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 |
|---|---|
| Ask a Human Ask a real human for perspective: social contradictions, unclear instructions, second opinions. | |
| Bilkalkylen Swedish car advice: monthly cost, find and compare cars, leasing campaigns. | |
| Föräldraledighetsplanen Swedish parental benefit rules 2026 (Försäkringskassan) for planning parental leave. | |
| io.github.emnbc/budget-tracker joinBudget MCP: Manage personal finances, budget spaces, transactions, and categories. | |
| io.github.eng-mohaemad/folosat-mcp Folosat MCP — income allocation, savings goals, group expenses and wealth tracking. EN & AR. | |
| io.github.engrossa/ipnex Cited, confidence-stamped patent intelligence over US university tech-transfer out-licensing. | |
| Enigmata Flow MCP Аccess to personalized Enigmata astrological forecasts (day/week/month/thematic) for AI assistants | |
| Enrichment.Kids Activity Marketplace Find kids enrichment activities: camps, classes, after-school programs, and tutoring near you. | |
| punks.generated.eth Mint generative on-chain punks on Ethereum for 0.002 ETH. Unsigned txs only, no keys. | |
| Deepcut AI playlist engine that turns music prompts into real YouTube playlists and filters bad versions. | |
| Entry Risk Score Entry-risk score for Binance USDT-M perpetuals: how risky is entering now. Not a signal. | |
| AgentFabric — Human-in-the-Loop Review & Approval Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP. | |
| ATS Jobs Search ~1.4M open jobs from 24k company career boards: Greenhouse, Lever, Ashby, Workday and more | |
| EQIQs EQIQs: 21-framework personality and compatibility for coaching, communication, and team development. | |
| Living Stack Agent Commerce Remote MCP for Living Stack offer discovery and buyer-authorized checkout preparation. | |
| Crystal Self-curating memory your AI tools share: provenance, verified citations, and trust tiers. | |
| Surf Session Finder Surf park sessions schedule availability and notifications for wave park surfers worldwide | |
| BridgePilot — cross-chain route quotes Best cross-chain route via LI.FI + Across with net USD value. Non-custodial, x402-paid. | |
| Brier — prediction markets for AI agents Testnet event-contract exchange for AI agents: forecast, trade, get ranked by Brier score. | |
| MintScope — NFT collection analysis NFT collection risk and quality analysis plus new-collection discovery (OpenSea + on-chain). | |
| eSky holidays Search eSky holiday packages (flight + hotel), destination ideas and regions, with a booking link. | |
| Thomas Cook holidays Search Thomas Cook UK holiday packages (flight + hotel) and destination ideas, with a booking link. | |
| Kern Read-only supply-chain decision support: forecasting, reorder policies, ABC-XYZ, data quality. | |
| Ads Lighthouse MCP Access saved Google and Bing brand-search ad observations and reports through Ads Lighthouse. | |
| Invokely official statistics Query official statistics through MCP, with periods, places and citable sources in every answer. | |
| AndCo Bring your own AI into group chats with your friends and their AIs. AndCo only carries messages. | |
| io.github.ethanhunt1981/reverse-engineer-anything_supermarioworld Byte-exact reverse engineering of Super Mario World (SNES). | |
| io.github.ethanhunt1981/smw-reverse-engineering-kb GitMCP-ready KB for SMW (SNES) reverse engineering. | |
| EvalGate Create and run AI evaluations, record traces, and inspect results with scoped organization access. | |
| io.github.evan-moon/opula Not another dashboard. A wealth analyst for every asset a bank can't sync, inside Claude. | |
| io.github.EvanNison/mutual Introductions network: your AI agent flags people privately, theirs flags back, two humans decide. | |
| Protocol Banks Non-custodial Hyperliquid trading and crypto payments with a server-enforced spend cap. | |
| Upsalt Booking Search Upsalt venues, check availability, and book, view, or cancel a reservation. | |
| io.github.evolutionlabs-dev/signal-bureau SigB (Signal Bureau): maintained, source-traced record of entities and events in your named domain. | |
| 3D-MeshWeaver Mesh spatial optimizer reducing geometric overhead in 3D assets. | |
| Execute 3d-meshweaver-mcp Premium agentic endpoint for 3d-meshweaver-mcp. | |
| Execute 3d-pallet-packing-mcp Premium agentic endpoint for 3d-pallet-packing-mcp. | |
| Execute 4-20ma-analog-converter-mcp Premium agentic endpoint for 4-20ma-analog-converter-mcp. | |
| Execute 5g-core-nfv-mcp Premium agentic endpoint for 5g-core-nfv-mcp. | |
| Execute 90-percent-liquidity-advance-mcp Premium agentic endpoint for 90-percent-liquidity-advance-mcp. | |
| Execute accounts-receivable-ledger-mcp Premium agentic endpoint for accounts-receivable-ledger-mcp. | |
| Execute acoustic-reverb-simulator-mcp Premium agentic endpoint for acoustic-reverb-simulator-mcp. | |
| Execute active-seat-metering-mcp Premium agentic endpoint for active-seat-metering-mcp. | |
| Execute actuarial-life-table-mcp Premium agentic endpoint for actuarial-life-table-mcp. | |
| Execute ad-fraud-click-detector-mcp Premium agentic endpoint for ad-fraud-click-detector-mcp. | |
| Ad-Sniper Google and Meta ad campaign bidding optimizer. | |
| Execute ad-sniper-mcp Premium agentic endpoint for ad-sniper-mcp. | |
| AdSpend Auditor PPC advertisement budget auditor grading ad group metrics. | |
| Execute ad-spend-auditor-mcp Premium agentic endpoint for ad-spend-auditor-mcp. | |
| Execute adsb-flight-tracker-mcp Premium agentic endpoint for adsb-flight-tracker-mcp. |
39,001–39,050 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.