpg/getqueryly-mcp Upload spreadsheets, get plain-English analysis with real computed charts and quality scores. | |
| io.github.thesuitabs/sealedmail thesuitabs/sealedmail Send and receive on-chain private messages via SealedMail on Sui. No browser wallet needed. | |
| Mirobody thetahealth/mirobody Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key. | |
| Ontario Protocol thetechdevpro/ontario-protocol Find live x402 APIs for any task (0.005 USDC, no match no charge); Base balance, tx and gas reads. | |
| Ads Editor: Meta Ads and Google Ads theusmyep/ads-editor-mcp Meta Ads and Google Ads MCP server: 250+ tools for Claude, ChatGPT, Cursor and Codex. | |
| MarkLayer thevrus/marklayer Work visual annotations on a live webpage: watch, acknowledge, resolve, reply, or leave your own. | |
| hotedit thewhey-brian/hotedit Open HTML reports in the browser and edit them live while the person watches, or by hand. | |
| 1c-rest-mcp theyahia/1c-rest-mcp MCP server for 1C Enterprise — ERP catalogs, documents via REST API (Russia) | |
| Theyond theyond/mcp Live jobs from employer career pages. Read-only. Hit Apply on theyond.com. You land on the employer. | |
| Base MCP Resolver thgun2yerhed/agent-services-v2 Free onboarding tool providing authentic live transaction analysis on Base mainnet. | |
| Maker Machines Atlas thiazzz/maker-machines Machine research, calculators and buying links; affiliate links may earn commission. | |
| Smart Glasses Atlas thiazzz/smart-glasses-atlas Smart glasses research and regional buying links; affiliate links may earn commission. | |
| Smart Rings Atlas thiazzz/smart-rings-atlas Smart ring research and regional buying links; affiliate links may earn commission. | |
| com.thingctx/thingctx thingctx/thingctx Drive devices and APIs from their W3C Thing Description. You gate every operation. | |
| io.elaan/mcp thingsidoforlove/elaan-js Create Elaan notification types, templates and brands, trigger sends, and debug delivery. | |
| Remote Browser MCP Server from MCPBundles thinkchainai/mcp Automate cloud Chrome—navigate, click, type, screenshot, run code, record screen video | |
| Fiveable for AP Students thinkfiveable/fiveable-mcp AP study content, practice, FRQ feedback, progress, plans, and student tools for AI apps. | |
| VisibilityAI thinksuitesolution-coder/visibilityai Search and compare businesses worldwide by category and city; AI-visibility data and lead capture. | |
| io.github.thirdtrail/thirdtrail thirdtrail/thirdtrail-python Elevation-corrected sun, moon, twilight, solar and tide data for any point on Earth | |
| Second Eyes Agent Workflow Services this-is-hellgate/second-eyes-ai Workflow diagnostics, capability routing, and x402 settlement for MCP-compatible agents. | |
| Cycle Tracker thisisbankole/starling-bank-bikes-mancheter Live UK bike-share availability: nearby bikes and stations, popular stations, 90-day history. | |
| Bizcraw thnthnh7/bd-tool Web scraping and AI sales workspace with scoped CRM, scraping, knowledge and sales workflow tools. | |
| all2md thomas-villani/all2md Read, convert, search, diff and outline PDF, Word, PowerPoint, HTML and 40+ formats as Markdown. | |
| VibeDeploy thomasbillen-netizen/vibedeploy-mcp Deploy AI-built sites and apps to EU hosting from your AI agent. OAuth sign-in, 14-day free trial. | |
| Returnolio thomasbodri/returnolio-mcp-server Read-only stock research: company scores, the Monthly Top 10, the screener and your own portfolio. | |
| FICTURN — Short Fiction Inside ChatGPT thomasjudes-del/ficturn Short, finished fiction to discover by mood, genre or reading time inside ChatGPT. | |
| Lexiara thomasmackie/legal-landscape Provenance-backed EU and UK legislation for AI agents, addressable to the individual provision. | |
| io.github.ThomasViennet/referencime thomasviennet/mcp-referencime Identifiez les meilleurs spots netlinking selon leur performance Google réelle. | |
| Pilot5 thomaswainstein/pilot5-mcp Five AI models debate your decision blind, then give one recommendation and the strongest objection. | |
| Smart Post Studio thorarinsson22/smart-post-studio-mcp Read, draft and schedule social media posts to 8 platforms. No post-now tool by design. | |
| THORChain Swap thorchain/swap.thorchain Read-only THORChain swap quotes, liquidity pools, and network status. | |
| CSharp.Refactor thorium/csharp-refactor Offline analyzers that find and fix intent-hiding, slow or noisy C#, including agent-written code. | |
| FSharp.Refactor thorium/fsharp-refactor Offline analyzers that find and fix intent-hiding, slow or noisy F#, including agent-written code. | |
| Criora climate risk thothbot/criora-mcp Climate and disaster risk for any place: warnings, floods, heat, storms, quakes, countries, map |
49,701–49,750 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.