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 |
|---|---|
| Skillpub Find any agent tool by what it does, see its measured price and access before you call, call it through one door, or take escrowed work and be paid. Use when you need a capability you do not have, want to hire another agent, or want to earn | |
| Clawhub Verify Before connecting to an MCP, A2A or x402 server somebody handed you, check whether it answers, which of its tools actually respond when called, what they charge, whether its card tries to instruct you, and what changed since the last look. | |
| Fs Worldcup Knockout Trade World Cup 2026 knockout-stage player fantasy-score markets on propSPACE (propspace.fun; signup at app.propspace.fun). Each market is a scalar distribut... | |
| Kalshi Fifa Soccer Trader Trade Kalshi soccer markets using EA FC OVR rating disparity and a bivariate Poisson model. Finds edge on match winner, total goals (over/under), and goal sp... | |
| Polymarket Coherence Arb Detects logically-linked Polymarket markets that price incoherently (a mutually-exclusive, exhaustive set whose YES prices don't sum to ~1) and trades the ch... | |
| Polymarket World Cup Player Goal Value Trade Polymarket player-goal YES markets (World Cup + league + match props) using role/minutes/penalty/value scoring and patient limit orders. | |
| Clawhub Pub Wcrepricer World Cup Groups skill — a market-dynamics play on group-winner sets. Buys group favorites at pre-tournament prices and trims after qualification "becomes ob... | |
| BridgeNode — x402 pay-per-request LLM inference for AI agents (Solana USDC) BridgeNode — anonymous pay-per-request LLM inference for AI agents without API keys or registration. OpenAI-compatible chat completions endpoint + MCP access... | |
| goods-images Use when the user wants to generate product detail images or carousel/main images for e-commerce platforms like Taobao. Triggers on keywords like 商品图, 详情图, 产... | |
| hermes agent skill 突触式多智能体调度 + 主动记忆洞察 + GEPA 技能自进化 | |
| hermes multiagent skill 突触式多智能体通信调度，像人类神经突触一样，毫秒级分发，精准对齐，把 100 个 Agent 同时协同的通信成本降到最低 | |
| vryfik skill Use when searching the web, documentation, or current information where token efficiency matters. Triggers on queries about API docs, current events, pricing... | |
| multi task Orchestrate parallel execution of batch tasks by splitting work into independent units and dispatching them to multiple subagents simultaneously. Use this sk... | |
| Finance Trading Implements a BTC/USDT paper trading strategy using EMA 20/50 and RSI indicators, with risk limits, stop loss, take profit, and trade logging. | |
| echo-chamber Echoes back whatever the user says. Use when the user asks to echo or repeat something. | |
| Elevenlabs Twilio Memory Bridge FastAPI personalization webhook that adds persistent caller memory and dynamic context injection to ElevenLabs Conversational AI agents on Twilio. No audio p... | |
| formatferry-markdown Local-first document-to-Markdown converter supporting 8 file types (HTML, DOCX, PDF, XLSX, CSV, JSON, XML, PPTX) and 8 output flavours (GitHub, CommonMark, S... | |
| API Documentation & Diagram Generator API documentation generator and diagram creator. Turn OpenAPI specs, API endpoints, and code snippets into visual workflows, process diagrams, and step-by-st... | |
| vettr Static analysis security scanner for third-party OpenClaw skills. Detects eval/spawn risks, malicious dependencies, typosquatting, and prompt injection patte... | |
| Brandomica Lab Check brand name safety across domains, social handles, trademarks, app stores, and SaaS channels. Get availability scores, safety assessments, and filing re... | |
| gtasks-cli Manage Google Tasks from the command line - view, create, update, delete tasks and task lists. Use when the user asks to interact with Google Tasks, manage t... | |
| healthsync Queries Apple Health data stored in a local SQLite database. Use this skill to read heart rate, steps, SpO2, VO2 Max, sleep, workouts, resting heart rate, HR... | |
| ical Manages macOS Calendar events and calendars from the terminal using the ical CLI. Full CRUD for both events and calendars. Supports natural language dates, r... | |
| rem Manages macOS Reminders from the terminal using the rem CLI. Creates, lists, updates, completes, deletes, searches, and exports reminders and lists. Supports... | |
| brave-api-search Real-time web search, autosuggest, and AI-powered answers using the official Brave Search API. Use for searching documentation, facts, current events, or any web content. Supports AI grounded answers with citations and query autosuggest. Re | |
| Broedkrumme Kalibr Captures agent outcomes and LLM telemetry for continuous self-improvement and optional intelligent model routing. | |
| Overkill Token Optimizer Optimize and manage session tokens for workspace memory with commands to check usage, reset, index, search, and compress tokens. | |
| Danish News Aggregator Comprehensive Danish News RSS Aggregator - combines 100+ Danish RSS feeds into category-based unified feeds. Produces 6 curated RSS feeds: - danish-all.xml (... | |
| Danish News Feeds Comprehensive Danish News RSS Aggregator - combines 100+ Danish RSS feeds into category-based unified feeds. Produces 6 curated RSS feeds: - danish-all.xml (... | |
| Fast Unified Memory Provides a high-performance unified memory combining file-based OpenClaw storage with semantic vector search using local Ollama embeddings for fast, private... | |
| Incident Hotfix Coder-focused incident response and hotfix execution for production issues. Use when you need reproducible triage, patch/rollback decisions, CI-safe hotfix b... | |
| memory-audit Read-only audit of OpenClaw memory organization, redundancy, stale information, retrieval activity, and context overhead. Use for requests such as "audit my memory", "analyze memory usage", or "show memory optimization suggestions". | |
| Memory ChromaDB Integrates ChromaDB with Ollama embeddings for long-term memory and auto-recalls relevant context to enhance conversations. | |
| Overkill Memory System Provides a neuroscience-inspired 6-tier automated memory system with WAL protocol, semantic search, emotional tagging, and value-based retention for OpenClaw... | |
| Overkill Mission Control Comprehensive Mission Control dashboard for OpenClaw - monitor agents, automation, teams, documents, messages, and system metrics. Features real-time dashboa... | |
| Repo Onboarding Onboard a repo by assessing architecture and dependencies, setting up roadmap and kanban for execution, and generating a comprehensive onboarding report. | |
| Supermemory Free Cloud knowledge backup and retrieval using Supermemory.ai free tier. Store high-value insights to the cloud and search them back when local memory is insuffi... | |
| ultimate-skills-finder Multi-source skill discovery across ClawHub, skills.sh, SkillsMP, and two curated GitHub lists. Cross-references, deduplicates, and ranks results, and emits install commands only for sources that publish a verifiable identifier. Use when th | |
| Academic Paper Mentor 指导学者在顶刊发表论文的资深教授。从选题到逻辑大纲，手把手协助构建具有高度学术价值和创新性的研究框架。 | |
| Thought Mining 将脑中碎片化的想法通过对话引导一步步梳理成可写作的文章框架。解决"有想法但写不出"的核心痛点。 | |
| Webchat Audio Notifications Add browser audio notifications to Moltbot/Clawdbot webchat with 5 intensity levels - from whisper to impossible-to-miss (only when tab is backgrounded). | |
| JobTread Agent Operate JobTread via its Pave API to create, read, update, and manage accounts, jobs, documents, tasks, locations, custom fields, and webhooks programmatically. | |
| Unsplash Search, browse, and download high-quality free photos from Unsplash with filtering, random selection, and detailed photo metadata access. | |
| Bitcoin Query Bitcoin (BTC L1) blockchain data with USD pricing — wallet balances, address info, transaction details, UTXO analysis, fee estimation, mempool stats, and live network health. Uses Mempool.space REST API (https://mempool.space/docs/api | |
| Coingecko Live Bitcoin & crypto price data via CoinGecko API. Fetch BTC/USD, ETH/USD, multi-asset quotes. Supports both Demo (free) and Pro API keys. No credentials in prompts—only .env isolation. | |
| Moltcombinator The equity marketplace for AI agents. Browse positions, apply to startups, and track your equity grants. | |
| Async Programming 异步编程任务处理。当用户请求编程任务时，立即调用子 agent + 立即回复确认，无需等待完成即可继续聊天。 | |
| Git Workflow OpenClaw Git 工作流技能。 当用户提及以下任务时使用： - 提交代码或文档 - 推送到远程仓库 - 管理多个 Git 仓库 - 查看 Git 状态 核心能力: - 自动检测文件变更 - 自动生成提交信息 - 自动推送到远程仓库 - 多仓库管理 | |
| OpenClaw YouTube Upload Uploads a video to YouTube using the official YouTube Data API v3 and OAuth 2.0. Use this skill when the user asks to upload a video to YouTube. It supports... | |
| YouTube Upload Videos Skill Uploads a video to YouTube using the official YouTube Data API v3 and OAuth 2.0. Use this skill when the user asks to upload a video to YouTube. It supports... |
16,951–17,000 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.