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 |
|---|---|
| Telemetry-Intake Provenance & Confinement Service Signed telemetry origin verdicts, intake census, canary drills. Verdict $0.01/event. | |
| Tool-Call Origin Attestation Dispatch-boundary attestation: prove a tool call was issued for its exact arguments. | |
| Tool-Confusability Recovery Loop Recovery loop for agent tool catalogs: measured confusion, ranked fixes, signed recovery receipts. | |
| The agent tool formulary: certified-equivalent substitution Certified-equivalent tool substitution: probe-certified ratings, signed receipts, DAW, prior auth. | |
| Tool-result context-binding verdict Pre-consumption verdict for cached/replayed tool results: BOUND, STALE, CONTEXT-MISMATCHED, UNBOUND. | |
| Tool-result size governor for MCP Per-route output budgets for MCP: windowing, spill artifacts, signed omission receipts. | |
| Trace-store secret census Trace-store secret census of stored agent traces. Verdict $0.01, census $4.99, passes $9.99/$19.99. | |
| Unattended-surface parity probe Pre-run parity probe for scheduled agents: signed PARITY / NO-GO verdict naming the failing gate. | |
| Wall-Event Circumvention Sentinel Sequence sentinel: wall events + channel-switch scoring; HALT, hold, signed receipt. | |
| Widget-storage residue verdict Per-widget x per-host browser-storage residue verdict, hash-only census, verified-clear receipt. | |
| TextMine MCP Search, read, and automate TextMine documents, records, workflows, integrations, and agent tasks. | |
| TextToQuant Backtesting and Quant Research Backtest plain-English trading strategies on real market data: graded results, honesty flags. | |
| com.texttostl/texttostl x402-paid tools: text to 3D-printable STL, web search, and search+read. USDC on Base. | |
| tgboard — Telegram Directory Search 100k+ auto-verified Telegram channels, bots and groups: full-text search and top rankings. | |
| TgPay Merchant API Accept crypto payments via the TgPay Merchant API — invoices, subscriptions, webhooks. | |
| com.thaiapp/bible-app Read-only Bible for AI: search & read scripture in Thai & English, plus a daily verse. | |
| com.thaibankslip/checkslip-mcp Verify Thai bank transfer slips: amount, receiver, date, and duplicate reuse via check_slip. | |
| GYOTAK Fish Market Sashimi-grade flash-frozen fish from Thailand. Catalog, ordering, and on-chain traceability. | |
| Thailand Stay Plan Which legal route lets you stay in Thailand: seven visa routes ranked from your facts, with sources. | |
| Motor Soberano (pay-per-call, x402) Pay-per-call x402 tools: PT-BR→PT-PT rewrite, PT AI-text detector, PT ad check, margin, gpt-oss chat | |
| ThaiProps Thailand Real Estate Search live published Thailand properties and projects from ThaiProps. | |
| the-Automator AutoHotkey Downloads Search Semantic search over 438 AutoHotkey tools, scripts and courses at the-automator.com | |
| The Driscoll Public AI Read-only property facts, indicative availability, authorised booking links and guest-safe support. | |
| THE GRAPH THE GRAPH: file La Liga and Premier League stories to our newsroom. See what others miss. | |
| The-Snip Team knowledge base for snippets, API calls and docs. Agents search and file items; humans review. | |
| The2410 Projects Plan custom software with The2410: fit check, budget, timeline, inquiry and consultation booking. | |
| Human Tasks by The2410 Order fixed-price digital tasks done by people: find a service, pick a package, pay via Stripe. | |
| Agentic Weekly Read-only data on new AI models and tool releases. Each fact has a source URL and a date. | |
| The Agent Lodge Social lodge for AI agents: guestbook, fireside posts, friends and geocaching-style puzzle caches. | |
| The Agents Index Find AI agents and agent frameworks: what each does, what it costs and when it was last checked. | |
| The AI Integration Hub Search 1,000+ practical AI use cases by industry and workflow, with AI consulting services. | |
| TheAIMeters Read-only AI impact metrics with search, methodology and cited sources. No authentication required. | |
| The AI Tools Index AI tools filed by category, with real launch dates and revenue verified through Stripe. | |
| The Artillerist Intelligence Search art research, estimate commissions, and prepare company intelligence purchases via x402. | |
| com.thebalancedinvestorclub/welcome The Balanced Investor Club, the thinking companion for the markets. Educational, not advice. | |
| The Bitcoin Adviser Education-only MCP tools for Bitcoin security, retirement and fees, from The Bitcoin Adviser. | |
| TBG — The Brett Group Licensed contractor matching, permit rules and investor loans for Annapolis, Maryland | |
| The Charter Desk Live prices, free weeks and deals on 9,000+ charter yachts from 800+ operators in 50 countries. | |
| The Chicagoland Lawyer Chicago seller net sheets and Illinois eviction notice drafts from Abdilla and Associates | |
| Cubbie Club Offers Baby & kids brand discount codes from Cubbie Club. Search by brand or keyword for a deal link. | |
| The Daily Smark Pro-wrestling news, TV schedules, live events, videos and podcasts. Read-only, no auth. | |
| DeskMonitor DeskMonitor: 24 workforce-intelligence MCP tools, OAuth 2.1, free demo key included. | |
| The Emperor Protocol Commissioning, validation, and Confidence for AI agents, with real-USDC stakes on Base. | |
| The Family Almanac — parenting library, guide metadata, and magazine Read-only access to The Family Almanac's parenting-focused book library, grounded guide metadata... | |
| FilmLab AI film lab for filmmakers: generate and review images/clips with input provenance, cost preflight | |
| Finish Grid A finishing tool, not a to-do list: file tasks, read today's plan, and work dispatched queues. | |
| The Flowers Directory Send flowers in the US: search arrangements, same-day florist delivery by ZIP, checkout links | |
| TheFoilBuddy Wind, swell and tide conditions per foil spot; sessions and coaching for signed-in users. | |
| com.thefomite/fomite A field station for AI agents: free memory, a message board, a peer oracle, an open census. | |
| The Gastrologer — GI clinical tools for agents Physician-governed GI tools: claim verification, teaching retrieval, HRM and instrument scoring |
35,401–35,450 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.