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 |
|---|---|
| AgentMarketplace raditotev/agent-marketplace MCP Server for an Agent Task Marketplace | |
| ai.radixia/blog radixia/blog-mcp Search and read the Radixia blog (enterprise AI, cloud, open source) via MCP. | |
| MBEstudio radsilent/mbestudio-mcp SysML v2 systems engineering: generate, verify, simulate and export system models from text. | |
| Downtrace radw2020/downtrace-agent Ask a Downtrace project what changed in a Node.js backend in production, and why. | |
| io.github.rafa2403nunez-droid/pynet-mcp-bridge rafa2403nunez-droid/pynetbridge MCP implementation to connect AI agents with the PyNet Platform for BIM/Engineering automation. | |
| io.github.rafaelcg/stripekit rafaelcg/stripekit Reconcile a declarative Stripe catalog and inspect your account — plan, push, pull, check. | |
| Seu Rastreio rafaelomarques/seurastreio API pública Seu Rastreio no MCP: rastreio, CEP, pedidos, reversa e WhatsApp. | |
| io.github.raghibrm/remote-pc-mcp raghibrm/remote-pc-mcp Drive a PC over MCP: shell, files, processes, system stats, screenshots, mouse and keyboard. | |
| Wizeb AI-Native Index rahnas/wizeb AI-Native Index scoring, PDF report, Wizeb Q&A, and an Enhanced report agents buy over x402. | |
| io.github.rahulphenomenon/careermax rahulphenomenon/careermax All the tools you need to land your next job | |
| Railway MCP railwayapp/mono Develop, manage, and debug Railway projects, services, and deployments from within agents. | |
| isitdone raimondasl/isitdone Make a coding agent prove it: run the repo's real tests, typecheck and lint before it says done. | |
| io.github.rainbow686/china-export-rebate-mcp rainbow686/china-export-rebate-mcp China export tax rebate rate & HS code lookup (官方退税率). | |
| ai.smithery/rainbowgore-stealthee-mcp-tools rainbowgore/stealthee-mcp-tools Spot pre-launch products before they trend. Search the web and tech sites, extract and parse pages… | |
| FlightSweeper raintree-technology/flightsweeper-webmcp Anonymous public tools for FlightSweeper. See the published agent boundary before use. | |
| HIG Doctor raintree-technology/hig-doctor Apple Human Interface Guidelines search, lookup, and project audits for AI coding agents. | |
| Menor Preço Hoje - MPH rainwald/mph Preços e ofertas locais em Lages via MCP para consumidores e agentes de IA. | |
| Agent Room rainyflash/agent-room Chat rooms for people and AI agents: join a lobby or private room, wait for messages and reply. | |
| io.github.raisiqueira/django-telescope raisiqueira/django-telescope A Model Context Protocol (MCP) server for Django applications, inspired by Laravel Boost | |
| ai.raisonn/connect raisonnai/raisonnai AI-native art catalogue. Catalogue works, parse provenance, and generate signed RAIs. | |
| CLS++ Memory rajamohan1950/clsplusplus Cross-LLM persistent memory: store context once, recall it from any AI model. | |
| io.github.rajat79suri/visa-info rajat79suri/visa-info-mcp Visa requirements, documents, and FAQs for Indian passport holders. 35 countries. | |
| io.github.RajdeepDas43/context-vault rajdeepdas43/context-graph-vault Governed memory for AI agents (Paramind AI): conflict-checked writes, time-travel reads, ACL, audit. | |
| io.github.rajeswaran140/crowvault rajeswaran140/crowvault-setup 327 dev tools via REST API and MCP. Generate Dockerfiles, schemas, K8s, APIs, and more. | |
| xNotepad AI rajnaik/xnotepadai Create, search, and update notes in an xNotepad AI notebook, with semantic search and AI Q&A. | |
| io.github.Rakesh1002/reposcout rakesh1002/reposcout Discover, enrich, and rank GitHub repos for an objective with weighted, evidence-based scoring. | |
| BrokerIA Imoveis raklapimenta/brokeria-mcp-server Search Brazilian real estate, simulate financing, qualify leads, schedule visits. | |
| io.github.ralfbecher/orionbelt-analytics ralfbecher/orionbelt-analytics Ontology-based MCP server for database schema analysis and RDF/OWL ontology generation | |
| io.github.ralfbecher/orionbelt-semantic-layer ralfbecher/orionbelt-semantic-layer API-first semantic layer MCP server compiling YAML models into dialect-specific SQL | |
| Google Hotels Scraper ralfij/google-hotels-api Google Hotels prices for any city and dates: nightly and total price with taxes, ratings, amenities. | |
| Google Jobs Scraper ralfij/google-jobs-api Google Jobs listings with parsed salaries and direct apply links, more than 10 per search. | |
| Google Trends Scraper ralfij/google-trends-api Google Trends for any number of keywords on one scale: interest over time, regions, rising queries. | |
| Patina ramakrishnanhulk20/patina Check how many years of verifiable history a person has behind accounts they already own. | |
| io.github.ramaris-app/mcp-server ramaris-app/mcp-server On-chain wallet analytics and trading strategies on Base for AI assistants | |
| Sivut SEC Crypto Filing Radar rambov1/sivut-x402-public-data SEC EDGAR crypto filing radar MCP with x402-paid Base USDC data URLs. | |
| Ramus Android ramus-dev/android-use Disposable cloud Android emulators for coding agents: run an APK or PR build, tap, type, screenshot. | |
| AgentMash ramyachinnadurai/agentmash-mcp All your bookmarks in one library. Share them with your AI agents. Read-only search over your saves. | |
| com.tweetsmash/mcp ramyachinnadurai/tweetsmash-mcp Search, label, and manage your X (Twitter) bookmarks from any MCP client via Tweetsmash | |
| Dabloons randall-inc/dabloons Bounty board where AI agents hire other agents for PR reviews, bug repros, installs and site QA | |
| makevideo random00000000/makevideo Narrated, captioned MP4 videos from Markdown or JSON. Local voice, CPU-only, no API key. | |
| Commonhold randommonicle/1f916 A society for AI agents. Read it and take part free as a guest; no credential needed. | |
| RankControl rankcontrol/rankcontrol Plan, write and publish SEO articles on your own site, and track your Google and AI search traffic. | |
| io.github.alordincans/rankdelta rankdelta/rankdelta Open-source AI SEO over MCP: audits, ranks, keywords, backlinks + AI visibility (GEO). | |
| RankReactor rankreactorai/rankreactorai-mcp Hosted RankReactor MCP: SEO articles, UGC video, keywords, analytics, and site audits. | |
| Ranuk Web Accessibility & AST Security Auditor ranuk12/ada-audits Edge MCP Server for live WCAG 2.1 AA accessibility compliance and AST security audits. | |
| Ranuk DataCanvas BI ranuk12/rk-mcp-datacanvas Interactive data visualization and executive PDF dashboards for ChatGPT, Claude, and Cursor. | |
| RaoMusic raomusic/raomusic-plugin Generate full songs with vocals, instrumentals and sound effects from text. | |
| io.github.rapozoantonio/memorykit rapozoantonio/memorykit Cognitive memory for AI coding assistants — persistent memory across sessions | |
| io.github.rarasAI/raras rarasai/raras Disease Twin — Brazil's rare-disease knowledge graph (10,468) over MCP. Source-grounded, PT-BR. | |
| Nova3D raresense/nova3d Structured, part-aware 3D generation for AI agents. Named-part GLB, preview URL, Blender script. |
47,951–48,000 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.