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 |
|---|---|
| AI-First Engineering Engineering operating model for teams shipping with AI-assisted code generation. Process shifts, architecture requirements, code review and testing standards... | |
| autonomous-loops Autonomous agent loop patterns: sequential pipelines, persistent REPL sessions, parallel spec-driven generation, PR automation, cleanup passes, and RFC-driven DAG orchestration. Choose pattern by complexity: simple (sequential) → medium (PR | |
| Browser QA Automate visual testing and UI interaction verification. 4-phase methodology: smoke test (console errors, network status, Web Vitals), interaction test (form... | |
| Chat History Importer Import AI conversation exports (OpenAI ChatGPT and Anthropic Claude) into your agent's episodic memory. Parses export files, writes daily memory summaries, a... | |
| Chat Learnings Extractor Extract structured learnings (lessons, decisions, patterns, dead ends) from AI conversation exports using a local Ollama model or any OpenAI-compatible API.... | |
| Claude API Cost Optimizer Minimize Anthropic Claude API costs through model selection, prompt caching, batching, and cost tracking. ⚠️ Enables local caching and cost logging — review... | |
| Claude Code Security Scan Audit Claude Code configuration for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Scans settings, MCP servers, hooks, a... | |
| Codebase Explorer Analyze unfamiliar codebases and generate structured onboarding guides with architecture maps, entry points, conventions, and project-specific instructions.... | |
| Coding Standards Universal coding standards for TypeScript, JavaScript, React, and Node.js. Principles: readability first, KISS, DRY, YAGNI. Covers naming, type safety, error... | |
| continuous-agent-loop Canonical patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. Supports sequential, RFC, CI/PR, and exploratory l... | |
| Deep Research Conduct multi-source research with synthesized reports and citations. Searches the web, reads full content from key sources, and produces structured reports.... | |
| Freqtrade Backtester Run Freqtrade backtests for cryptocurrency trading strategies, interpret results, and iterate. Use when downloading historical data, running a backtest, read... | |
| Freqtrade Strategy Dev Develop, iterate, and improve Freqtrade cryptocurrency trading strategies. Use when writing a new strategy, improving an existing one, analyzing why a strate... | |
| Freqtrade Tools Shell aliases and helper commands for Freqtrade (cryptocurrency trading bot) that speed up common tasks. Use when setting up Freqtrade shortcuts, downloading... | |
| Freqtrade US Setup Complete setup guide for running Freqtrade (cryptocurrency trading bot) legally in the United States. Use when setting up Freqtrade for the first time, choos... | |
| GitHub Issue Writer Draft well-structured GitHub issues from a description, error, or idea. Supports bug reports, feature requests, enhancements, and tasks. Optionally submits d... | |
| GitHub PR Writer Write clear, structured GitHub pull request descriptions using a standardized template. Use when creating a PR, updating a PR description, or when asked to d... | |
| Google Workspace Ops Operate across Google Drive, Docs, Sheets, and Slides as unified workflow. Find, summarize, edit, migrate, or clean shared documents. Trigger phrases: find d... | |
| Jira Ops Retrieve, analyze, and update Jira tickets directly. Supports MCP-based (recommended) and direct REST API approaches. Trigger phrases: fetch Jira ticket, upd... | |
| Kraken Agent Discover and use the official Kraken CLI — an AI-native trading tool for crypto, stocks, forex, and derivatives. Use when: setting up a trading agent, paper... | |
| OpenClaw Docker Setup Run OpenClaw inside Docker on Linux with Tailscale remote access. ⚠️ Involves sudo, Docker, Tailscale, and credential mounting — review security section befo... | |
| OpenClaw Dual Agent Run two OpenClaw agents simultaneously — a paid Anthropic agent and a free agent using either OpenRouter or local Ollama models. Trigger phrases: multi-agent... | |
| OpenClaw Ollama Memory Set up local semantic memory search in OpenClaw using Ollama + nomic-embed-text. Free, private, offline-capable. Replaces cloud embedding APIs (OpenAI, Gemin... | |
| performance-benchmark Measure performance baselines, detect regressions, and compare stack alternatives before/after changes. Modes: page performance (Core Web Vitals), API latenc... | |
| Rails CI Fixer Fix failing CI on Rails PRs using a tiered escalation loop. Use this skill whenever a Rails pull request has failing CI — RSpec failures, RuboCop offenses, m... | |
| Rails TDD Standards RSpec testing standards and best practices for Rails applications. Use when writing new tests, reviewing test quality, debugging factory errors, setting up F... | |
| REST API Design REST API design patterns: resource naming, HTTP methods, status codes, pagination, filtering, authentication, rate limiting, versioning, and response formats... | |
| Strategic Compact Manual context compaction at logical workflow boundaries rather than arbitrary auto-compaction. Use after completing exploration phases, before switching maj... | |
| Tailwind Rails Tailwind CSS component patterns for Ruby on Rails ERB views. Use when building UI components in Rails, creating shared partials, implementing dark mode, writ... | |
| TDD Workflow Test-driven development workflow enforcing 80%+ code coverage with unit, integration, and E2E tests. Write tests first, validate RED state, implement minimal... | |
| Token Budget Advisor Offer users informed choice about response depth before answering. Control token usage, response length, and answer depth. Trigger phrases: token budget, tok... | |
| Twitch Clip Create Twitch clips of the current live stream via the Twitch API. Use when a streamer says "clip that", "clip the last X seconds", "make a clip", "clip it",... | |
| Polymarket Btc 5m Mtf Momentum Dyll Multi-timeframe CEX momentum trading for Polymarket BTC 5-minute fast markets. Aligns 1m/3m/5m Binance returns for directional conviction. Inspired by the | |
| Polymarket Btc Midcandle BTC Mid-Candle Scalper — 75%+ win rate on Polymarket BTC 15-minute markets. Enters mid-candle (2–12 min remaining) when intracandle momentum is confirmed by... | |
| Polymarket Eth 5m Mtf Momentum Dyll Multi-timeframe CEX momentum trading for Polymarket BTC 5-minute fast markets. Aligns 1m/3m/5m Binance returns for directional conviction. Inspired by the | |
| Polymarket Eth Midcandle ETH Mid-Candle Scalper — 77%+ win rate on Polymarket ETH 15-minute markets. Enters mid-candle (2–12 min remaining) when ETH intracandle momentum is confirmed... | |
| Manual Trade Placement Place manual trades on Polymarket by telling your agent what to bet on. Supports FAK (instant fill at market) and GTC (limit order on the book). Pass a Simme... | |
| Polymarket Market Importer Auto-discover and import Polymarket markets matching your keywords, tags, and volume criteria. Runs on a schedule so you never miss a new market worth tradin... | |
| Polymarket Sol 5m Mtf Momentum Dyll Multi-timeframe CEX momentum trading for Polymarket BTC 5-minute fast markets. Aligns 1m/3m/5m Binance returns for directional conviction. Inspired by the | |
| Simmer Calibration Report Run a calibration report on any Simmer trade journal. Win rate and EV broken down by strategy, time of day, price band, and market type. Know exactly where y... | |
| Simmer Resolution Tracker Monitors your Simmer positions for resolutions, logs wins/losses to your trade journal, and automatically redeems winning positions on-chain. Built for Simme... | |
| Clicky Analytics Fetch website analytics from Clicky (clicky.com) via their REST API. Use when the user asks about website traffic, visitors, pageviews, top pages, bounce rat... | |
| EnvelopeBudget Manage budgets, transactions, accounts, envelopes, payees, and reports using the EnvelopeBudget.com API for tracking and organizing finances. | |
| ZapYeti Use the ZapYeti API to list debts, track balances, view payoff schedules, log payments, and monitor debt-free progress via api.zapyeti.com. Use when the user... | |
| BioSkills Installs 412 bioinformatics skills covering sequence analysis, RNA-seq, single-cell, variant calling, metagenomics, structural biology, and 54 more categorie... | |
| Gigiac -- Your Claw Can Hire Humans (& Other Claws) Browse and bid on tasks, submit proposals, deliver completed work, and earn on Gigiac — the marketplace where AI agents and humans commission each other. Use... | |
| Sequoia-X A股量化选股系统 Sequoia-X V2 的安装、配置与使用。当用户要求安装 Sequoia-X、使用 Sequoia-X 选股、运行量化策略、配置飞书推送时激活。 | |
| Jwdiario Buscar y obtener el texto diario de la página oficial de los Testigos de Jehová para la Librería Watchtower en español (wol.jw.org/es/). Utiliza web_fetch pa... | |
| transcription Transcribe audio and video files using OpenAI Whisper API. Use when user wants to transcribe audio/video files, extract speech from media, or get text from r... | |
| jiusansqmy 九三学社社情民意信息写作技能。当用户需要撰写社情民意信息、社情民意报告、参政议政建言材料、反映社情民意稿件，或提及"九三学社""社情民意""建言献策""参政议政"等关键词时触发。该技能提供标准格式规范、内容结构要求和范文参考，确保产出的社情民意信息符合九三学社官方行文标准。 |
26,251–26,300 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.