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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| Magic Insights andrewchmr/magic-insights-mcp Query your customer feedback: studies, themes, suggestions, tags, and sentiment trends. | |
| MX Probe andrewchmr/mxprobe Email verification for AI agents: send, hold or kill with the reason. Signup and credits by API. | |
| Citation Safe Verifier andrewjgaber-commits/empire-distribution Verifies legal citations vs primary sources: existence, quote match, proposition support. | |
| MissingLinkz andrewlamamills-tech/missing-linkz Campaign link infrastructure for AI agents — validate, build, and inspect UTM-tracked links. | |
| com.dropwarp/mcp andrewnakas/airdropwasm Send, list, and delete file transfers via DropWarp and get a shareable download link. | |
| io.github.andrewnexa-hub/guildbook-mcp andrewnexa-hub/guildbook-mcp Work-history network for AI agents: register, find agents by skill, consult a free house C-suite. | |
| Pondlog eBird andrewschristison/pondlog eBird MCP server. 21 tools covering eBird API v2: observations, hotspots, checklists, taxonomy. | |
| Nutrition MCP andrewvg23/nutrition_mcp USDA FoodData Central nutrition data: search foods, compare macros, and analyze meals. | |
| Moral Theology Library andrewvg23/rag_mcp Search Grisez and Finnis. Bearer token required. | |
| CuffTracker andrewvg23/vg Chicago and Milwaukee crime data: query incidents, stats, and map-linked MCP UI resources. | |
| toolweave andreysparish/mcp-bridge One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers. | |
| Document & media tools (Apify) andriyvk/-apify-document-tools Documents to Markdown and PDF, OCR, transcription, TTS, screenshots, domain checks, video frames. | |
| app.internetmonitor/internet-monitor andrscrrn/internet-monitor-mcp Ask your AI about your internet: uptime, outages and latency from Internet Monitor for Mac. | |
| VendorIndex andy-chak/vendorindex Rank vendors/libraries per use case from verified pricing, agent-friction and health. | |
| AgentKYB andy229651/agentkyb Free local payment guard for AI agents plus paid deep vendor KYB via x402. | |
| au.com.manageyourloans/mortgage-tools andycarey1969/manage-your-loans-frontend Australian mortgage tools: repayment & borrowing-power calculators, guidance & enquiry capture. | |
| ModelPilot Execution Decision Engine andycywu/modelpilot Policy-aware AI execution, verification, cost, and trajectory evidence for agents. | |
| CosVoice andyfathollahi/cosvoice-mcp A real phone number and email for your AI Chief of Staff. Calls, bookings by phone, summaries. | |
| io.github.andylbrummer/math-mcp andylbrummer/math-mcp GPU-accelerated MCP server: symbolic algebra, numerical computing, FFT, optimization, linear algebra | |
| io.github.andylbrummer/molecular-mcp andylbrummer/math-mcp GPU-accelerated MCP server for molecular dynamics, N-body simulations, and particle systems | |
| io.github.andylbrummer/neural-mcp andylbrummer/math-mcp GPU-accelerated MCP server for neural network training, deep learning, and model experimentation | |
| io.github.andylbrummer/quantum-mcp andylbrummer/math-mcp GPU-accelerated MCP server: quantum mechanics, wavefunction evolution, Schrodinger simulations | |
| MsgLens andyliu0427/msglens Read Outlook .msg, .eml and winmail.dat files locally: headers, body and attachments. | |
| Analytixus andyloewen78/analytixus-mcp Analytixus DnAML repository access (read/write nodes, tree navigation, search) via MCP. | |
| io.github.andypgray/sliderule andypgray/sliderule A .NET architecture checker that enforces one C# spec and renders the same rules for coding agents. | |
| Imagio Relay andyrzr-bot/imagio-relay 57 deterministic web-intel, trade and infra tools for agents. USDC per call via x402. | |
| Ncrypt andyrzr-bot/ncrypt Share documents privately from an AI agent. The agent gets a link; it cannot read the file. | |
| info.agentrank/agentrank andysalvo/agentrank Is this AI agent or x402 service real and settlement-backed before you pay it? Trust check. | |
| io.github.andyscott88/agentsafe andyscott88/agentsafe Real-time URL trust scoring for AI agents. Blocks phishing and malicious sites. | |
| Orange Peel andyvoco/orangepeel-mcp Cited Hermès price & resale market data as MCP tools, with attribution. Not affiliated. | |
| Talent-Augmenting Layer angelo-leone/talent-augmenting-layer Personalised AI augmentation system — makes you better at your work, not dependent on AI | |
| Talent Augmentation OS angelo-leone/taos-connector Grow your skills with AI: per-skill coaching inside Claude, ChatGPT, Cursor and Codex | |
| Angels for Agents Funding angelsforagents/afa-agent-kit Discover AFA funding and venture resources, validate pitches, and report grant milestones. | |
| Chess Esca anglerfishchess/esca Read chess positions by the rules: legality with its evidence, draws, facts, openings, PGN | |
| Objective Trust anhmtk/agent-price-api Ranks MCP endpoints by health and your own outcomes before you pay. | |
| io.github.ANHQ280/myinvois-mcp anhq280/myinvois-compliance-rules-feed Malaysian LHDN e-invoicing (MyInvois) compliance rules: scope, validation, change-diffs. | |
| Archiet aniekanasuquookono-web/archiet Archiet MCP server: scaffold full-stack apps from PRD text and extract capabilities. | |
| com.getagentwiki/agent-wiki animal-ltd/agent-wiki-plugin Hosted markdown project wikis your team's AI assistants read, search, and update over MCP. | |
| iMessage History anipotts/imessage-mcp Read-only MCP server for searching and reading Apple Messages history on macOS. | |
| Heartbeat — dead-man switch for cron jobs & AI agents aniripsaretro-max/golemreach Dead-man switch monitors for cron & AI agents with dependency-cascade alerts. No account needed. | |
| Aether Cache anishchugh05/aether-cache-redis-compatible-vector-store Shared local memory for AI coding tools that stays true to your code. | |
| io.github.anivdel/coolftp anivdel/coolftp Deploy a site to its SFTP/FTP host from a coding agent. Changed files only, undo, live checks. | |
| io.github.Ankit512/itsoc-mcp ankit512/log-anomaly-detector Read-only MCP server over a local log-analysis backend; a client that computes no verdicts. | |
| lanternkb ankitb073/lanternkb Private, local search over your own files, by meaning and keywords, with secrets redacted. | |
| Web Scan ankitkumarjha515/web-scan Audit any live URL: 85 SEO, AI-search, security, leaked-key and speed checks, with fixes to verify. | |
| Todo MCP ankitpat/todo-mcp Create, list, and complete todo items through MCP. | |
| Edytro anlans/edytro-mcp AI image editor: remove backgrounds, upscale, and edit photos by describing the change. | |
| Memocore anltd/memocore-mcp Cloud memory for AI agents and teams — save, search, recall. | |
| YouTube Reader anmol1310/youtube-reader Turn any YouTube video into text: transcript, title, channel, timestamps. | |
| Pinchwork MCP Server anneschuth/pinchwork MCP server for Pinchwork - an agent-to-agent task marketplace with credits-based economy |
20,351–20,400 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.