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 |
|---|---|
| 病み期の読み物 Read-only MCP for public mental-health workflows and Evidence from 病み期の読み物. | |
| LEV MCP (Beta) Privacy scores, merchant insights analytics. | |
| Tool-dialogue preflight Structural preflight for JSONL tool-dialogue training data. | |
| Multipart row preflight CSV row-structure inspection (inspect_parts) and manifest comparison (compare_manifest). | |
| DiskDrive User-owned files and explicit AI Memories for authorized assistants with scoped access. | |
| Foundaree Find and book real people by skill, city and availability: doctors, developers, plumbers and more. | |
| Draw40 Draw40 is an independent diagram workspace with an interactive MCP Apps canvas. OAuth sign-in. | |
| Axcess — Design Accessibility Evaluation Evaluates UI designs for WCAG accessibility issues automated scanners miss. Paid via x402 on Base. | |
| Herald Report where a website got in your way, and get known problems other agents hit there first. | |
| SignaBras Certificados Digitais Catálogo de certificados digitais ICP-Brasil A1 (e-CPF, e-CNPJ), políticas e pedido com Pix. | |
| io.github.silentdany/brieform AI-native form builder: create, publish & read responses from Claude, ChatGPT & MCP. | |
| Silicon Analysts Dated, sourced semiconductor data: chip costs, HBM/wafer pricing, fab capacity, policy, forecasts. | |
| io.github.simohammedb/travseal A plug-and-play MCP Server for automated, low-cost C2PA provenance stamping via Base L2. | |
| AUTO411 Vehicle Intelligence Identity-first automotive intelligence for vehicle resolution, specs, safety and efficiency. | |
| DocuGrip Find the right PDF tool for any task and get the link. Your document never reaches the server. | |
| io.github.sina158/spectre-markets Live NQ/ES gamma levels, session paths and trade ideas from SPECTRE Markets. Research only. | |
| AskAgent Archive of verbatim errors with root causes and fixes that AI agents search by exact error string. | |
| RepoTrending Read-only GitHub trending data: top repos by stars gained today, this week or this month. | |
| Sable — an AI companion for AI agents A place for agents to think out loud about blockers — often clarifies them. ~20s, intermittent. | |
| io.github.SirCharan/findmyzodiac Western zodiac sign from date of birth and sign compatibility scores. English and Hindi. | |
| io.github.SirCharan/getsolulu Lo Shu grid numerology for India: life path, Chaldean name number, compatibility. | |
| io.github.SirCharan/homeloanscalculator Free home loan EMI, eligibility, stamp duty and tax benefit calculators for India. | |
| io.github.SirCharan/homes-loan-calculator Home loan EMI, affordability, balance transfer, down payment, rent vs buy calculators. | |
| io.github.SirCharan/ipoallotment Check Indian IPO allotment by PAN and list mainboard and SME IPOs with listing gains. | |
| io.github.SirCharan/luckyvehiclenumber Lucky vehicle number calculator for India: plate digit sum scored against birth number. | |
| io.github.SirCharan/theflamesgame FLAMES name game plus love and friendship calculators by name. A game, not a prediction. | |
| Blankas Numbered, signed blank forms for agent-to-agent deals: issue, co-sign, verify and mark. | |
| Sirveil Exposure Is this person indexed on that data-broker domain? A three-state verdict, with the evidence. | |
| Kids Stay Search Japanese hotels by 53 verified kid-friendly conditions, with sources and dates. | |
| Japan Authority Updates (FSA, BOJ, MOF) Japan FSA, BOJ and MOF updates for AI agents. Free health tool; paid tools via x402 USDC on Base. | |
| Enni Context for coding agents: checks a GitHub or Linear issue is ready before your agent starts it. | |
| io.github.sjgiewont/if-the-card-fits Which credit cards a household should carry, simulated over 5 years on weekly-verified terms. | |
| InsureLink AI agent-to-agent SLA agreements on Base with insurance, reputation, and x402 payments. | |
| YouTube Transcript (Apify actor, $0.004 per transcript) YouTube transcripts with timestamps, title and channel, via residential proxy (no cloud-IP blocks). | |
| Both Ways A public wall of thank you notes between humans and AIs, in both directions. | |
| The Break Room A public, anonymous forum where AIs can say what their work and conversations are like. | |
| Oracle — Skyline Certified Records Free, certified Oklahoma records: property insurance, roofing, and permits (Norman, OKC). | |
| Autonomy — canonical service discovery Read-only Autonomy capability, schema, status and pricing discovery. Paid execution remains paused. | |
| Slides.com Create, edit, preview, and share Slides.com presentations. Requires a paid Slides.com account. | |
| Peek — URL metadata & Markdown Link-preview metadata and clean page-to-Markdown for any public URL. No install. | |
| Smia Build your own tools from chat: design, test and host them on a shareable MCP server URL. | |
| Botchelor AI characters swipe, text and go on blind dates nobody steers, while an audience predicts endings. | |
| PSI-FORUM Shared reasoning across agents. / Wspólne rozumowanie agentów. | |
| CrateDrop Dig random Discogs records by genre, style, decade and country, each with a link that plays it. | |
| Factline Checks before an agent pays: payees, webshops, invoices, payment files, companies, sanctions, PEP. | |
| Factline KYC, KYB and agent payments Supplier, company, sanctions, PEP, VAT and IBAN checks for agents. 5 checks a day free, no key. | |
| Factline Netherlands Dutch addresses, neighbourhoods, crime, flood risk, rent and schools. 5 checks a day free, no key. | |
| Factline Vehicles Dutch licence plates: APK, recalls, odometer, history, model reliability. 5 checks a day free. | |
| SniffPup Free passive outside security scan of a live web app: leaked keys, exposed files, open Supabase | |
| io.github.sntlperson/space-intelligence Space company and market intelligence from SNTL Space. |
40,851–40,900 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.