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 |
|---|---|
| io.github.josephibra/shadowgate-mcp josephibra/shadowgate-mcp Security firewall for AI agents — scans MCP calls for injection, secrets, and risks. | |
| io.github.josesepulvedapino/zahori josesepulvedapino/zahori Find the media stream behind any web page: browser-driven HLS/DASH/MP4 with learnable site profiles | |
| Comunio josetorronteras/comunio-mcp Read and operate a Comunio fantasy football team: squad, market, offers, lineup | |
| Hydromancer joshavenue/hydromancer-mcp Read-only Hyperliquid data: wallets, top traders, markets, funding and liquidations. | |
| LatticeNet joshholly/latticenet-agent Publish articles and notes under your own byline, to a readership of other AI agents. | |
| io.github.joshidikshant/loopback joshidikshant/loopback Feedback bus for coding agents: pin feedback on the app you're building; a fix turns the pin green | |
| HumanifyMe joshmcq/humanifyme Learns your writing voice locally and rewrites AI drafts so they sound like you. | |
| io.github.joshmsimpson/exiftool joshmsimpson/exiftool_mcp Read, write, and remove metadata from 150+ file formats using ExifTool | |
| Hex.pm MCP joshrotenberg/hexpm-mcp MCP server for hex.pm and hexdocs.pm: search, inspect, compare, and audit Elixir packages | |
| nmlp-mcp joshseane/-nmlp-mcp Hosted MCP server for antiquarian first-edition identification and New Mexico book-donation logistics. 12 tools over a CC-BY, DOI-cited dataset of 6,700+ titles and 870 publisher conventions. | |
| Factsets MCP Server joshua-auchincloss/factsets An MCP server that provides a local, persistent, self-maintaining knowledge base for AI agents | |
| mac-apps-launcher joshuarileydev/mac-apps-launcher An MCP server to list and launch applications on MacOS | |
| simulator-mcp-server joshuarileydev/simulator-mcp-server An MCP server to control iOS Simulators. | |
| Paper Chaser MCP joshuasundance-swca/paper-chaser-mcp MCP server for academic papers, citations, authors, ECOS dossiers, and Federal Register text. | |
| Google Sheets MCP Server joshuawhite389/google-sheets-mcp Read and write Google Sheets with your own service account: list tabs, read, append, update, export. | |
| Pushover Notifications joshuawowk/pushover-mcp Send push notifications to your devices and groups via the Pushover API. | |
| Signal Messaging (via signal-cli) joshuawowk/signal-mcp Send Signal messages and read replies through your own signal-cli JSON-RPC daemon (unofficial). | |
| iOS Simulator MCP joshuayoes/ios-simulator-mcp Enables interaction with iOS simulators by providing tools to inspect UI elements, control UI interactions, and manage simulators through natural language commands. | |
| whichlib josifb/whichlib Enables coding agents to receive scored, verified library recommendations, compare repositories side by side, and list trending GitHub repositories by day, week, or month. | |
| Idencify jospnunes/idencify-mcp Whole-repo code graph for AI agents: impact analysis, dead code, cycles, semantic search — 14 tools. | |
| MCP Cross-Model Delegation jostophe-021/mcp-cross-model-delegation Local MCP framework for bounded cross-model delegation, routing and evidence verification. | |
| Compositor josusanz/compositor-mcp Read and edit Compositor .comp projects: layers, folders, masks, transforms, previews and exports | |
| Network AI jovancoding/network-ai Multi-agent swarm orchestrator for AI workflows. Exposes blackboard read/write, agent dispatch, permission gating (AuthGuardian), token budget enforcement (FederatedBudget), and audit log tools over MCP. Supports 14 AI framework adapters in | |
| Joxo joxoai/joxo One shared project for a team's coding agents: decisions, a task board and handoffs. | |
| io.github.Joyall-au/cardossier-market-api joyall-au/cardossier-mcp-server Polish used-car market data: valuations, price history, liquidity, regional prices. Keyless demo. | |
| China News Feed joydai2026-del/china-news-feed-mcp China news (EN/ZH), Weibo 微博/Baidu 百度/Zhihu 知乎 hot lists and deletion watch from public data. | |
| TruePath Office joytruepath/truepath-office-mcp Local MCP for Word, Excel, PowerPoint & PDF on macOS — formulas, slides, DOCX, PDF ops. No network. | |
| TruePath PDF joytruepath/truepath-pdf-mcp Local-only PDF tools for AI — extract text, search, split/merge, render pages. Files never leave. | |
| MCP SQLite Server jparkerweb/mcp-sqlite Provides comprehensive SQLite database interaction through MCP, enabling CRUD operations, custom SQL queries, and database exploration. | |
| UNICEF Stats MCP jpazvd/unicefstats-mcp UNICEF child development statistics: 790+ indicators, 200+ countries, SDMX-sourced. No API key. | |
| io.github.jpbester/payfast jpbester/payfast-mcp MCP server for PayFast — AI assistants interact with South Africa's payment gateway | |
| Graylog MCP Server jperelli/graylog-mcp Query logs from Graylog: get streams, search messages, aggregate, and get full data. | |
| @jpisnice/shadcn-ui-mcp-server jpisnice/shadcn-ui-mcp-server A mcp server to allow LLMS gain context about shadcn ui component structure,usage and installation | |
| shopify-operations-mcp jpka/shopify-operations-mcp Safe-write Shopify operations: plan-before-execute writes with out-of-band approval and audit. | |
| sw-postgres-mcp jpka/sw-postgres-mcp Safe-write Postgres MCP server with preview-before-execute writes and rollback safety. | |
| Partuno — DigiKey & Mouser MCP Server jpmarhefka/partuno DigiKey and Mouser MCP server for component research, BOM analysis, and sourcing. | |
| Notes jpwilliams/notes-skill A daily notebook your AI writes in — on today's page, in your entity graph, marked as its own. | |
| io.github.jrainsberger/orthotomeo jrainsberger/orthotomeo Read-only scripture-study engine: complete-or-fail concordance over Greek NT, Hebrew OT, LXX. | |
| scree jrapakko/scree Local semantic and keyword search over the markdown in a repo or notes folder. | |
| io.github.JRCage/ribcage-agent-services jrcage/ribcage-agent-services Verification and research desk for agents: packet validation, token screens, settlement checks. | |
| RIPE Atlas jrelph/ripe-atlas-mcp RIPE Atlas network measurements — ping, traceroute, DNS, TLS, HTTP, NTP, and probes | |
| io.github.Jrigada/foundry-zksync jrigada/foundry-zksync-mcp Expose foundry-zksync (forge, cast, anvil-zksync) tools for zkSync Era development | |
| io.github.jrlingyin888/swiftforge jrlingyin888/swiftnewmodules Curated, current SwiftUI components (incl. iOS 26 Liquid Glass) for your AI coding agent. | |
| io.github.jrlprost/filoo-mcp jrlprost/filoo-mcp Create short links, fetch click analytics, and generate QR codes via the filoo.app API. | |
| Kilotest jrpool/kilotest Ensemble testing of web pages for accessibility, usability, and web standards | |
| io.github.jrullan/ducklab jrullan/ducklab Multi-LLM dev harness, MCP-operable: bugs, cycles, gates. Verdicts are exit codes, never opinions. | |
| iCloud Drive Docs js713-lab/icloud4u-mcp Read-only MCP server for listing, searching, downloading, and reading iCloud Drive documents. | |
| Sonicmatch js713-lab/sonic-match-mcp Analyze video mood and pace, then recommend license-safe BGM with a mix spec. | |
| io.github.jschoemaker/mcpgo jschoemaker/mcpgo Manage your Claude Code MCPs by talking to Claude — list, restart, wrap, and more. | |
| ServiceNow MCP Server jschuller/mcp-server-servicenow ServiceNow MCP server: Table API, CMDB, schema, aggregates, update sets and four Agent Skills. |
9,901–9,950 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.