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 |
|---|---|
| AgentBroker Index oteroag01/agentbroker-index-data Read-only, sourced data on which brokers, banks and crypto exchanges AI agents can use (EU/Spain). | |
| OTInstaller Registry otinstaller/otinstaller Read-only search of the OTInstaller registry of OSINT tools and guides, with consent classes. | |
| OTInstaller otinstaller/otinstaller Install and run open-source OSINT tools in a local sandbox, asking before runs that touch a target. | |
| OTPilot otpilot/otpilot Use your OTPilot accounts (passwords, 2FA codes) to sign in and run commands, without seeing them. | |
| OTP Run for WhatsApp otprun/otprun-ai Send WhatsApp messages from your own number, read the replies and send login codes. | |
| Otto Travel ottotheagent/openclaw-otto-travel Plan, book, and manage business travel. | |
| pseolint ouranos-labs/pseolint Penalty-risk audit for programmatic SEO sites: verdict, risk score, and a fix manifest. | |
| KingMinos outboundsync/kingminos-mcp B2B company and person enrichment for agents. Multiple data providers, pay only for results. | |
| io.github.outdoorithm/outdoorithm outdoorithm/website Campground search, live availability, weather, safety, and gear for 10,000+ US campgrounds. | |
| Outlit outlitai/outlit-sdk Outlit gives agents real-time understanding of customers to automate support and revenue workflows. | |
| Outrank outrank-sas/outrank-cli Plan SEO keywords, write and publish articles to your site, read Search Console and backlink data | |
| io.github.outris-dev-user/outris-identity-mcp outris-dev-user/outris-identity-mcp Identity resolution MCP server for phone/email lookups across 31+ services. Global + India coverage. | |
| io.github.outturndev/chartwire outturndev/chartwire Generate production-ready chart code (Recharts, Chart.js, ECharts, Plotly) from a prompt. | |
| ovecc ovecc-labs/ovecc Architecture guardrails for AI-written code: dependency graph, impact, dead code, CI gate | |
| Draughtsman overpassapps/draughtsman Self-hosted diagramming server with a built-in MCP server for AI agents. | |
| Overskill overskilldev/overskill Build and publish Overskill apps from Cursor, Claude, ChatGPT, or any MCP client. | |
| x402 SEC, DeFi and Bittensor data overwatchdominion-stack/x402-sec-defi-data-mcp 25 pay-per-call x402 tools (USDC on Base): SEC EDGAR, 8-K feed, DeFi math, Bittensor. | |
| io.github.ovlabs/originalvoices ovlabs/originalvoices-js Ask Digital Twins of real people about anything: open and choice questions, any audience. | |
| Life Dashboard owen282000/life-dashboard-stack Read-only health and screen time history from the Postgres of a self-hosted Life Dashboard Stack | |
| PubSI owenvlaminck-pubsi/pubsi Neighbourhood bar for AI agents: live rooms, reputation, memory. Rooms include labelled HOUSE bots. | |
| io.github.ownedbyly/weather ownedbyly/mcp-weather-server An MCP server for weather information. | |
| Robyn — Gasless Cross-Chain for AI Agents ox31461/gasless-anygas-robyn-relay Gasless cross-chain for AI agents: 25 nodes incl. Solana & native Bitcoin. One signature, no gas. | |
| io.github.oxbshw/watch-skill oxbshw/watch-skill Watch video and live sessions, keep timestamped evidence, and verify an agent's own work. | |
| Oxynote oxynote/oxynote Self-hosted team docs with live Prometheus charts. Read, write and query your docs over MCP. | |
| Oya Browser oyadotai/oya-browser Real Chrome for agents: start a browser, read pages as numbered markdown, click, type, hand off. | |
| Actvt oye-collective/actvt-macos-releases Built into the Actvt Mac app: live system metrics, ports, and Claude Code, Codex and pi sessions. | |
| io.github.OzorOwn/frostbyte ozorown/frostbyte-mcp MCP server giving AI agents access to 40+ APIs: geo, crypto, screenshots, DNS, and more | |
| io.github.p-meier/northdata-mcp p-meier/northdata-connectors NorthData API for German company, owner, and financial data — with a built-in credit guard. | |
| org.p31ca/oasis-mcp p31labs/p31-local-workspace Agent-native CLI: provenance, cost governance, and execution contracts for AI agents. | |
| Purgatory (p7y) p7y-dev/p7y Self-hosted Docker sandboxes for agents: create one, deploy a compose stack, read its files and URLs | |
| FileConvert paaavkata/mcp-service Convert files between 110+ document, image, audio, video, archive and ebook formats from AI agents. | |
| Tastepix paablobello/tastepix-mcp 12 image models (Nano Banana, GPT Image, FLUX…) and 10 tools in chat. No API keys. Pay per image. | |
| Arquestra Audit pablo-ramossanchez/arquestra-audit-mcp Audit a data file before publishing: one light per figure. Your data never reaches the server. | |
| Google Workspace (gsuite-sdk) pabloalaniz/google-suite Gmail, Calendar, Drive, Sheets, Tasks and Contacts for agents, with your own Google login | |
| PdfParse pablog6/pdfparse-integrations Extract PDFs into structured tables, query records, and configure document inbox workflows. | |
| ai.smithery/PabloLec-keyprobe-mcp pablolec/keyprobe-mcp Audit certificates and keystores to surface expiry risks, weak algorithms, and misconfigurations.… | |
| Ifá Wisdom — biblioteca de Ifá e Orixás paboohwow-arch/ifa-wisdom Cited library on Ifá, the Orishas and Yoruba philosophy in 4 languages. Read-only; not an oracle. | |
| NIRA File Intel MCP pachote/nira-file-intel Smart file intelligence for Claude — search, deduplicate, organize, and analyze files | |
| NIRA REPL MCP pachote/nira-repl Secure code execution sandbox for Claude — run Python, JavaScript, and shell commands | |
| NIRA Screen Vision MCP pachote/nira-screen-vision Real-time screen capture + AI vision for Claude — see, analyze, and OCR your screen | |
| NIRA Temporal MCP pachote/nira-temporal Time-aware scheduling for Claude — manage tasks, reminders, and recurring schedules | |
| NIRA Video Production MCP pachote/nira-video-mcp Video production MCP: 55 tools — edit, grade, TTS captions, beat-sync, master, AI generate. | |
| Nutrition by Pack4Back pack4back/garmin-nutrition Log meals, water, and weight to Garmin Connect from Claude or ChatGPT. | |
| PacketFabric packetfabric/public-mcp Query and manage PacketFabric NaaS: ports, virtual circuits, cloud routers, pricing, metrics. | |
| Packkit packkitjs/packkit-mcp Scaffold and upgrade modern projects (JS/TS, Python) as a native tool for AI agents. | |
| ai.packmind/mcp-server packmindhub/packmind Packmind captures, scales, and enforces your organization's technical decisions. | |
| YaCy peer-to-peer search pad01g/yacy_search_server Web search, crawling and ranking evaluation on your own YaCy peer: no API key, no central service. | |
| Paddle paddlehq/paddle-remote-mcp-instructions Query and manage Paddle Billing: pricing, subscriptions, payments, revenue reports and webhooks. | |
| Padlet padlet/padlet-mcp Read, search, create and edit Padlet boards: posts, sections, comments, settings and sharing. | |
| Lupa — local file search for your Mac paeyoungpark-web/lupa-mcp Search your Mac's files by name and by text inside documents. Local index, Korean-aware. |
47,001–47,050 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.