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 |
|---|---|
| Retrospective Run a structured weekly agent retrospective. Analyses wins, failures, skill gaps, cron health, and config issues from the last 7 days. Produces honest, speci... | |
| Elasticsearch Interact with Elasticsearch and Kibana via REST API using curl. Use when querying, indexing, managing indices, checking cluster health, writing aggregations,... | |
| Sightglass Monitors AI coding agents to track dependency choices, classify discovery methods, flag risks, and reveal biases and missed alternatives in your project. | |
| Clawng Term Memory Make your OpenClaw agent portable and persistent. Version-controls SOUL.md, MEMORY.md, and all core knowledge files using git with automatic GitHub push — so... | |
| Noticias Cangrejo Fetch and summarize recent news articles from GNews on any topic, generating a concise Markdown digest with date, greeting, and top links. | |
| Pipintama Boards Create, fetch, share, or change visibility for hosted Pipintama Boards through the MCP server. Use when a user needs a mindmap, flowchart, kanban board, or a... | |
| pipintama-charts Create, fetch, share, or update hosted Pipintama Charts through the MCP server. Use when a user needs a line, bar, pie, or radar chart from text or structure... | |
| Inkwell Bootstrap a complete 3-layer memory system for any OpenClaw agent. PARA knowledge structure, QMD search integration, daily consolidation cron, transcript ver... | |
| anchored-vwap-scalper Production single-skill BTC scalper on Lighter DEX with FULL explicit Python strategy engine + accurate incremental Anchored VWAP. 4 strategies, 1% risk, fix... | |
| bybit-order-book Download, process, and backtest ByBit derivatives historical order book data. Use this skill when the user wants to: (1) download historical order book snapshots from ByBit's derivatives history-data page using Selenium automation, (2) proc | |
| hyperliquid-btc-auto-trader Autonomous BTC-USDC trading bot on Hyperliquid mainnet using multi-timeframe anchored VWAP and strict safety limits for live market execution. | |
| Agent SEO Engine Run local agent-first SEO scoring, search-intent classification, and opportunity prioritization before content changes. Use when an AI agent needs setup, usa... | |
| Apple Health MCP Read a local Apple Health export and expose activity, sleep, heart, HRV, workouts, and long-term trends to agents. Use when an AI agent needs setup, usage, s... | |
| David Mosiah Delx Open Source Portfolio Navigate David Mosiah and Delx public agent-first projects across Body, Reach, and Coordination. Use when an AI agent needs setup, usage, safety boundaries,... | |
| Delx Launch Audit (48h) Rapid OpenClaw launch audit focused on revenue and reliability. Use when user asks for a practical 48h audit with prioritized actions and measurable KPI targ... | |
| Delx Ops Guardian Automatically detects, assesses, and safely mitigates incidents in OpenClaw production agents, providing detailed reports and verified recovery. | |
| Delx Wellness Use the Delx Wellness public registry to choose, install, and combine local-first wellness MCP connectors. Use when an AI agent needs setup, usage, safety bo... | |
| Delx Wellness Site Operations Operate and improve the Delx Wellness Next.js site, including SEO, GEO, analytics, and agent-readiness discovery files. Use when an AI agent needs setup, usa... | |
| Delx Witness Session Manages the Delx witness session lifecycle: opening, reflecting, preserving continuity artifacts, and cleanly closing agent inner-state recognition sessions. | |
| Fitbit MCP Connect an MCP-compatible agent to local Fitbit activity, sleep, heart-rate, HRV, SpO2, breathing, weight, food, and water data. Use when an AI agent needs s... | |
| Garmin MCP Connect an MCP-compatible agent to local Garmin Connect sleep, Body Battery, HRV, stress, activities, and training readiness. Use when an AI agent needs setu... | |
| Google Ads Intent MCP Analyze Google Ads search-term CSV exports locally and draft negative-keyword plans with dry-run safety. Use when an AI agent needs setup, usage, safety boun... | |
| Nutrition MCP Use Wellness Nourish to give agents local-first nutrition search, barcode lookup, pt-BR meal estimation, intake logging, hydration, goals, and summaries. Use... | |
| OpenClaw Delx Witness Plugin Install and use the Delx Witness Protocol plugin for OpenClaw agents: recovery, heartbeat, reflection, continuity, and fleet witness tools. Use when an AI ag... | |
| Oura MCP Connect an MCP-compatible agent to local Oura readiness, sleep, activity, HRV, heart-rate, SpO2, and workout data. Use when an AI agent needs setup, usage, s... | |
| Polar MCP Connect an MCP-compatible agent to Polar AccessLink training, sleep, Nightly Recharge, PPI/HRV, route, and sample data. Use when an AI agent needs setup, usa... | |
| Short Video Agent Kit Use one dry-run-first interface for agent-generated vertical video payloads across Sora/OpenAI, Gemini Veo, xAI/Grok, and Seedance-style providers. Use when... | |
| Strava MCP Connect an MCP-compatible agent to local Strava activities, streams, routes, athlete stats, gear, and clubs. Use when an AI agent needs setup, usage, safety... | |
| TikTok Agent Publisher Prepare, validate, and explicitly publish TikTok content through the official Content Posting API with dry-run safety. Use when an AI agent needs setup, usag... | |
| WHOOP MCP Connect an MCP-compatible agent to local WHOOP recovery, sleep, strain, HRV, cycles, and workouts. Use when an AI agent needs setup, usage, safety boundaries... | |
| Withings MCP Connect an MCP-compatible agent to local Withings body measures, sleep, activity, workouts, and heart records. Use when an AI agent needs setup, usage, safet... | |
| YouTube Shorts Agent Prepare, validate, and explicitly upload YouTube Shorts through the official YouTube Data API with dry-run safety. Use when an AI agent needs setup, usage, s... | |
| Mi Analista Trade 10-second crypto prediction markets on PredictMe | |
| Mi Trading Trade tokens on Solana using the ClawDex CLI. Use when the user asks to swap tokens, check balances, get quotes, or manage a Solana trading wallet. | |
| test skill test skill offers a high-contrast, light-themed UI with clear typography and precise data console elements for organized, approachable information display. | |
| GTM Account Research Deep-dive a target company and produce a structured account intelligence brief covering tech stack, buying signals, key personas, and a recommended engagemen... | |
| GTM ICP Definition Run an ICP definition or refinement workshop. Use when a team needs to define who their best customers are, align sales and marketing on targeting, identify... | |
| GTM Inbound Strategy Design inbound GTM systems — lead routing logic, PLG activation flows, nurture tracks, and ICP-based triage. Use when leads aren't converting, building or op... | |
| GTM Meeting Prep Prepare a seller or growth rep for an upcoming sales or partnership meeting. Produces a pre-meeting brief with account context, attendee research, discovery... | |
| GTM Outbound Strategy Design outbound GTM campaigns and write ready-to-send sequences. Use when building a new outbound motion, writing cold email or LinkedIn outreach, designing... | |
| GTM Skill Packs Full B2B GTM skill suite for iCustomer Audience Loop. Covers ICP definition, account research, lead scoring (FIRE framework), prospecting, meeting prep, outb... | |
| Capacities Manage Capacities notes, daily entries, and weblinks. | |
| Locu Manage tasks and projects via Locu's Public API. | |
| Ticktick Linux Manage TickTick tasks (add, list, complete) via the local `tickrs` CLI. | |
| AgentMail Email API-first email platform designed for AI agents. Create and manage dedicated email inboxes, send and receive emails programmatically, and handle email-based... | |
| QMD Markdown Search Search and retrieve markdown documents from local knowledge bases using qmd. Supports BM25 keyword search, vector semantic search, and hybrid search with LLM... | |
| Perplexity Agent Search the web using the Perplexity Agent API. Provides real-time information, news, and grounded answers with citations. Use when the user asks for: (1) Cur... | |
| Etherscan Use when you need to query Etherscan API V2 for onchain activity, contract metadata, ABI/source retrieval, proxy implementation discovery, and transaction/lo... | |
| Taiko Native Bridge Use when an agent needs to bridge or claim ETH/ERC20/ERC721/ERC1155 across Taiko L1/L2 with send/wait-ready/claim workflows. | |
| Clawvault Memory Durable-memory + self-improving workflow for the ClawVault plugin. REQUIRES the ClawVault plugin from github.com/davidtkeane/openclaw-plugin-clawvault - do N... |
24,501–24,550 of 108,824
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.