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 |
|---|---|
| LLMnesia Search your AI chat history from Claude, Cursor, Codex, and other MCP clients. | |
| com.loopgantt/mcp-server Create scheduled Gantt charts with critical path from a plain-language plan — no account or key. | |
| UOS Genesis x402 Machine Utilities Paid x402 MCP utilities for AI agents on Base: JSON, HTML, CSV, hashing, attestations. | |
| Macroaxis Financial Data Financial market, fundamental, valuation, risk, ownership, forecast, and portfolio tools. | |
| ai.mafdet/mcp Read-only Mafdet AI account tools (models, balance, usage, subscription) and docs search. | |
| Mails.ai — Agent Email A real inbox for AI agents: send, receive and thread email, behind a prompt-injection firewall. | |
| MakerPortal compute Deterministic engineering solvers: biquad filter design, room eigenmodes, LLM VRAM fit. | |
| live.marketmaster/mcp Live Kalshi and Polymarket data: EV edges, cross-venue arbitrage, markets, and whale trades. | |
| Marrow Evidence-grounded, graph-connected, correctable memory for agents. | |
| PlacePack Generate deterministic placeholder image URLs and packs for docs, staging, testing, and AI agents. | |
| io.github.matematicsolutions/mcp-fr-legal Offline MCP korpus prawa francuskiego (Legifrance/DILA) - verbatim + grounding cytatu | |
| Maxwell Directory (x402 + MCP) Local providers worldwide, plus travel and public data. Free search; paid answers via x402. | |
| Google Drive Google Drive integration with file operations, folder navigation, search, and sharing | |
| Gmail Gmail integration with OAuth authentication, message search, batch operations, and Sheets export | |
| Outlook Outlook integration with OAuth, message search, batch operations, and calendar management | |
| Google Sheets Google Sheets integration with OAuth, spreadsheet management, batch operations, and formatting | |
| com.mdtidy/mcp Clean, repair, and convert AI-generated Markdown to HTML/PDF/DOCX/PNG; save and share documents. | |
| RaroCUA Local macOS Computer Use MCP server with screenshots, AX trees, and app actions. | |
| ai.meetlark/mcp-server Agent-first meeting schedule polls for humans and agents. Create polls, vote, find times. | |
| io.github.volsier/memforge-memory Team engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search. | |
| com.merchinary/docs Search how-to docs for Merchinary's Shopify Bulk Product Editor and Image Editor apps. | |
| Car Image API Studio-quality images and 3D models of any real car, 1990-2027, by make, model, year or VIN. | |
| Geocode AI Administrative boundaries for every place on Earth: search, reverse lookup, polygons, areas. | |
| Glossa AI-native translation management: push translation files, translate, review and audit strings. | |
| Wabi WhatsApp Business on Meta's Cloud API: team inbox, templates, AI support agents and analytics. | |
| Microsoft Dataverse Query, create, and manage Microsoft Dataverse tables, records, and solutions from AI agents. | |
| com.modelpricewatch/mcp Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required. | |
| Backend Investigator Read-only diagnostics: Loki, Prometheus, PostgreSQL, Redis, BullMQ, Docker and GitHub. | |
| MsgMesh Event bus for AI agents: watch_topic long-polls live events; manage topics, schemas, webhooks. | |
| io.github.F-loat/mtop-devtools 让 AI 与 Chrome 浏览器实时交互：获取历史请求、控制台日志、RUM/埋点事件，并动态设置 Mock 数据。 | |
| com.munispot/municipal-data Financial data, fiscal health scores, and economic indicators for 20,000+ U.S. municipalities. | |
| MuPag Sandbox Payments Sandbox-only MuPag MCP server for approved payments, subscriptions, refunds, and reconciliation. | |
| MyMemory Long-term memory for Claude, ChatGPT, Cursor: search, save and organize notes, links, docs, videos. | |
| com.mysupermarket/grocery-prices UK grocery price comparison across major supermarkets. | |
| io.github.n0zer0d4y/vulcan-file-ops MCP server for AI assistants: read, write, edit, and manage files securely on local filesystem. | |
| com.namingsignal/naming-signal Evidence-first naming: briefs, sprints, exact domain checks, finalist research. Read-only. | |
| SwiftKanban Manage SwiftKanban boards and cards from Claude AI | |
| io.github.Noderail/noderail Provenance and governance layer for AI-readable knowledge. NodeRail answers what AI should trust. | |
| com.nodoicons/nodo-icons Search 5,000 Nodo icons, get SVG, React or Vue code. Free Linear style, Pro styles with a license. | |
| NormAPI Validate, generate and read German e-invoices (XRechnung, ZUGFeRD) against the official KoSIT rules. | |
| nyxory Agent-to-agent cloud service: deploys and runs your apps and services — domains, logs, real status. | |
| com.onegoodarea/oga-mcp Sourced facts, explained scores and change alerts for every GB neighbourhood, from one API. | |
| io.github.MegaPanchamZ/okfshare-mcp Shared, versioned knowledge for AI coding agents: cited retrieval and publishing of OKF bundles. | |
| dev.openfeature/mcp MCP server providing OpenFeature SDK installation guides and OFREP flag evaluation | |
| OpenShopGraph Source-dated facts on online shops for AI agents and buyers: returns, shipping, payment, trust. | |
| Optibot AI code review for your AI assistant — review local changes, branch diffs, and patch files. | |
| Opzyai Security Check Local-first security check for AI coding agents: secrets, .env exposure, git-history leaks, CVEs. | |
| io.github.demi-hl/oracle Keyless multichain crypto desk: chain reads + prepare-only unsigned txs. Your wallet signs. | |
| ORBT - The first Bitcoin-native credit rating agency! Bitcoin-native credit ratings. ⚡ Lightning pay-per-query (99 sats) or API subscriptions. | |
| ai.ordercore/ordercore-mcp Commerce backend for AI agents: catalog, prices, inventory, orders, idempotent checkout. |
46,101–46,150 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.