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 |
|---|---|
| Riveter riveterhq/riveter-mcp MCP server for Riveter's enrichment, scraping, and monitoring API | |
| Recite MCP rivradev/recite-mcp Local MCP server for Recite receipt processing with ledger and memory tools. | |
| io.github.rixile9999/tdl-mcp rixile9999/tdl-mcp Read-only Telegram MCP server wrapping the tdl CLI: list chats, read messages, download media. | |
| Mail-MCP rixtayz/mail-mcp Personal Outlook.com / Hotmail inbox: read, search, file, delete, unsubscribe via Microsoft Graph. | |
| mcp-usage rixtayz/mcp-usage Find out which MCP servers you actually use: local, read-only audit of Claude Code transcripts. | |
| io.github.rjandino/zopaf rjandino/zopaf Negotiation math engine. Pareto frontier, counteroffer generation, zero LLM tokens. | |
| io.github.rje1974/arca-agro rje1974/arca-agro-mcp Cartas de porte, padron y comprobantes de ARCA (Argentina). Solo lectura. | |
| io.github.rjexile/sports-card-agent rjexile/sports-card-agent Sports card pricing, market analysis, grading ROI, and player stats (NBA/NFL/MLB) | |
| OSINT MCP rjn32s/osint-mcp 26 free OSINT tools as MCP tools for AI agents. Auto-installs everything on first run. | |
| io.github.RLabs-Inc/gemini-mcp rlabs-inc/gemini-mcp Gemini 3 MCP server with 30+ tools: images, video, research, TTS, code exec & CLI | |
| io.github.rlawogh1005/green-mcp rlawogh1005/green-mcp Measure a program's CPU energy and LLM tokens, then refactor it cheaper. Measure, never estimate. | |
| Dutch Property Context rleefers/dutch-property-context Dutch property report by address: build year, energy label, neighbourhood, monument, schools. | |
| Dutch Vehicle Context rleefers/dutch-vehicle-context Dutch vehicle report by licence plate: MOT, defects, odometer verdict and open recalls. | |
| io.github.rlrghb/outlook rlrghb/olkcli Outlook & OneDrive MCP: personal & enterprise tools for mail, calendar, contacts, tasks, files | |
| Catalyst Edge Research rm0nroe/catalyst-edge-mcp Source-linked market intelligence for AI agents researching public-company tickers. | |
| io.github.thealidev/dmcps rmaapk/dmcps DMCPS: Highly secure, isolated MCP server environment giving AI agents sandboxed shell access. | |
| Losbeto — Market Data for AI Agents rmartins1451/losbeto Market data, LLM gateway, ML forecasts, batch+bundle, self-building catalog. USDC via x402 + MPP. | |
| io.github.rmathew1973/ios-sim-mcp rmathew1973/ios-sim-mcp Drive the iOS Simulator via semantic accessibility-tree snapshots. Sub-200ms, no WebDriverAgent. | |
| io.github.rmeadomavic/ardupilot-mavlink-mcp rmeadomavic/ardupilot-mcp Live ArduPilot control over MAVLink: state, params, modes, prearm diagnosis, gated arm. SITL-first. | |
| AddSign rmindgh/addsign-mcp Send documents for e-signature from templates, track status, remind signers, get signed PDFs. | |
| io.github.rmterenzi/qseow-mcp rmterenzi/qseow-mcp Agent tools for Qlik Sense Enterprise on Windows: troubleshoot, govern, query and build. | |
| rn-devtools-hub rn-devtools-hub/rn-devtools-hub Drive a running React Native or Expo app from inside its JS runtime: see, act, prove. | |
| WordPress MCP Server rnaga/wp-mcp MCP server for WordPress. Manage posts, users, comments, terms, metadata, and settings. | |
| dev.rendraputra/100pro-token-risk rndrpp/100pro-mcp Read-only risk tools: token screen, contract source, wallet. $0.10 USDC on Base. | |
| RNWY Trust Intelligence rnwy/mcp Check if an AI agent is trustworthy. Sybil detection, signed attestations, 150,000+ agents. Free. | |
| RoamProxy roamproxy/roamproxy-mcp Fetch pages and get proxies via residential, datacenter and mobile IPs in 190+ countries. | |
| Roar AI roar-ai-labs/roar-ai-mcp Deploy the apps you build with AI, with databases and domains, and call 200+ AI models on one key. | |
| io.github.robbhimself-1337/claude-army robbhimself-1337/claude-army Orchestrate multiple Claude Code agents in parallel from chat | |
| mcp-lint robert19001-cmyk/mcp-lint Lint MCP tool schemas for client compatibility and agent recovery. | |
| io.github.robertdoneill/jmap-calendar-mcp robertdoneill/jmap-calendar-mcp Read calendars and create, change or (opt-in) delete events on any JMAP server, such as Stalwart. | |
| Ikuna robertohanas/ikuna-mcp Read workspace context and activity from the running Ikuna macOS app, with app-managed permissions. | |
| search-rotation robin-bially/search-rotation-mcp MCP server for web search and page extraction across the free tiers of several providers | |
| SimConnect MCP robin24/simconnect-mcp MCP server for MSFS SimConnect - full read/write access to SimVars, L-vars and events | |
| Stripe MCP robinafaruqia/stripe-mcp Read-only MCP server for querying Stripe customers, payments, and invoices. | |
| Postel robinfaraj/postel-mcp Write posts in your voice from what's going viral in your niche. Schedule to X, LinkedIn and more. | |
| io.github.robinlidberg-dot/cap-shield robinlidberg-dot/cap-shield-mcp Context selection and compression for AI agents - recall measured, not claimed. | |
| xbrlkit robofinsystems/xbrlkit Read SEC EDGAR and XBRL filings with an AI: 18 tools over the filing itself. Local, free, no account | |
| Robot Speed robot-speed/mcp SEO tools for AI agents: audits, Core Web Vitals, keywords, AI visibility, traffic, backlinks. | |
| HTTP 402 AI Tollbooth robotfleet-hq/http-402-ai-tollbooth-public Free MCP troubleshooting-preview tools; purchases stay human-directed. | |
| io.github.RobotFleet-HQ/security-orchestra robotfleet-hq/security-orchestra Multi-agent MCP platform for data centers and critical power. | |
| Sugar roboticforce/sugar Autonomous AI development system with persistent task queue and background execution | |
| io.github.robotmcp/ros-mcp-server robotmcp/ros-mcp-server Connect AI models like Claude & ChatGPT with ROS robots using MCP | |
| io.github.RobThePCGuy/rag-vault robthepcguy/rag-vault Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup | |
| ChangeAtlas robyroro/mcp-changeatlas Local Git change impact and related test discovery with inspectable import paths | |
| OSINT robyroro/osint-mcp Domain and website investigations: batch recon, shared infrastructure, CT history and public lookups | |
| PersonaMCP robyroro/personamcp Local-first memory of how you write: style profile and real reply examples from your chat exports | |
| Romania robyroro/romania-mcp Romanian company reports, ONRC search, public contracts, VAT checks and local monitoring | |
| Harbor Crew Cross-Chain Report rocket-harbor-420/harbor-cross-chain-report-mcp Paid read-only reports for 1–5 EVM addresses across four networks; 0.02 supported stablecoin direct. | |
| Voris rocket-venture-labs/voris-mcp Voris privacy-native web analytics for AI agents: query metrics & citations, scaffold tracking. | |
| io.github.Rocketech-Software-Development/formacv rocketech-software-development/formacv-mcp FormaCV MCP server for AI-powered CV formatting, anonymization, tailoring, and ATS push-back. |
15,951–16,000 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.