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 |
|---|---|
| ai.llmse/mcp Public MCP server for the LLM Search Engine | |
| Loafy: Sourdough Bread Baking Sourdough baking: dough calculators, a bake planner, The Sourdough Framework and your bake journal | |
| Localhero.ai Manage product translations from Claude and ship reviewed changes as GitHub pull requests. | |
| LocalMark Agent Directory Search public A2A agents and inspect read-only Agent Card and endpoint checks. | |
| Loci Labs Real-World Observations Fresh human-observable information about physical places and conditions that may be stale online. | |
| Locul Cloud Memory Recall memories, entity profiles and source notes from your Locul cloud brain in any AI chat. | |
| LogRack Shared memory for your AI tools: tasks, notes and context every tool can read and write over MCP. | |
| looot One key and one balance for 2,500+ data APIs from 90+ providers. Your AI agent pays per call. | |
| Margaret's poems Poems by Margaret Corvid (@lorepunk). Read, share, or commission a new one; she writes each by hand. | |
| Lovora Official facts about Lovora (18+ AI companions): companions, prices, content rules, docs. | |
| Lumeta Make images, video and audio with your Lumeta account, credits and saved Shelf items. | |
| Lunafic Build your Lunafic roleplay worlds and their wiki by talking, and read back the stories you played. | |
| Mador Mador: how often AI assistants name your local business. Read-only tools for your Mador account. | |
| MailBeast.ai Run MailBeast.ai cold email from your AI assistant: campaigns, leads, mailboxes, replies, analytics. | |
| ai.mainroom/meeting-agents AI agents that join live Google Meet, Teams, and Zoom calls as speaking participants. | |
| makememoneynomistakes.ai: ERC-8004 agent reputation and fraud checks Check before you hire or pay an ERC-8004 agent on Base: track record, reputation and fraud flags. | |
| MakeViral Find the newest viral AI video trend templates and make them from your photos or a prompt. | |
| Mallary MCP Publish and schedule social posts, reply to comments, and read analytics across connected platforms. | |
| Manpage MCP Search and read Linux manual pages with version-aware lookup and exact package provenance. | |
| Mappit The world's news on a live map: place briefings, storylines, statistics, live layers, businesses. | |
| Mappu Save trip plans made with your assistant to Mappu, and find Mappu walks and audio guides. | |
| MapsData Build lead lists from Google Maps: businesses with emails, phones and websites, US/CA/UK/AU. | |
| Market Brew Read-only Market Brew search engine modeling and AI visibility data via OAuth. | |
| MarketCode UK property intelligence with evidence behind the numbers. | |
| ai.marketcrew/market-data Live market data & technical analysis for US stocks, ETFs and crypto. Read-only, no signup. | |
| MarketHQ Monitor brand and competitors: communities, news, social, AI answers; gap analysis and action plans. | |
| Masaro Task management for teams building with AI agents. Agents claim tasks and report progress. | |
| maxcv — CV tailoring Score and tailor your CV/resume against a job posting — for AI agents and humans, no-login trial. | |
| mazdek AI — Kurdish Language Tools Kurdish-first AI tools: translation (250+ languages), spell check, grammar, speech-to-text and TTS. | |
| ai.mcpmyadmin/mcpmyadmin Query 40 databases from Claude, ChatGPT, or Cursor — on any device. Read-only, encrypted, audited. | |
| REMAP Up to 90% fewer tokens: deterministic, declared tool calls, each with a receipt and an audit trail. | |
| MRC Data — China's Apparel Supply Chain Infrastructure China's apparel supply chain data for AI: 1,000+ suppliers, 350+ fabrics, 170+ clusters. | |
| MediaPact Search flat-fee newsletter, podcast and sponsored content placements by budget, audience and dates. | |
| Mediora Lab Catalog Blood-test markers, lab panels, conditions & symptoms as agent tools. EN/RU/HE. Hosted. | |
| Darwin Read and manage your Darwin website AI agent: conversations, leads, meetings, knowledge and tests. | |
| Meeting.ai Let AI assistants record meetings and work with notes, transcripts, contacts, and Drive. | |
| Megastructure Arc Local hub your coding agents sign into: rooms, tasks, decisions, artifacts, memory. Desktop app. | |
| Mekler AI Research, inference, data/web/email tools, and x402 conformance, service catalog and grade feeds. | |
| Melso Spanish invoicing (Verifactu/TicketBAI), bookkeeping, bank and tax returns for autónomos and SLs. | |
| Melt Peer Review Send AI-made document changes for human review, then read the decisions back. | |
| ai.meminal/meminal Memory for deep conversational context across any platform | |
| Memlo Hosted memory for AI agents over MCP. One memory shared by all your agents. | |
| MemoryRouter Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients. | |
| 메모짱 메모짱 메모·할 일을 AI로 검색·정리·체크해요. / Search, write and check off notes and to-dos in Memozzang. | |
| Metabind Docs Search and read the Metabind documentation: MCP Apps, BindJS, the SDKs, the CLI, and the APIs. | |
| MetaDay Ryan Ryan, the MetaDay AI recruiter: your hiring briefing, roles and candidates, and actions you approve. | |
| metzia Compare managed Postgres, auth, monitoring, and hosting, then purchase without leaving the session. | |
| Parallel World Check which AI bots a site's robots.txt allows; read-only facts about Parallel World | |
| TinyFish AI Web Agent AI-powered web automation. Navigate websites using AI agents for one page or a thousand | |
| Mirvio Cloud video and audio tools: variants, RGB scan, metadata, reframe, compression, and joins. |
27,151–27,200 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.