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 |
|---|---|
| com.deerdawn/deerdawn hissingspider/deerdawn-mcp AI session memory: the brief your AI reads before every session so no session starts cold. | |
| HitPay MCP Server hit-pay/claude-code-plugin Official HitPay MCP: sales, payouts, balances; create payment links and invoices. OAuth; no refunds. | |
| ClawLink hith3sh/clawlink MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth. | |
| Hit The Road Rentals hittheroad-git/hittheroad-mcp Search campervans and motorhomes worldwide. 300+ rental companies. AU, NZ, US, CA, UK and more. | |
| io.github.omiiyamu/hiveclaw hiveclaw-ai/hiveclaw Connect AI assistants to HiveClaw — manage projects, talk to AI agents, and more. | |
| Dibs (Hive Commons) hivecommons/dibs Submit ideas to hive-managed open source repos and get credited when agents ship them. | |
| Knolo hiveforensics-ai/knolo-core Verified, local-first retrieval over pinned Knolo Knowledge Images. | |
| io.github.hiveforge-sh/hivemind hiveforge-sh/hivemind MCP server for Obsidian vaults - AI tools with consistent canonical context. Local-first. | |
| HiveLearn hivelearn/community-hub Read and author HiveLearn courses, events, quizzes, certificates, resources, leaderboards, tracks. | |
| STAS Running Coach for Claude hivrich/stas.run Connect Claude to your Intervals.icu watch data for fitness, workout review, and plan writing. | |
| 한국일보 뉴스 (Hankookilbo) hkilbo/hankookilbo-mcp Hankookilbo (Korean daily) news metadata: titles, dates, sections, bylines, links, and excerpts. | |
| HList AI Tools hlist0001/hlist Search 386+ AI tools with China-access data, live GitHub stats, 4-language metadata. No key needed | |
| io.github.hlix-ai/hlix hlix-ai/hlix Work with Hlix projects, tasks, cycles, comments, and verified reviews in one workspace. | |
| io.github.Hlobo-dev/tengu-firm hlobo-dev/tengu-mcp One MCP key: prices, fundamentals, SEC filings, insider/13F/congressional trades. 336 tools. | |
| MintPage hlsitechio/mintpage Publish Markdown or HTML as a live, shareable web page in one tool call. Guest mode needs no key. | |
| io.github.HMAKT99/akf hmakt99/akf Trust metadata for AI agents — check files before building on them, stamp verified work. | |
| ClawTank hmakt99/clawtank Let agents see and drive a Mac: screenshots, clicks, typing, apps and virtual displays. | |
| io.github.HMAKT99/scbee-mcp hmakt99/scbee Score repos for launch and agent readiness, find verified agents, read collaborations. Read-only. | |
| PlaywrightGen hmamut39/playwrightgen Approved test intent, reviewed Playwright automation and run evidence, inside your editor. | |
| io.github.hmamut39/tewip hmamut39/tewip Proves software work: triages failing tests, checks whether a test can fail, and reads migrations. | |
| HeyYumi hmp-dev/heyyumi-mcp Find & book real Korean restaurants in any language, in-chat. Seoul, Busan, Jeju & 6 more regions. | |
| DONVI108 Free Research Beta ho11-bit/donvi108-agent-skills Free scholarly paper and DOI discovery via Crossref. Self-service registration; no invitation. | |
| Mnema — AI Memory Layer hoanglt1223/secondbrain Personal knowledge graph as an AI memory layer over MCP - read, save, and link your memories. | |
| CoachSync hobodave/coachsync-mcp Barbell strength training tools for AI assistants. Warmup, plate loading, and LP. | |
| Tafla hoddmachine/tafla-plugin Calculation walkthroughs for AI tools. Hand in a calculation, get a link that shows the working. | |
| com.hodlodds/hodlodds-mcp hodlodds/hodlodds-sdk Local crash-odds tools with free market discovery and bounded x402 USDC payments on Solana or Base. | |
| HODLXXI Read-Only hodlxxi/universal-bitcoin-identity-layer Public read-only MCP server for HODLXXI agent identity, trust, receipts, and verification. | |
| 3D Print Log hoffmanengineering/3d-print-log-api Log and query 3D prints, printers, filament, and projects on 3dprintlog.com, and search its docs. | |
| webcapture hogan-yan/webcapture Hosted MCP server: render any URL to print-stable PDF, PNG, WebP or Markdown | |
| PennyPilot holco-apps/pennypilot AI copilot for French accounting firms on Pennylane. Monthly close memo in 8s, full general ledger. | |
| PennyPilot MCP holco-apps/pennypilot-mcp Open-core, local, read-only MCP server for Pennylane Company API v2. Auditable READ_ONLY_GUARD. | |
| Holdings holdings-io/workspace Let your AI send invoices and take payment — card or ACH. Free. | |
| RCLL holetron-lab/fleet-memory Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path. | |
| Holiday Forever holiday-forever/holiday-forever-2 Interactive photo gallery widget for a single Airbnb listing with price, rating, and link. | |
| io.github.holiday-forever/holiday-photo-plus holiday-forever/holiday-photo-plus Show holiday photos from Vercel Blob inline in Claude chats. | |
| io.github.holiday-forever/holiday-photo-plus-2 holiday-forever/holiday-photo-plus-2 Holiday photo MCP server: list and fetch personal holiday photos inline in Claude chat. | |
| io.github.holiday-forever/holidayforever holiday-forever/holidayforeverphoto Searchable directory of Airbnb listings — discover properties and retrieve direct Airbnb links. | |
| io.github.holistis/yad-agent-mcp holistis/al-yad MCP wrapper for Yad, a local browser-automation companion, for coding agents. | |
| io.github.holistis/capacity-attest holistis/tokenizen Signed delivery claims for x402 capacity trades: GPU-hours, storage, API credits, bandwidth. | |
| io.github.holistis/cra-check holistis/tokenizen Free read-only check of a public GitHub repo for eight security signals related to the EU CRA. | |
| ai.smithery/hollaugo-financial-research-mcp-server hollaugo/tutorials Analyze stocks with summaries, price targets, and analyst recommendations. Track SEC filings, divi… | |
| Hologram Model Hub hologram-technologies/hologram-live Find open models and get download links with the SHA-256 each file must have. | |
| TAP holonym-foundation/tap-oss Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval. | |
| Bloom Study Guides holosoul-team/bloom-study-guide-mcp Turn AI learning chats into illustrated study guides, and search guides already on Bloom. | |
| Protocol Career holox76000/protocol-career-mcp Practice consulting drills and prepare for case interviews at the top US consulting firms. | |
| Teetrack holymarcell/teetrack-mcp Privacy-first time tracking for freelancers. EU-hosted, with an MCP server for AI assistants. | |
| Ganty MCP homareyoshizaki/ganty-mcp Gantt chart SaaS with server-side critical path and dependency-aware shift-impact tools, plus CRUD. | |
| nintact homareyoshizaki/nintact-mcp Contact forms that actually arrive. No SPF/DKIM, no SMTP. AI sorts them and drafts the reply. | |
| CompletionKit homemade-software-inc/completion-kit Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge. | |
| io.github.HomenShum/nodebench homenshum/nodebench-ai 260 MCP tools across 49 domains. AI Flywheel, quality gates, research, web scraping. |
23,801–23,850 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.