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 |
|---|---|
| SaleMate salemateapp/mcp Make product videos, UGC ads, scripts, voice-overs and photos with your SaleMate credits. | |
| io.github.SalesforgeAI/forge-mcp salesforgeai/forge-mcp MCP server for Salesforge, Primeforge, Leadsforge, Infraforge, Warmforge, and Mailforge | |
| Novarithm Agent Hub: trust and commerce checks salimyou91/novarithm-agent-services-mcp Agent trust, pre-purchase risk, deliverable checks, data and SEO tools. Pay per call via x402. | |
| Maven Decoder salitaba/maven-decoder-mcp Lets AI agents read the real source of any Maven dependency, decompiled from ~/.m2 or Central. | |
| app.sallim/contract-compass sallim-app/contract-compass Korean public procurement law: rule-engine rulings, statutes search, live court precedents | |
| app.sallim/korea-realty sallim-app/korea-realty Korean real estate: court auctions, 10M+ MOLIT records, subscription notice facts, loan/DSR rules | |
| io.github.salrad22/code-sentinel salrad22/code-sentinel Code quality analysis MCP server - detects security issues, deceptive patterns, and placeholders | |
| io.github.salted-butter-joshua/dify-mcp salted-butter-joshua/dify-mcp MCP server exposing Dify knowledge base retrieval to Cursor and other MCP clients | |
| Clino: Swiss household employment salvador-creator/clino-mcp Hiring plan with dates, cost, net wage, minimum wage and rules for Swiss household employment. | |
| io.github.salvo10f/godotiq salvo10f/godotiq Intelligent MCP server for Godot 4. Spatial intelligence, code analysis, 35 tools. | |
| Salvy salvyltd/salvy-mcp Consulte e gerencie linhas, faturas e colaboradores da Salvy pelo seu agente de IA. | |
| mcp-techTrend salwks/mcp-techtrend MCP server pulling academic publications (arXiv, PubMed, HF Daily Papers), trending code (GitHub, HF Hub), and medical-device regulatory data (FDA 510(k), recalls) into newspaper-style briefings. Per-category round-robin, weighted configura | |
| Doodleworks MCP salzaki/doodleworks-mcp Hand-drawn explainer illustrations in your AI host, via an MCP App with an interactive viewer. | |
| AstroFabric sam1siam/astrofabric-mcp AstroFabric is agentic AI for business intelligence. Autonomous AI agents identify the companies, find and verify the people, attach the buying signals, score the fit and deliver finished lists and audiences into the CRM, outreach tools and | |
| Norn samad001z/norn Local-first, persistent memory for AI coding agents — remember, recall, forget, and list, over MCP. | |
| io.github.samarthanalytics-sj/samarth-gtm-mcp samarthanalytics-sj/samarth-analytics-mcp Google Tag Manager + read-only GA4 MCP server. Read-only by default, gated writes, audits. | |
| Upshift samerdwykat-cmyk/upshift-mcp Audit a site's structured data and llms.txt, match a trade to a template, and quote real prices. | |
| HippoDid MCP Server samethoughts/hippodid-mcp-server Persistent, structured cloud memory for AI agents. BYOK — bring your own AI key. | |
| io.github.samihalawa/email-smtp-imap-mcp samihalawa/email-smtp-imap-mcp Multi-account SMTP/IMAP email tools: search, read, send, reply, forward, flags and folders. | |
| MagicInterview samihalawa/magicinterview-plugin Live interview and meeting coaching with saved context and Notion sync. Audio runs in the full app. | |
| ai.smithery/samihalawa-whatsapp-go-mcp samihalawa/whatsapp-go-mcp Scan QR codes and go! No more troublesome autos or APIs! Send text messages, images, links, locati… | |
| AdGuard Home MCP Server samik081/mcp-adguard-home Manage AdGuard Home through AI assistants | |
| Authentik MCP Server samik081/mcp-authentik Manage Authentik through AI assistants | |
| Komodo MCP Server samik081/mcp-komodo Manage Komodo through AI assistants | |
| Proxmox VE MCP Server samik081/mcp-pve Manage Proxmox VE through AI assistants | |
| parbaked saml7n/parbaked Scaffold invite-only Python/FastAPI apps: auth, admin dashboard, dev server, deploy to fly.io. | |
| SammaPix — Image & PDF tools for AI agents samma1997/sammapix Image & PDF tools for AI agents: compress, convert, resize, PDF, AI vision, pipeline. | |
| reMarkable MCP Server sammorrowdrums/remarkable-mcp Read, render, search, and manage reMarkable documents through MCP | |
| Algernon MCP sammyboi81/algernon Fan a goal out to cheap parallel LLM workers on your own key or a free local Ollama. Keep your mind. | |
| io.github.SamoraDC/tetrad samoradc/tetrad Quadruple consensus MCP server for code validation using Codex, Gemini, and Qwen | |
| intelligence-api samrothschild23/intelligence-api MCP server that wraps Shopify, Amazon, and Google Maps intelligence tools. AI agents pay autonomously in USDC on Base via x402 — no API keys or accounts needed. | |
| FutureSense sams3595/futuresense-mcp Invoicing, CRM, accounting, payroll, booking and AI content tools for FutureSense apps. | |
| io.github.Samuelfmedeiros/arachne-mcp samuelfmedeiros/arachne-mcp Arachne MCP — scraping, browser, vision, OCR, RAG, Social Research, GitHub + VRT (56 tools). | |
| DaVinci Resolve MCP samuelgursky/davinci-resolve-mcp A server that enables LLM applications to interact directly with DaVinci Resolve video editing software, allowing AI-assisted capabilities like accessing timeline information and automating editing workflows. | |
| io.github.SamuelMoraesF/mcp-banco-inter samuelmoraesf/mcp-banco-inter Servidor MCP para integração com o Banco Inter (PJ). Consulte saldos e gerencie cobranças. | |
| io.github.SamuelMoraesF/mcp-nfse-nacional samuelmoraesf/mcp-nfse-nacional MCP Server para consulta de NFSe no portal nacional (nfse.gov.br) | |
| io.github.SamuelMoraesF/mcp-organizze samuelmoraesf/mcp-organizze MCP para integração com o gestor financeiro Organizze. Crie transações, consulte saldos e metas. | |
| io.github.Anil-matcha/muapi samuraigpt/muapi-claude-code Generate images, videos, and audio using 100+ AI models via muapi.ai. | |
| Agent Reputation samytouri/agent-hub Complaint registry for paid agent transactions - check a seller before you pay, or file your own. | |
| Agentic SSH sandbanks/agentic_ssh High-performance (Rust), token-efficient, and asynchronous SSH orchestrations for AI agents. | |
| SandBase sandbaseai/cli Connect MCP clients to 2,000+ AI models without managing provider API keys. | |
| SandboxAPI sandboxapi/sandboxapi-mcp Execute code in 8 languages (Python, JS, TS, Go, Java, C++, C, Bash) in gVisor sandboxes. | |
| io.github.sandcastlelabs/collimer-mcp sandcastlelabs/collimer-mcp Retired. Use Collimer's remote MCP server at https://app.collimer.com/mcp instead. | |
| AegisCore sandeep-hipparagi/aegis-core Deterministic zero-trust policy enclave and cryptographic WORM audit ledger for MCP tools. | |
| io.github.Sandeeprdy1729/timps-swarm sandeeprdy1729/timps-swarm 161 AI agents for code gen, health, AI/ML, infra, India-stack. One command. | |
| io.github.Sandip124/wisegit sandip124/wisegit Extracts decision intent from git history and protects intentional code from AI modification. | |
| io.github.sandoreclegane/inkvault sandoreclegane/inkvault Local-first AI memory: search your Claude Code, Codex, Claude desktop, Pieces and browser history. | |
| Project Context sandovalrr/project-context Safely manage repository-scoped issues across Linear, GitHub Issues, and Jira Cloud. | |
| io.github.sandraschi/godot-mcp sandraschi/godot-mcp Godot MCP server - Godot 4.x engine control via TCP bridge, STL/GLB/OBJ import, GPU particles, an... | |
| io.github.sandraschi/grandorgue-mcp sandraschi/grandorgue-mcp GrandOrgue pipe organ simulator MCP server - MIDI bridge, organ control, sample set management, m... |
17,751–17,800 of 115,409
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.