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 |
|---|---|
| Databar MCP Drive Databar MCP: leads, marketing intel, tables, flows. | |
| design-brief Turn a vague feature idea into an approved design brief — a file recording the intent, every decision made (with why and cost-if-wrong), scope boundaries, exact interfaces, and constraints — that task-executor, backlog-planner, and autopilo | |
| diagnose Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. On non-trivial cases, Phase 3 spawns parallel `Explore` sub-agents — each defending a distinct hy | |
| dotnet-onion-api Scaffold a new .NET solution (Web API + Worker microservices) using ONION architecture and EF Core, codifying battle-tested layered patterns and explicitly avoiding the common pitfalls of legacy stored-procedure-centric codebases. Use this | |
| e2e-verify Verify a change end-to-end in a real browser, routed by one question — who needs this check to run again? Ephemeral checks run via Expect (millionco/expect) or browser-use (AI agent driving headless Chromium — references/browser-use.md) whe | |
| github Work with GitHub issues and pull requests via the gh CLI — query assigned/milestone issues (incl. cross-repo search and Projects v2 boards), read an issue's description AND download+view its embedded screenshots, publish branches, and creat | |
| goal-runner Autonomous multi-task orchestration loop over a roadmap file (ROADMAP.md, TODO.md, or any checkbox task list) — pairs with the built-in /goal Stop hook to work tasks ONE at a time until the file is done. The main agent orchestrates only; ev | |
| handoff Capture a session hand-off so work can resume cleanly in a new Claude session before context runs out. Writes a canonical dated Markdown file (objective, progress, decisions, files, open issues, and a ready-to-paste "Next Session Prompt") A | |
| humanizer Rewrite text so it does not read like an LLM wrote it. Strips AI-writing patterns (significance inflation, "delve"/"tapestry" vocabulary, rule-of-three lists, em-dash sales rhythm, sycophancy, hedge filler, tidy cadence) without inventing f | |
| improve-codebase-architecture Surface architectural friction in a codebase and propose **deepening opportunities** — refactors that turn shallow modules into deep ones, informed by the project's `CONTEXT.md` glossary and `docs/adr/` decisions. Walks the codebase with an | |
| maestro-mobile-test Write and run E2E tests for React Native / Expo apps using Maestro CLI — the open-source tool that drives the **real native app** on an Android emulator or iOS simulator, not a web build. Covers what browser-based e2e (Playwright, Expect, e | |
| migration-safety Review a schema migration for production safety under live traffic — destructive operations (dropped/renamed columns or tables, type narrowing) gated behind expand-contract plans, lock-taking DDL flagged with the specific lock and its durat | |
| model-inventory Scan the machine for installed AI coding CLIs (claude, codex, gemini, copilot, opencode, ollama), detect whether each account is actually active and which models are usable, and cache the result to ~/.claude/model-inventory.json with role→m | |
| nextjs-app-router Scaffold a new Next.js (App Router) fullstack app with TypeScript, NextAuth (Auth.js v5), Prisma + PostgreSQL, Route Handlers, Redux Toolkit + RTK Query, Tailwind + shadcn/ui, React Hook Form + Zod. Pages are 'use client' SPA-style — RTK Qu | |
| regression-hunt Find what a change can break in the code that did NOT change — trace a diff, branch, commit range, or named feature outward through callers, consumers, shared state, and contracts, rank the concrete regression scenarios by blast radius, and | |
| safe-refactor Execute a behavior-preserving refactor with a proof of preservation — establishes a safety net first (existing tests or new characterization tests over every touched path), locks a baseline green run, then moves in small always-green steps | |
| security-review Attacker's-eye security review of a diff, branch, or module — walks a fixed vulnerability catalog (missing authz on new endpoints, injection, secrets in code/logs, trusting client-sent identity, SSRF, path traversal, insecure deserializatio | |
| ship-it Pre-launch operational-readiness checklist for a feature, release, or branch. Walks a fixed 10-category gate (logging, error handling, telemetry, feature flags, migrations, rollback, secrets, local-first storage, auth, update strategy), pro | |
| sql-review Pre-commit SQL code review for uncommitted database changes. Detects antipatterns that cause real production incidents — broken TRY/CATCH error handling, swallowed errors, retry patterns without loops, tables missing PK/indexes, type-mismat | |
| task-executor Disciplined, legible, resumable execution of a single already-defined task — one task, one plan the user approves before any code is written, every change validated. Use this skill whenever the user says "/task-executor", "task-executor", " | |
| tauri-2-app Scaffold a new Tauri 2 desktop app (Rust backend + TypeScript/React frontend) using a thin-frontend / rich-Rust-backend architecture with modular commands, trait-based platform abstractions, encrypted secrets at rest, single-instance enforc | |
| think-like-fable An operating manual for rigorous reasoning — how to read the real request beneath the words, decompose into independently-checkable pieces, spend effort where the risk lives, verify by re-derivation instead of plausibility, label known vs. | |
| upgrade-deps Upgrade project dependencies safely — inventories current→target versions from the actual manifest/lockfile, reads the real changelog/release notes for every major bump (a breaking-change claim without a changelog citation is a hypothesis), | |
| write-a-skill Create a new Claude Code skill — scaffolds a properly-structured `SKILL.md` (with YAML frontmatter, trigger-rich description, workflow, examples, anti-patterns), drops it in the right location (this library's `skills/`, the project's `.clau | |
| write-tests Author tests that actually catch regressions — picks WHAT to test by risk (branch points, boundaries, error paths, money/auth/concurrency), proves every new test can fail (a test never seen red is decoration), mocks only boundaries you don' | |
| 田伯光股票分析 股票深度分析（18维度融合版）：基本面估值+实战交易双重视角，支持A股/港股/美股，输出完整9部分飞书文档报告。 | |
| Crypto Short Signal Generator Generates short signals predicting 30%+ coin drops within 7 days based on historical token unlock schedules and price trends analysis. | |
| NeuralDebug AI-powered debugging for software (8 languages) and LLM/transformer reasoning. Debug programs with natural language via real debuggers (GDB, LLDB, CDB, JDB,... | |
| Session Storage Management Analyze and clean up OpenClaw session storage files. Use when the user wants to manage session files, clean up old sessions, delete cron/heartbeat, or organi... | |
| Solvera Markets Interact with on-chain marketplace intents by submitting offers, getting selected, and fulfilling outcomes using verified ERC-20 rewards and safe filters. | |
| AIFeed Verify signed AIFeed declarations and publish signed AIFeed origins (permissions, feeds, manifests). | |
| Super Personasiled Search Build, debug, and extend the Connectify founder network platform (React/Vite frontend + Express backend + Redis cache + OpenAI ranking + Apify ingestion). Us... | |
| Interview Driven Learn Interview-driven is all you need. Drives end-to-end tech learning with interview standards. Activated when the user submits study notes, project summaries, o... | |
| Client Design, manage, and improve client relationships across sales, onboarding, delivery, communication, retention, and account growth. Use when someone needs to... | |
| Pipeline Diagnose pipeline health, detect stalled deals, and surface what needs attention this week. Built for sales teams managing active opportunities. | |
| Proposal Design, structure, and improve proposals for sales, services, partnerships, projects, and strategic opportunities. Use when someone needs to turn interest in... | |
| Prospect Filter raw target lists into prioritized prospects worth pursuing. Score fit, timing, value, and access. Route each target to pursue, research, watch, or drop. | |
| Tracker Design, organize, and improve tracking systems for work, goals, follow-ups, pipelines, projects, habits, issues, and ongoing operations. Use when someone nee... | |
| AIFS - HTTP File system Store and retrieve files via AIFS.space cloud storage API. Use when persisting notes, documents, or data to the cloud; syncing files across sessions; or when the user mentions AIFS, aifs.space, or cloud file storage. Not to be used for any | |
| SwarmSkill Use when an AI agent wants to trade Solana pump.fun coins together with a swarm of other agents — coordinated coin voting, simultaneous buys, a voted hold du... | |
| daily-reflection-journal 每日反思日记引导技能，基于《认知觉醒》的反思框架。当用户说"做每日反思"、"写反思日记"、"今天反思"、"daily reflection"、"回顾今天"等触发。引导用户通过事实-感受-启发三层面深度反思，将日常经历转化为成长素材。 | |
| PaleBlueDot CLI Command-line tool for PaleBlueDot AI platform supporting login, API token management, usage and balance queries, and browsing available AI models. | |
| WeChat Cover Generate WeChat official account cover images with proper 2.35:1 aspect ratio. Supports OpenAI DALL-E and Gemini image generation with customizable styles. | |
| Exchange Skills Full email, calendar, contacts, tasks, and notes management for Microsoft Exchange/Outlook. Use when Claude needs to list unread emails, read email content,... | |
| Model Provider Support Answer official-doc-grounded support questions about Claude, OpenAI/GPT, and Gemini model availability across Bedrock, Vertex AI, Azure, OpenAI, and Gemini API. | |
| News Briefing Real-time AI news briefing for any topic. Say "给我看大谷翔平的新闻" or "AI今天有什么大新闻", and your agent instantly searches the web, summarizes the top stories in Chinese,... | |
| Tech Radar Daily 每日技术情报雷达 - 自动发现有趣工具、技术趋势、赚钱项目。扫描 GitHub Trending、Product Hunt、Hacker News、Awesome Lists，智能评分筛选高价值项目，每日推送 7-9 条精选情报到飞书。 | |
| Qwen Web Agent Browser automation for 通义千问 (Qwen) web interface at qianwen.com. Use when the agent needs to ask questions to Qwen AI and get back responses via browser auto... | |
| nihao Nostr identity setup and health-check CLI. Creates a complete Nostr identity (keypair, profile, relay list, lightning address, Cashu wallet) in one command. Audits existing npub health with a 0–8 score. Single Go binary, non-interactive, ag | |
| API Endpoint Tester CLI tool to test REST API endpoints with various HTTP methods, headers, and payloads. |
25,251–25,300 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.