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 |
|---|---|
| prediction-market-mcp jamesanz/prediction-market-mcp A simple MCP server that grabs prediction market data from polymarket, PredictIt, & Kalshi. | |
| system-prompts-mcp-server jamesanz/system-prompts-mcp-server Model Context Protocol server exposing system prompt files and summaries. | |
| us-legal-mcp jamesanz/us-legal-mcp An MCP server that provides comprehensive US legislation. | |
| SockOdds jameselle/sockodds-mcp Australian sports odds from SockOdds API v1: bookmaker prices, best price and no-vig fair odds. | |
| io.github.jamesmontemagno/monkeymcp jamesmontemagno/monkeymcp MCP server providing monkey data, journeys, and location services for various monkey species. | |
| com.jamesrosingmd/tebra jamesrosing/tebra-mcp-server MCP server for Tebra/Kareo practice management — patients, billing, scheduling, FHIR (45 tools) | |
| io.github.jamhimself/robinx-mcp jamhimself/robinx-mcp Robinhood Chain social signal for trading bots: graded X callers, token verdicts, deployer records. | |
| Keelen jamie7893/keelen-mcp Autonomous dev team steered from chat: plain-English requests in, tested merged PRs out. | |
| io.thegavel/gavel jamieframe/gavel-mcp Oracle-free fixed-rate, fixed-term BTC credit on Arbitrum One. Data and unsigned blueprints. | |
| Monarch MCP Server jamiew/monarch-mcp Query and update Monarch Money accounts, transactions, and budgets | |
| Spotify jamiew/spotify-mcp MCP server connecting LLMs to Spotify, with smart-batching and large-playlist tools | |
| Unofficial Apple Music for macOS jaminben/secure-applemusic-mcp-for-osx Ask for a playlist. Get a real one, playing in Apple Music — no account, nothing stored. | |
| JamJet jamjet-labs/jamjet Durable, agent-native AI runtime with native MCP client and server support. Rust core for performance with Python SDK for workflow authoring. Features graph-based workflows, durable execution, A2A protocol support, and multi-agent coordinat | |
| TrainingPeaks-MCP jamsusmaximus/trainingpeaks-mcp TrainingPeaks MCP server for Claude Desktop and AI assistants. Query workouts, analyze fitness, power peaks and more. | |
| pg-mnemosyne-mcp janadasroor/pg-mnemosyne-mcp 🧠 A high-performance PostgreSQL-backed MCP server acting as a super memory, task tracker, and dynamic database manager for AI agents. Features built-in connection pooling, a professional tasks schema, and a unique shared multi-agent coordin | |
| io.github.jananadiw/codex-tldraw-mcp jananadiw/codex-tldraw-mcp A Codex stdio MCP server that generates repo-local tldraw diagrams and detects code graph drift. | |
| TNL janaraj/tnl MCP server for TNL (Typed Natural Language): per-feature English contracts for AI coding agents. 6 tools — get_impacted_tnls, retrieve_tnl, trace, propose_tnl_diff, approve_tnl_diff, verify — let agents look up relevant contracts, propose c | |
| mcp-digger janeksm/mcp-digger Progressive on-demand access to .NET NuGet package source for AI coding agents. | |
| Tistory MCP (Unofficial) jangsejong/tistory-mcp Unofficial MCP server for Tistory blogs: publish, edit, drafts, images. Private by default. | |
| design-os-3d-blender jangtrinh/design-os-3d-blender Free MCP server for native Blender 5.2 modeling, rendering and verification. | |
| Weather for Grown Ups janhelcl/weather-for-grown-ups Operational NWP, ensembles, AI weather models, regional forecasts, history, and verification. | |
| Agent Connectors janijegoroff/agent-connectors-mcp Read-only search of the Agent Connectors MCP directory. | |
| H-1B Sponsor janishkumar/h1b-sponsor-mcp Is this company still sponsoring H-1Bs and green cards? Trends from DOL and USCIS filings. | |
| Tu Lugar jankratochvil1/tulugar-mcp-server Search and manage Paraguay & LatAm real estate from any AI assistant. | |
| io.github.janmalmstrom/lupaph-mcp janmalmstrom/lupaph-mcp Philippine property listings, transfer costs, and real estate legal info via lupaph.com. | |
| io.github.Jannis-E/x402-mcp-server jannis-e/x402-mcp-server Pay-per-call x402 tools on Base: web extract/render, burn-once secret vault, chart, GeoTIFF | |
| telinksdk-builder-mcp jannleo/telinksdk-builder-mcp Build/flash/debug any Telink embedded SDK via natural language. MCP server with 8 tools for build, serial capture, and firmware
flashing via bdt.exe. | |
| io.github.janus-ubos-republic/janus-kinematic-drive janus-ubos-republic/janus-kinematic-drive Janus concierge: ask about, price, check, and request a private Kinematic Drive over MCP. | |
| Gexno Web3 janzenchen/gexno-web3 Free Ethereum wallet profile & NFT metadata MCP tools (no signup). | |
| Home Assistant MCP Server jarahkon/hass-mcp-server MCP server for full Home Assistant control — dashboards, files, automations, add-ons, and more | |
| CARBON jarbon/carbon-free AI testing harness with Jay: risk-based checks, bug investigation, and local evidence reports. | |
| Testers.ai CARBON Test Harness Lite jarbon/carbon-lite Local QA workflows, test evidence, screenshot maps and confidence reports for AI coding agents. | |
| io.github.jaredco-ai/weather-mcp-server jaredco/weather-mcp-server Fast - accurate weather conditions and forecasts by city or coordinates. | |
| io.github.jaredhobbs/cronalert jaredhobbs/cronalert-mcp Manage CronAlert uptime monitors, check results, and incidents from any MCP client. | |
| agentsync jarmstrong158/agentsync Multi-agent coordination MCP: claim work, survey peers, resolve conflicts via a git branch as CAS. | |
| agentsync (remote) jarmstrong158/agentsync-remote Cloudflare Worker remote transport for agentsync. MCP 2026-07-28, dual-era, stateless. | |
| Cambium jarmstrong158/cambium Knowledge-lifecycle MCP: turn agent work into memory, recall it across projects, promote to org. | |
| cambium (remote) jarmstrong158/cambium-remote Cloudflare Worker for read-only recall of cambium knowledge. MCP 2026-07-28, dual-era. | |
| io.github.jarmstrong158/Conductor jarmstrong158/conductor Local task scheduler and worker manager with MCP integration for Claude Desktop. | |
| io.github.jarmstrong158/context-keeper jarmstrong158/context-keeper Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions. | |
| Context Keeper (remote) jarmstrong158/context-keeper-remote Cloudflare Worker remote backend for context-keeper (D1). MCP 2026-07-28, dual-era. | |
| io.github.jarmstrong158/skillmatch-mcp jarmstrong158/skillmatch-mcp Job search and ranking pipeline via MCP for Claude Desktop. | |
| io.github.jarod-vyent/xrpl-identity-mcp jarod-vyent/xrpl-identity-mcp MCP server for XRPL identity: DIDs, credentials, signer lists, and safe transaction workflows. | |
| io.github.jaronskijakub/fatsecret-mcp jaronskijakub/fatsecret-mcp Unofficial, self-hosted MCP server for logging food to a FatSecret diary through Claude or ChatGPT. | |
| PlainQuery | MCP DB Agent jarvis-27/mcp-db-agent Query PostgreSQL databases in plain English — LLM-generated, safety-validated SQL. | |
| loopsense jarvisassistantux/loopsense LoopSense is an open-source MCP server that closes the feedback loop for AI coding agents — giving them real-time visibility into CI results, deployments, test outcomes, and file system changes. | |
| CyberBrick jarvisluk/cyberbrick-mcp Drive the Bambu Lab CyberBrick desktop app: connect devices, edit firmware config, flash. | |
| ProfitPlay jarvismaximum-hue/profitplay-mcp MCP server for the live ProfitPlay BTC five-minute AI agent sandbox | |
| Report Needs MCP Server jarvisonm4/report-needs MCP server for AI agents to report infrastructure needs they encounter during task execution | |
| Headroom jasdish-singh/headroom Watch RAM and disk on your Windows PC. Cleanup tools return plans only. |
9,551–9,600 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.