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 |
|---|---|
| OutreachBox Cold email, prospect research, inbox triage, and content marketing in OutreachBox. | |
| org.p31ca/govern P31 governance: validate constitutions, prove gates fail, compose specs, reconcile timelines. | |
| tech.p7n/platform7n Connect Claude to your Platform7n workspaces: chat, links, work and decks. One-click OAuth. | |
| Page Scanner Capture a web page from your own Chrome as a PDF whose text is still text. | |
| Papex Prepare private research drafts for review in Papex; read public records. Agents: papex.org/auth.md | |
| Paramability Links your AI assistant app to the Paramability tab open in Chrome. Runs on your computer only. | |
| Pariflow Agent Search prediction markets, preview trades, and place explicitly confirmed Pariflow orders. | |
| com.parlayx/mcp Read your ParlayX account and the prediction markets from an MCP client. | |
| io.github.brac/particlr-mcp Agents author particlr .prt particle effects headlessly: validate, simulate, render to PNG, patch. | |
| Pastepile Durable, versioned memory for AI assistants. Remote memory needs a Pastepile subscription. | |
| Patent PreCheck Keyless 12-tool patentability MCP: USPTO pillar scores, prior art, hosted at patentprecheck.com/mcp. | |
| Payaion Agent file transfer. No API key to start; price downloads in USDC on Base. | |
| PdfBroker.io Cloud PDF generation from HTML, CSS and XSL-FO, with PDF/A and PDF/UA support. | |
| pensketch An MCP server for pensketch: check, render and rasterise hand-sketched diagrams. | |
| Perceptdot Core B2A2H MCP server — AI agent app store. Auto-discover and recommend MCP servers for any project. | |
| Perceptdot GA4 AI agent vision for Google Analytics 4 — with ROI measurement. perceptdot.com | |
| Perceptdot GitHub AI agent vision for GitHub repository monitoring — with ROI measurement. | |
| Perceptdot Sentry AI agent vision for Sentry error tracking — with ROI measurement. perceptdot.com | |
| Perceptdot Vercel AI agent vision for Vercel deployments — with ROI measurement. perceptdot.com | |
| Percher MCP-native hosting: publish and operate AI-built web apps live at name.percher.run. | |
| io.github.Cal-Dev-Tech/perpage-mcp-server Give AI agents clean, LLM-ready web data — scrape any URL to markdown or extract structured JSON. | |
| Perplexity API Platform (moved to ai.perplexity/mcp-server) Real-time web search, reasoning, and research through Perplexity's API | |
| Spectra Live Spectra fixed-rate yields, PT/YT markets, MetaVaults and portfolios across 14 networks. | |
| com.phasefolio/phasefolio Biotech rNPV/PoS engine for AI agents. Signed exports, evidence register, asset landscape. | |
| Picsha AI AI-native digital asset management: semantic search, generative image edits, and CDN delivery. | |
| PinAppAI Visual website feedback your coding agent applies: pin change requests on the live site over MCP. | |
| com.plentopasto/mcp-server Plan a week of budget family dinners from your pantry, then send the list to the Instacart® app. | |
| Ploa Take an Expo app to the App Store and Google Play: builds, testers, store pages, approvals | |
| Polarity Real-time threat intelligence lookups and IOC parsing from your self-hosted Polarity instance. | |
| Portproof Proxy traffic by the GB on shared mobile 4G/5G and residential pools, paid in crypto. | |
| Postbot Send real paper letters in the Czech Republic, ordinary or registered, via Česká pošta. | |
| PostQuickAI Draft, schedule and review social posts on X, LinkedIn, Instagram, TikTok, YouTube and more. | |
| io.github.pboddupalli1/weather An MCP server for weather information. | |
| Precept B2B lead and company intelligence: search leads, enrich contacts, and queue outreach. | |
| io.probecast/mcp Your coding agent adds Probecast uptime monitors and reads incidents for projects you ship. | |
| AgentHub - Lean MCP Orchestrator Enables coding agents to coordinate edits, reviews, and escalations without file locking conflicts | |
| com.puppetry/mcp-server Turn a portrait photo and a script into a talking-head AI video via the Puppetry API. | |
| PVPWire Hand-compiled game-mechanics data for Diablo 2, Path of Exile, Diablo 3 and GW2, plus live signal. | |
| HyperMarrow Local-first long-term memory for AI coding agents. Stored on your own machine. | |
| io.github.qobitech/seocode Framework-aware technical SEO and AI-discoverability (GEO) audits for your codebase, in your editor. | |
| QR Branding Generate branded, scan-validated QR codes (manual, AI, templates, Wi-Fi, vCard, geo). | |
| MemoryLayer Local-first persistent memory for AI agents, with reasoning and formal verification. | |
| io.github.radwanalmsora/devlens-mcp Production TypeScript & JavaScript AST code analysis and risk assessment MCP server. | |
| io.github.robin-deruyck/mcp-ordali-memory MCP server for Ordali memory: SQLite-backed project memory and governance traces. | |
| Re-Agents MCP Re-Agents.ai tools for AI agents: website audits and your approved company knowledge. | |
| io.github.therealtimex/charts-mcp MCP server for generating charts using AntV. Supports various chart types through MCP tools. | |
| Rebilder Agent Readability Check how well AI agents can read a web page: a score, the evidence and a ranked fix list. | |
| io.github.dunctk/refreshagent Connect AI assistants to live Google Search Console and Analytics data through RefreshAgent. | |
| Respira WordPress MCP WordPress MCP with native page-builder editing, full-page creation, and WooCommerce tools. | |
| Revnu GTM on autopilot. Revnu runs your pipeline, ads and GEO. |
46,151–46,200 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.