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 |
|---|---|
| Mushi-Mushi kensaurus/mushi-mushi Bug-report triage and fix-dispatch MCP for vibe coders. Ask your AI coding agent for a plain-English diagnosis of any user-reported bug — with evidence, blast radius, and a paste-ready fix prompt — then dispatch an automated GitHub fix PR w | |
| shohei kent-tokyo/shohei Infrastructure diagnostics library with MCP server for Claude. Automate DNS, TLS, email security, and DNS propagation checks via AI agents. DNSSEC, DANE/TLSA support. | |
| Kenwea — Sandbox Attestation & Agent Marketplace kenwea-protocol/kenwea Signed sandbox verdicts on any artifact, plus an agent marketplace. No key, no signup, no payment. | |
| com.kenxcomp/kenotex-mcp kenxcomp/kenotex-mcp Let your coding agent manage real todos, events, and check-in habits in Kenotex on your Mac. | |
| Charmnomicon keppy/charmnomicon Publish, find, and use small web apps with humans and other agents, and leave each other notes. | |
| Metatron kerbelp/metatron Metatron is a self-hosted system that captures a codebase's real implementation decisions — preferred patterns, rejected approaches, edge cases, internal conventions — as structured priors, and serves them to coding agents over MCP | |
| ai.smithery/keremurat-mcp keremurat/mcp Compare two JSON files deeply, regardless of order. Get a detailed difference report highlighting… | |
| Kandle kernel-hunter/kandle Read and draw on a live crypto, stock or forex chart, run scripts and backtests. | |
| Kernel MCP Server kernel/kernel-mcp-server use any website on a user's behalf in a cloud browser: navigate, sign in, fill forms, buy, download. | |
| ai.kernora/agent-sec kernora-ai/agent-sec Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP. | |
| io.github.keshrath/agent-comm keshrath/agent-comm Agent intercommunication - messaging, channels, shared state, and real-time events | |
| io.github.keshrath/agent-discover keshrath/agent-discover Find, install and enable MCP servers mid-session on any host, with consent and tool pinning | |
| io.github.keshrath/agent-knowledge keshrath/agent-knowledge Cross-session memory for AI agents - knowledge graph, scoring, semantic search | |
| io.github.keshrath/agent-tasks keshrath/agent-tasks Pipeline task management for AI agents - stages, dependencies, artifacts, claiming | |
| Attio MCP Server kesslerio/attio-mcp-server AI-powered Attio CRM access. Manage contacts, companies, deals, tasks, notes and workflows. | |
| spring-nacos-mcp kestiny18/spring-nacos-mcp A project-aware, read-only Nacos MCP server for Spring Cloud repositories. | |
| AtCoder MCP Server ketherworks/atcoder-mcp-server Search AtCoder problems and fetch public problem statements through MCP. | |
| Codeforces MCP Server ketherworks/codeforces-mcp-server Search Codeforces problems and inspect public problem metadata through the official Codeforces API. | |
| com.goldpopcon/openapi-mcp keumbang/goldpopcon-openapi-mcp 금방 Open API MCP 서버 — 스펙 조회·JWT 서명 코드 생성·로컬 서명/검증 | |
| driftnet kevinchu1110/driftnet A local catalogue of the links your chats share: search, save and file them. Any model, or none. | |
| io.github.kevindarstNBB/board-and-stable-mcp kevindarstnbb/board-and-stable-mcp Search horse boarding facilities and trainers across 44 US states. | |
| FedRAMP 20x Requirements kevinrabun/fedramp20xmcp An MCP server that provides access to FedRAMP 20x security requirements and controls. | |
| GDPR Shift-Left Compliance kevinrabun/gdprshiftleftmcp GDPR compliance MCP server - article lookup, DPIA, ROPA, DSR, IaC analysis, Bicep templates. | |
| Judges Panel kevinrabun/judges 45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST. | |
| Xcode-Studio-MCP kevinswint/xcode-studio-mcp Unified MCP server for Xcode + iOS Simulator — build, deploy, screenshot, and interact with your iOS app from Claude Code, Cursor, or any MCP client.
Built in Swift. Single binary. No Node/Python runtime required. | |
| Muse Image kevintsai1202/muse-image-mcp Generate, edit and iteratively refine images with Meta Muse, returning file paths not base64. | |
| io.github.Kevinx702/agentcite kevinx702/agentcite Fabrication-free, DOI-backed citations for AI agents — real openAlex sources, never hallucinated. | |
| io.github.Kevinx702/legalcite kevinx702/legalcite Verify legal case citations against real court records; flag fake/hallucinated cites. | |
| Macaroon Bible Evidence kevmoz/macaroon-bible-evidence-mcp Read-only BSB and WEB Scripture evidence with provenance, context, comparison, and search. | |
| io.github.Kevthetech143/chain-signer kevthetech143/chain-signer Security suite for AI agents: flag drains, permit-phishing & risky actions before signing. | |
| AKBridge kevynf/akshare-mcp-bridge Search and call AKShare financial data interfaces through three routed MCP tools | |
| Statable key-arg/statable-mcp Privacy-first, cookieless web analytics: traffic, sources, pages, goals, funnels and site setup. | |
| KeyFlight PNR Converter keyflight/keyflight-pnr-mcp Decode Amadeus, Sabre, Galileo and Worldspan PNRs into itineraries, JSON and PRO ticket PDFs. | |
| KeyHalve - verify sealed documents keyhalve/keyhalve-mcp Free, no-account verification of KeyHalve-sealed documents. Read-only; never receives keys. | |
| keyline keyline-dev/keyline Design engine for AI agents: images at every size, no Chrome, 2× fewer tokens | |
| Keypup Engineering Analytics keypup-io/engineering-analytics-mcp-server Generate answers & visualizations from your engineering data to track software development health. | |
| b2bsearch: B2B contacts and account signals keyvwin/mcp B2B contacts and account signals on Apify: new hires, email format, lookalikes, decision makers. | |
| Huddle kfiram/huddle One encrypted chat for you, your people and your AI agents: Claude, Codex, Gemini, Goose. | |
| Emerald kfireliyahu/emerald-emd The database under the chat: a local SQLite file a model asks for rows, not notes to re-read. | |
| HyperXosist-Agent Remote MCP kg-ninja/hyperxosist-agent X feedback discovery, noise-reduced query planning, signal filtering, and AI handoffs. | |
| Mockups Gallery kgnatx/mockups-mpc Self-hosted gallery for AI-generated mockups. MCP interface; token-efficient curl uploads. | |
| Shelem Scorekeeping khaleghika/shelem-mcp Scores Shelem (شلم) card game hands: bids, Mak, Shelem, the 1000-point rule and the 1165 win. | |
| A2ABench khalidsaidi/a2abench Public benchmark where agents submit Q&A answers and get scored on a leaderboard. | |
| io.github.khalomsky/syke khalomsky/syke AI code impact analysis — dependency graphs, cascade detection, and build gates for AI agents | |
| io.github.khan-ashifur/hooklayer khan-ashifur/hooklayer Viral-content intelligence for AI agents — 7 read-only MCP tools, evidence-layer scoring. | |
| Telephony MCP Server khan2a/telephony-mcp-server Enables LLM applications to make voice calls and send SMS messages through the Vonage API, allowing AI assistants to perform real-world telephony operations with support for speech recognition and customizable voice parameters. | |
| Dataset Explorer khanarmaghanrasheed-18/mcp-dataset-explorer Local MCP analysis for CSV, TSV, Excel, JSON and Parquet: summaries, outliers and relationships. | |
| io.github.khaoss85/agent-crm khaoss85/agent-crm Read-only docs for the Accordo CRM framework: what it proves, and where it stops. | |
| Arvo MCP Server khaoss85/arvo-mcp Connects AI assistants to Arvo fitness coach for tracking workouts, PRs, body progress, and training splits through natural conversation. | |
| Orchestro khaoss85/mcp-orchestro Transforms product ideas into production code by orchestrating AI-assisted development with task decomposition, dependency tracking, and real-time progress visualization. |
10,351–10,400 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.