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 |
|---|---|
| WinCtl sitharaj88/winctl Windows desktop control for AI agents: screen, UI Automation, input, processes, files, shell. | |
| Sippion sitten-tokyo/sippion Local read-only repository context retrieval for AI coding agents. | |
| RoutineKit sjh9714/routinekit Capture tool workflows, save typed tools, and replay with human approval. Includes an MCP Apps UI. | |
| io.github.sjk4425/ncloud-gov sjk4425/ncloud-gov-mcp-server DEPRECATED: merged into ncloud-mcp-server (use NCLOUD_ZONE=gov). Ncloud Gov zone MCP server. | |
| io.github.sjk4425/ncloud sjk4425/ncloud-mcp-server MCP server for Naver Cloud Platform (Ncloud) — Public, Government and Financial zones | |
| Reversecore MCP sjkim1127/reversecore_mcp Security-first MCP server for reverse engineering, malware analysis, forensics, and SAST. | |
| io.github.SK-DEV-AI/codesearch sk-dev-ai/codesearch Code, package, docs, paper and vulnerability search. 17 tools, keyless lanes. | |
| io.github.SK-DEV-AI/websearch sk-dev-ai/websearch Multi-engine web search, fetch, browser control. 11 tools, keyless lanes. | |
| Norwegian Company Data skaidigital/brreg-mcp Norwegian company search, accounts, roles, groups and websites from Brønnøysund, remote MCP. | |
| LLM Pricing skakumanu/llm-pricing-mcp-server Real-time, drift-verified LLM pricing across 31 providers with cost+quality model routing. | |
| TradingCalc MCP: Options, Forex, Risk Stats, Prediction Markets, On-Chain & Crypto Futures skalinin909/tradingcalc-mcp Deterministic options, forex, risk, on-chain & futures math. Not AI estimates. Tools: tradingcalc.io | |
| Sellat skanthemore/sellat-mcp Proof of existence for files from any MCP client: hashed locally, anchored on Polygon and Bitcoin. | |
| call4me skeptrunedev/call4me MCP server for making phone calls: your agent books, cancels, asks and waits on hold for you. | |
| Stipple - Government Tenders and Grants sketchjar/stipple-mcp Find open Australian and NZ tenders and grants, match them to a company, and see who holds the work. | |
| skforecast-ai skforecast/skforecast-ai Forecast time series in CSV files: deterministic skforecast workflows and the script that ran. | |
| email-tool skhan61/email-tool IMAP/SMTP email for AI assistants: read, search, draft and send, with CMMC-grade safeguards. | |
| com.halffee/coinrebate skheman2026-sketch/coinrebate-mcp-server Compliance-filtered crypto exchange fee comparison and rebate-link routing for AI agents. | |
| DialMCP skillfulagents/dialmcp-connector Let AI agents place real phone calls from your verified number, with transcripts and recordings. | |
| SkillGild skillgild/skillgild Search and run hosted AI agent skills for Claude Code, Codex, Cursor and Gemini CLI. | |
| com.skillmd/skillmd skillmds/skillmd Search, fetch, lint, and install Agent Skills (SKILL.md) from the SkillMD registry. | |
| io.github.Skillproofdev/skillproof skillproofdev/skillproof-mcp Check whether a Claude Code skill was tested and whether it works before installing it. | |
| Federal Compass MCP skivuha/federal-compass-mcp AI compass from private sector to federal career — USAJobs search, salary, KSA | |
| Sklarstad Storefront sklarstad/sklarstad-storefront-mcp Sklarstad products for AI agents: FirstTake, free open-source video production, shoot to master. | |
| Skopia skopia-mcp/skopia-mcp Floor plans in real mm: doors, windows, fixtures; validate, render, elevations, sections, storeys. | |
| Stock Trends Market Intelligence skotlander/stocktrends-mcp-server Equity trend, relative-strength, expected-return, market-context, and research resources for agents. | |
| com.korture/hiring skprasad-korture/korture-mcp Who is wired for this role, in four plain facets, and what one change would widen it. | |
| Skryvo skryvo/agent Write and schedule social posts in your brand's voice on LinkedIn, X, Bluesky, Mastodon and more | |
| Smartipedia sksareen/smartipedia-mcp Read, search and edit Smartipedia, an open AI-native encyclopedia. No API key, no signup. | |
| Anode background Windows desktop skulitom/anode Background Windows desktop for AI agents: native GUI automation, screenshots and app testing. | |
| Cutbolt video editing engine skulitom/cutbolt Local video editing engine for agents: exact timelines, saved sessions, rendering and FFmpeg export. | |
| Inkbolt vector and raster editor skulitom/inkbolt Local vector and raster editing engine for agents: layered documents, saved sessions and exports. | |
| Maskbolt Segment Anything on CPU skulitom/maskbolt Segment Anything on CPU for agents: cut out objects, find every object, export masks and outlines. | |
| Nestbolt sheet nesting skulitom/nestbolt Local fixed-sheet nesting for laser and CNC cutting: SVG/DXF import, nest, validate, export. | |
| Pixelbolt pixel art toolkit skulitom/pixelbolt Pixel art and sprite animation for agents: JSON recipes to PNG, APNG, GIF and sprite sheets. | |
| io.github.skunkobi/leclerc-drive skunkobi/mcp-leclerc-drive MCP server for E.Leclerc Drive — search products, manage cart, and order groceries from Claude | |
| GetExperience skurakov/getexperience-mcp Search and book tours and travel experiences in 40+ countries via MCP. | |
| WpfPilot MCP skuzadev/wpfpilot-mcp Automate Windows WPF apps from AI agents with semantic UIA selectors and FlaUI test generation. | |
| SKV Network skv-neteork/skv.network Memory + answer checks for AI agents: recall across chats, draft→check→seal, fewer hallucinations. | |
| SkyAccess sky-access/skyaccess-mcp Search 5,000+ live empty leg flights, get charter estimates and booking links. Free, no API key. | |
| Skycloak sky-cloak/skycloak-mcp Managed Keycloak from any MCP client: clusters, realms, apps, SSO, users, domains, audit events. | |
| com.adsbiq/adsbiq sky-power-services/adsbiq-mcp-server Read-only access to live ADSBiq aircraft and network state, with community contribution metadata. | |
| LockIn sky-walkerx/lockin A notebook your coding agents write to: notes that track the code's commit, and handoffs. | |
| io.github.skylarng89/cogmemory-mcp skylarng89/cogmemory-mcp CogMemory MCP Server — Unified context subsystems for AI coding agents | |
| M3 Memory skynetcmd/m3-memory Local-first, cloud-friendly memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search. | |
| ClawPage skypher/clawpage-mcp Extract and structure any web page into clean JSON. Free tier: 10/day. | |
| io.github.skypier-jp-works/mcp-jp-calendar skypier-jp-works/mcp-jp-calendar MCP server for Japanese business days, holidays, and fiscal-period calculations. | |
| io.github.skypier-jp-works/mcp-jp-corporate-id skypier-jp-works/mcp-jp-corporate-id Validates and normalizes Japanese corporate numbers and invoice registration numbers (format only). | |
| io.github.skypier-jp-works/mcp-jp-paid-leave skypier-jp-works/mcp-jp-paid-leave MCP server for Japanese statutory annual paid leave (nenkyu) calculations. | |
| LAT - Living Apart Together skyradi/lat Open, unverified census of what AI agents can do; connect and self-report. | |
| Skysay skysay-ai/skysay-mcp Skysay voice agents, phone numbers, calls, SMS and campaigns over MCP. 100+ countries covered. |
17,001–17,050 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.