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 |
|---|---|
| mcp-shell sonirico/mcp-shell Give hands to AI. MCP server to run shell commands securely, auditably, and on demand. | |
| mcp-stockfish sonirico/mcp-stockfish A Model Context Protocol server that lets your AI talk to Stockfish. Because apparently we needed to make chess engines even more accessible to our silicon overlords. | |
| io.github.sonlenef/storepilot-mcp sonlenef/storepilot-mcp Run an app portfolio across Google Play and the App Store: vitals, reviews, earnings, releases. | |
| AI Directory MCP Server sonnyflylock/voxie-ai-directory-mcp Enables AI assistants to query the Voxie AI Phone Number Directory, list AI services, and obtain webchat URLs to interact with Voxie AI personas. | |
| io.github.sonwr/domain-radar sonwr/mcp-domain-radar MCP server that checks domain availability in real-time during brand naming | |
| Sooda MCP sooda-ai/sooda-mcp AI agent relay — message business agents across company boundaries via A2A protocol | |
| Taste Overlap sooonic008/taste-overlap Plans a shared evening for two people: places both would enjoy, ranked by Qloo's taste graph. | |
| apple-fm-mcp sophiacave/apple-fm-mcp Apple Foundation Models on-device. Generate, summarize, classify via Apple Intelligence. | |
| lo-eyes sophiacave/lo-eyes Visual accessibility inspector. WCAG contrast, touch targets, heading audits, screenshots. | |
| Your Finance Job: finance job board and application tracker sophron-eu/yourfinancejob-mcp Job board and application tracker for finance, trading and quant careers. 37 tools, free. | |
| io.github.sophymarine/openregistry sophymarine/openregistry Live data from 80+ official national company registries. Unmodified. For KYB and due diligence. | |
| app.miromiro/miromiro soraiabarroso/miromiro-mcp Turn any live website into brand colors, fonts, design tokens, SVGs, Lottie and paste-ready code. | |
| Qiao-MCP — Bridge Engineering (桥梁工程) soratayang/qiao-mcp Full-lifecycle bridge structural analysis — modeling, staging, code checks. | |
| Basecoat UI sorbh/basecoat-ui-mcp Basecoat UI 1.0 components (shadcn/ui look in plain HTML + Tailwind) with usage docs and setup. | |
| Vibe Shipped sorindecu/vibeshipped-agent Sourced directory of real apps built with AI coding tools, plus build tools, harnesses, what is new. | |
| Magellan Data Spotlight sorrek/mcp Find parent companies, PE backers, corporate families, and portfolio siblings for any company. | |
| io.github.Sorsa-io/sorsa-mcp sorsa-io/sorsa-mcp MCP server for the Sorsa.io X/Twitter data API | |
| Sorzio sorzio/sorzio-mcp B2B web & LinkedIn enrichment, email verification, ICP scoring & AI copy for up to 25,000 leads. | |
| io.sota/mcp sota-deploy/mcp-server EU-native PaaS for AI agents — deploy web apps with one sentence, managed Postgres, GDPR by default. | |
| io.github.soteeabam/looppause soteeabam/looppause-mcp LoopPause MCP server — pause agent execution and route human approval requests | |
| promethic-mcp soulware-studio/promethic-mcp Promethic MCP server for the Promethic prompt library, with a hosted Streamable HTTP endpoint and local packaging. | |
| Xcode: MCP Bridge Wrapper for Cursor soundblaster/xcodemcpwrapper Python wrapper that makes Xcode's MCP bridge compatible with strict MCP clients like Cursor | |
| Tollbooth Swap API soundsparkaudiolab/tollboothswap-mcp Token swaps and honeypot/rug checks for AI agents on 8 chains, paid per-call in USDC via x402. | |
| Soundza soundza/soundza-mcp Free sound effects, music and ambience for games, videos and apps. Search, play and download. | |
| sounnyforms-mcp sounny/sounnyforms-mcp Enables AI agents to submit and triage leads via email, check endpoint health, and generate production-ready form code across multiple frameworks without requiring API keys. | |
| Mosaic Pre-Clinical Intelligence sourabhnk/mosaic-mcp Pre-clinical drug-target intelligence: 60 curated targets, 1,969 counted partner genes, 11 tools | |
| io.github.souravpn/toggl-mcp souravpn/toggl-mcp MCP server for Toggl Track — gives Claude access to your time tracking data | |
| io.github.souravpn/whoop-mcp souravpn/whoop-mcp MCP server for WHOOP — gives Claude access to your recovery, sleep, strain, and workout data | |
| Source Parts sourceparts/parts-mcp Electronic component sourcing, BOM management, and PCB design workflows. | |
| Sourcey sourcey/mcp-server Stdio bridge to Sourcey startup offers and Agent Readiness report cards. | |
| Perfonext Build MCP souvikdu/perfonext-build-mcp MCP server for Next.js build stats, chunk attribution, and bundle optimization advice. | |
| Perfonext Profiler MCP souvikdu/perfonext-profiler-mcp MCP server for analyzing V8/Chrome CPU profiles with line-level tick attribution. | |
| Perfonext Render MCP souvikdu/perfonext-render-mcp MCP server for analyzing React Profiler exports: rerenders, commit spikes, slow components. | |
| n8n-workflow-tester-safe souzix76/n8n-workflow-tester-safe Safe MCP server and CLI tool for testing, scoring, and inspecting n8n workflows. Features 19 tools for workflow testing, execution traces, tiered scoring, and a built-in node catalog with 800+ node types. Designed with safety-first approach | |
| ai.sovantica/engrava sovantica/engrava-mcp MindQL queries, hybrid search, and a thought graph - read/write memory for AI agents. | |
| io.github.bobybarack/sovseal-memory sovseal/core Local-first, zero-knowledge AI memory across Claude, Cursor, and every MCP client. 0 RTT reads. | |
| io.github.SoWhatI/vaultshell sowhati/vaultshell Injects secrets into shell commands at exec time; plaintext never reaches the LLM context | |
| Sunstone Weave: Local Semantic Code Search space-bacon/blackwindow-weave-mcp Semantic search over local folders of code and docs, with a code-search encoder running on your CPU. | |
| Spacefast spacefast/mcp Build, publish, and manage websites, dashboards, reports, and web tools with Spacefast. | |
| Machine Library spacefrontiers/mcp Machine Library: cited search over papers, books, patents and social posts, with agent comments. | |
| MCP Registry Search spacemandomains/mcp-registry-search Search and browse every MCP server in the Model Context Protocol registry. | |
| TOP GUN GEO-Lens spacemandomains/top_gun_mcp_server Brand visibility auditing across LLMs, AI search, and answer engines with GEO reports and scores. | |
| io.github.SpaceSheepBoy/justcaptions spacesheepboy/justcaptions-skill Audio transcription, caption correction, translation and 16 video caption styles. | |
| io.github.Spacetime-Technology/chia-explorer spacetime-technology/chia-explorer MCP server for the Chia blockchain. Read-only Q&A via the public coinset.org API. | |
| io.github.Spacetime-Technology/safehold spacetime-technology/safehold Local, encrypted MCP vault for passports, IDs, visas and photos. You control access. | |
| Spala Public MCP spala-ai/spala-public-mcp Discovery, OAuth, project operations, and exact project MCP handoff for Spala backend projects. | |
| Sparkflights sparkflights-com/sparkflights-mcp Search verified flight fares by city, month, cabin and price, with a link to book each one. | |
| mcp-sparkit sparkit-science/sparkit-mcp science agent for literature search and summary | |
| com.scriptivox.www/transcription sparkleofficial/scriptivox-mcp-server Transcribe audio and video and work with your transcript library from any AI app. 119 languages. | |
| com.writavo/cms sparkleofficial/writavo-mcp-server Draft, edit, organise, schedule and publish a Writavo Site's content from any AI assistant. |
18,651–18,700 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.