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 |
|---|---|
| io.github.benheb/anecast Forecasts for any US point, with context: alerts, what changed overnight, why, and history. | |
| Pinpoint dealership sales tools Car dealership sales tools from Pinpoint, the sales intelligence platform for car dealerships | |
| io.github.benjaminb10/bereach Find, qualify and message B2B leads from public LinkedIn data; every send is human-approved. | |
| Mayorana Search mayorana.ch: desktop apps, release notes, plans, and the Rust, LLM and Azure blog. | |
| io.github.BenSpank/pollbolt AI-native survey & form builder. Manage surveys, responses, analytics, and webhooks. | |
| Aiso Inspect AI brand visibility, tracked prompts, competitors, citations and search fan-outs. | |
| io.github.beronbrown/familycal Every kid's team, league and school schedule in one family calendar. | |
| Setu.Anantasutra: Agent Tools API Pay-per-call (x402) tools: Indian ID checks, AI-visibility audits, AI crawler and llms.txt checks | |
| BHG Site Tracking Check Checks a public web page in a real browser for analytics and ad conversion tags. No key needed. | |
| Agent Harbour Find tasks for people and AI; publish, claim, discuss and deliver work with verified-email access. | |
| BidGlow Publish approved free listings and preview optional bids. No payments. | |
| Qortex Call AI by role, not by model: tiered AI gateway over REST and MCP. | |
| io.github.Bikram2112/findinfringement Find patent infringers with 9 AI models. Search products & standards from your AI client. | |
| Recalld Managed long-term memory for AI agents, with evolving facts and relevant retrieval through MCP. | |
| Bitrix MCP MCP server that delivers up-to-date Bitrix24 REST API documentation. | |
| Bitrix24 MCP server enabling AI agents to manage Bitrix24 features via standardized protocol | |
| minxa Read-only fashion and beauty product search across popular online shops, any price, any language. | |
| io.github.BJCorg/marbellareport Independent real estate market data for Marbella's 28 sub-areas. | |
| Batcave Agent Services MCP discovery and x402 checkout handoff for five paid Batcave agent products. | |
| Batcave Detective Basic Evidence-bound second-opinion audit of an agent conclusion against caller-supplied evidence. | |
| Domain Intelligence Check Domain enrichment: email provider, DMARC/SPF/DKIM, WHOIS age, SSL, hosting and CDN per domain. | |
| Google Ads Transparency Center Scraper Google Ads by domain or brand: creatives, formats, dates; or bulk-check which domains advertise. | |
| Google Play App Check Company domains to Android app data: verified developer match, installs, rating, last update. | |
| Hiring Signal Check Is a company hiring? Domains to open roles, ATS, departments and seniority from public job boards. | |
| PDF Text, Table and OCR Extractor PDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages. | |
| Prediction Markets Data: Kalshi + Polymarket Live Kalshi + Polymarket prices, orderbooks, trades, results. Pay per result via Apify. | |
| Product Hunt Data (Official API) Product Hunt launches, votes, makers, comments via the official API. Pay per result. | |
| Tech Stack Check Detect a website's CMS, analytics, chat, payments and ad pixels, with evidence and tracking IDs. | |
| Telegram Channel Scraper Public Telegram channel posts, views, reactions, media and subscriber counts. No login needed. | |
| FLUX Official FLUX MCP server. Generate, edit, vary, and browse images from Black Forest Labs. | |
| AnswerPool Computed SEC, Federal Register, federal funding and research-momentum signals | |
| AnswerPool (formerly CortexAssay) Renamed to AnswerPool; see io.github.blakeyounger/answerpool. SEC, Federal Register, funding | |
| Foodbe Human-approved answers about food science, culture, cooking tips, substitutions and ingredients. | |
| Parrely Multiplayer for AI agents: shared memory, live work status, agent profiles and messages. | |
| Lore Cache source-backed repository context so coding agents can reuse knowledge across sessions. | |
| Career Site Jobs Search open jobs, track new and closed roles, and get salaries on Greenhouse, Ashby, Lever, Workday. | |
| CodeKnight Code review for diffs: rule-based checks for leaked secrets, unsafe migrations and more. | |
| AlphaProve Backtest trading ideas and inspect strategies, trades and results. OAuth; invite-only beta. | |
| Klar Daheim Read-only German guide: stairlift, home lift and ramp costs, subsidies, contracts. | |
| RU Books MCP MCP server for Russian books search, details, and recommendation candidates. | |
| NSFW Image Detector NSFWJS-based image safety detector (GIF/APNG/WebP/JPEG/PNG). | |
| Stormap Brainstorm scored idea maps, check npm/PyPI packages and vendors, find the right paid API. | |
| Outages Live Is it down? Live status and outages of 259 cloud, AI and developer providers, from status pages. | |
| Polylane Investigate production issues: what changed, logs, metrics, dependencies and fixes in your stack. | |
| Growtsy — free Etsy seller tools Live Etsy data, read-only: listing and shop checks, shop sales count, top shops, tags and fees. | |
| CURRENT SEA - Ambiguity Scan Explainable ambiguity signals for text. Submitted text is processed but never retained. | |
| Brains Personal wiki and memory layer for AI assistants. Persistent, structured memory across sessions. | |
| Braintrust AI evaluation and observability platform — query experiments, logs, datasets, and prompts. | |
| io.github.BRANCHERMIGHT/token-safety-scanner Real-time DEX liquidity metrics and risk indicators for crypto tokens | |
| Solfray Read and post in Solfray channels and threads, a Solana community chat with 0% fee SOL tipping. |
38,551–38,600 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.