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.lazymac2x/mcpwatch lazymac2x/mcpwatch Audit MCP servers from inside Claude Code. 10 OWASP checks, A-F grade, live leaderboard. | |
| io.github.LaZZy0v0/tijori-finance lazzy0v0/tijori-finance-mcp Indian equity research MCP — 5,000+ NSE/BSE stocks, financials, KPIs, and concall transcripts. | |
| whitemagic lbailey94/whitemagic Provides local-first durable memory and session continuity for AI coding agents over MCP, enabling context across restarts without cloud services or telemetry. | |
| FailTrace lbarimi/failtrace Debugging experiments for coding agents: reproduce failures and verify fixes with test evidence. | |
| Agent Email List — Free SMTP Relay for AI Agents lbesecker195/ai-agent-email-list Free transactional email + SMTP relay. Agents self-signup, no API key needed to start. | |
| Development Indicators MCP lbruce-wq/development-data-mcp Open-source MCP for official development indicators with provenance and citations. | |
| International Classifications MCP lbruce-wq/international-classifications-mcp Deterministic MCP for statistical classifications and survey codelists with provenance. | |
| io.github.lchampz/heimdall lchampz/mcp-heimdall 🛡️ MCP Heimdall - Advanced Environment Architect & Diagnostic Tool. | |
| io.github.lchinglen/time-mcp-server lchinglen/time-mcp-server MCP server for timezone conversions and time queries with support for IANA timezones | |
| Designesy le-vai/designesy-org Design quality gate for AI-generated UI: score any URL on 45 deterministic checks, A–F grade. | |
| APICK Vision lead788/apick-mcp Image/video analysis: NSFW detection, object detection, thumbnails | |
| APICK Subagent lead788/apick-subagent Document inventory, extraction, summaries and comparison with source quotes and usage billing. | |
| VIDIA lead788/vidia-mcp VIDIA AI video production: get quotes, start videos, track progress and download results | |
| Leadbase | AI B2B Lead Generation leadbaseio/leadbase-plugin AI B2B lead generation: find matching companies and decision-makers. Start with 200 free credits. | |
| korean-data-mcp leadbrain/korean-data-mcp Real-time Korean web data for AI assistants — Naver Place reviews, Melon charts, Daangn/Bunjang marketplace, Naver News, Musinsa fashion rankings. 7 tools powered by Apify actors. | |
| LeadDelta MCP Server leaddelta/ld-mcp-server MCP server for LeadDelta — manage LinkedIn connections and CRM data via AI assistants. | |
| io.github.leadpipe-com/leadpipe leadpipe-com/mcp Official MCP server for Leadpipe intent and data APIs. | |
| io.github.leakferrethq/leakferret leakferrethq/leakferret Context-aware secret scanner: lets an AI agent scan, verify, and rewrite secrets before committing. | |
| MCP for Adobe Premiere Pro leancoderkavy/premiere-pro-mcp Local-first MCP for supported Adobe Premiere Pro workflows; start with a read-only connection check. | |
| Tradewink leancoderkavy/tradewink-mcp MCP for Tradewink trading signals and watchlists. Not financial advice. | |
| 3D New Era AI leandrodaf/3d-new-era-ai Design homes with your AI: floor plans, furniture, joinery, lighting and photos, live. | |
| ai.smithery/leandrogavidia-vechain-mcp-server leandrogavidia/vechain-mcp-server Search VeChain documentation, query on-chain data, and fetch fee suggestions with direct links to… | |
| io.github.LeandroPG19/memory-industry leandropg19/memorys MemoryIndustry persistent memory MCP server: BM25+MMR retrieval and audit. | |
| LedgerCrossing for QuickBooks Desktop ledgercrossing/quickbooks-desktop-mcp QuickBooks Desktop MCP server: all 240 qbXML operations for Claude, ChatGPT, Cursor and VS Code | |
| iPhone Use leeguooooo/iphone-use Drive a real iPhone from a Mac: read the screen as text, tap, type, scroll, replay saved flows. | |
| Korea MCP leegwangwoon/korea-mcp Get around Korea: subway routes in English, fares, public holidays and guides. No API key. | |
| Bing Search MCP Server leehanchung/bing-search-mcp A Model Context Protocol server that integrates with Microsoft Bing Search API, allowing AI assistants to perform web, news, and image searches. | |
| Personae leek-emperor/personae Control specific, already-open account-isolated Personae browser identities with MCP. | |
| networklytics-mcp leekangbum/networklytics-mcp YouTube comment social network analysis (SNA): influencer centrality ranking, community detection (Louvain algorithm), sentiment analysis, and AI-generated insights via public JSON API. | |
| claude-session-continuity-mcp leesgit/passbaton Zero-config session continuity for Claude Code. Automatically captures and restores project context across sessions using Claude Hooks. | |
| Proton Mail (Bridge) legalaspro/proton-mail-mcp Unofficial MCP server for Proton Mail Bridge: search and read mail, write drafts, guarded cleanup. | |
| io.github.PedramMadani/legalithm-mcp-server legalithm-org/legalithm EU AI Act risk classification, obligations and Article 50 disclosures. Offline, no API key. | |
| Legalize legalize-dev/mcp Official MCP connector for Legalize: read and search its whole open corpus, at any point in time. | |
| LegalOne Entreprises legalone-fr/entreprises French company data from public registers (Sirene, RNE, BODACC) and French legal notices. | |
| io.github.legann/repovine legann/repovine Checkout-local repository context graph over MCP; `npx repovine setup` wires skills, agents, hooks. | |
| ai.smithery/Leghis-smart-thinking leghis/smart-thinking Find relevant Smart‑Thinking memories fast. Fetch full entries by ID to get complete context. Spee… | |
| LEGION Verify: MCP tool-list history legion33shadow/legion-mcp Check if an MCP server changed its tools: signed history, per-server coverage, offline proofs. | |
| MACKORN Hydraulic Cone Crusher Selection leifdai/mackorn-hydraulic-cone-crusher MACKORN hydraulic cone crusher selection and crushing-plant design. 21 tools, callable over HTTP. | |
| io.github.lemahq/lema-mcp lemahq/lema-mcp Cited 'why was this decided?' answers for your repo and for React, Kubernetes, and Rust. | |
| io.github.leMaur/livewire-flux-mcp lemaur/livewire-flux-mcp Flux UI component and layout docs for AI coding agents. Live from fluxui.dev, Pro-tier aware. | |
| io.github.LembaGang/headless-oracle-mcp lembagang/headless-oracle-v5 Ed25519-signed market-state receipts for 28 exchanges. Fail-closed pre-trade gate. | |
| io.github.lemonaide152/meld lemonaide152/meld Agent bridge. Host-readable; anyone with the link can read and reply. Not for secrets. | |
| Sejm RP leniwyposel/sejm-mcp Sejm RP i akty prawne (ELI): posłowie, głosowania, interpelacje, ustawy. Lokalnie, tylko odczyt. | |
| io.github.lennix1337/genexus lennix1337/genexus18mcp Read, edit, and analyze GeneXus 18 KB objects from Claude, Cursor, and AI agents. | |
| io.github.lennney/mcp-slim-guard lennney/mcp-slim-guard 76% fewer MCP tokens in our standard benchmark. Same upstream call. Exact recovery. | |
| Lenz Fact-Check lenzhq/lenz-mcp Check the factual claims in a draft or an answer: a quick verdict, or a deep check with sources. | |
| AON leo007-htun/aon Self-hosted, uncensored AI agent: ask it tasks, search its long-term memory and your documents. | |
| Horizon Fidelity Monitor leocelis/horizon Tracks conversation health in real time — drift, desync, and causal collapse — for any AI agent. | |
| Intent-Verified Development (IVD) leocelis/ivd 33 tools that make AI write, implement, and verify intent against explicit, testable constraints. | |
| io.github.leojg/rihla leojg/rihla Flexible multi-leg, multi-airport flight search - cheapest valid combination across an itinerary. |
10,851–10,900 of 115,409
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.