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 |
|---|---|
| Muxray Inspect tmux panes as JSON: snapshot, diff, and classify Claude/Codex/Copilot agent state across the whole fleet. | |
| AnalyticLunch Query live traffic data, tracking links, and weekly reports from AnalyticLunch | |
| openclaw-kirocli-coding-agent Run Codex CLI, Claude Code, Kiro CLI, OpenCode, or Pi Coding Agent via background process for programmatic control. | |
| ralph talker Self-improving conversational skill. Gets better at talking with every use. Saves what works to memory, evolves identity over time. | |
| Seedance 2.0 prompt-engineering skill Generate precise, timecoded Seedance 2.0 prompts integrating multimodal inputs with asset mapping for controlled 4-15s video creation and editing. | |
| tg buttons Automatically colors Telegram bot choice buttons as default, destructive (red), or secondary (gray) based on the action's criticality and reversibility. | |
| emoji and tg stickers use proactively based on mood Automatically send Telegram stickers and emojis that match the mood and vibe of the conversation. Activates on every Telegram message to add expressive, huma... | |
| botcall Phone numbers for AI agents. Provision numbers, receive SMS, extract verification codes. Use when you need to sign up for services, receive 2FA codes, or han... | |
| botcall-mcp Give your AI agent a real phone number for SMS verification. Provisions numbers, receives SMS, and extracts verification codes via the botcall API. Requires... | |
| AI Twitter Daily Generate daily AI Twitter report from top AI researchers and companies. Use when user asks for AI Twitter summary, daily AI news, or wants to track AI commun... | |
| Grok Twitter Query Query and summarize Twitter/X information using Grok AI. Use when user asks about Twitter trends, tweets, X platform content, or needs Twitter information su... | |
| Nomad Query HashiCorp Nomad clusters. List jobs, nodes, allocations, evaluations, and services. Read-only operations for monitoring and troubleshooting. | |
| Starlink Control Starlink dish via local gRPC API. Get status, list WiFi clients, run speed tests, stow/unstow dish, reboot, and get GPS location. Use when the user asks about Starlink, internet status, connected devices, or satellite connectivity. | |
| house-skills-kit 房产AI技能仓库总览：按身份分技能（房开企业/经纪公司/渠道分销/购房者业主/二手经纪人/一手销售/房产自媒体）。已发布calc-toolkit公共计算工具包与案场销售线五技能（话术库/异议处理/算价逼定/接待挖掘/判客跟进）（19件收官：房贷月供/二手房全成本/一手房成本/购房能力/提前还款/首套二套认定/楼层折扣/公积金额度/佣金提成/得房率换算/租金回报/LPR变动影响/持有成本/买房vs理财/面积误差补退/违约金定金/房龄贷款年限/楼面价货值/日照楼间距，35城规则库 | |
| Playwright Service Capture web screenshots, retrieve page titles, and scrape text or HTML content from web pages using URL and optional CSS selectors. | |
| Ai Claims Assessment Assesses public healthcare-AI vendor documents to identify gaps between AI use claims, legal language, and HIPAA rules on PHI handling and model training. | |
| AI Tooling Inventory Builds the inventory of AI capability an organization actually runs, across the five ways it enters: purchases, in-house builds, vendor features switched on inside approved products, integrations attached to approved platforms, and free too | |
| Baa Review Clause-by-clause BAA analysis against 45 CFR 164.504(e)(2). Evaluates all 9 required HIPAA provisions with risk scoring and remediation recommendations. | |
| compliance-posture-intake Comprehensive HIPAA compliance posture assessment for agent and API contexts. Runs a structured intake covering all Seven Elements of an effective compliance program, chains hipaa-gap-analysis, baa-review, framework-mapping, compliance-qa, | |
| compliance-qa RAG-enhanced compliance Q&A with regulatory interpretation guardrails, source attribution, and escalation triggers. | |
| Control Assessment Evaluate individual framework controls against organizational documentation with evidence extraction, severity classification, and remediation recommendations. | |
| Document Finder Scan a directory of documents, classify each file by compliance type, resolve version conflicts with the user, and produce a prioritized analysis plan mappin... | |
| Framework Mapping Map document sections to compliance framework controls with confidence scoring. Produces bidirectional mappings for gap analysis. | |
| Hipaa Gap Analysis Assess compliance documents against HIPAA Security Rule and Privacy Rule requirements. Produces structured findings with evidence, gap descriptions, and reme... | |
| legal-page-discovery Discover and classify a live website's legal/compliance pages — privacy policies, HIPAA/Part 2 notices, terms of use, informed consents, and similar documents — by triangulating sitemap.xml, robots.txt, footer/nav links scraped from multipl | |
| Part 2 Notice Assessment Evaluates a publicly posted Part 2 patient notice for SUD programs to identify missing or insufficiently stated federally required §2.22(b) confidentiality e... | |
| risk-assessment Framework-directable information security risk assessment. Identifies threats, evaluates likelihood/impact via a 3x3 matrix, maps findings to any compliance framework, and recommends risk treatment options with prioritization guidance. | |
| Skill Router Read one or more document manifests (from legal-page-discovery and/or document-finder) plus the full rote-compliance-toolkit skill catalog, and reason about... | |
| Create Payment Credential Gets secure, one-time-use payment credentials (cards, tokens) from a Link wallet so agents can complete purchases on behalf of users. Use when the user says... | |
| gh-modify-pr Modify code based on GitHub PR review comments and create a local commit using gh + git. Use when the user asks to "follow PR comments", "fix review comments... | |
| React Seo Skills Guides SEO and AI-search visibility for Next.js, Astro, and React apps in Cursor, Claude Code, and Codex. Use when setting up metadata, Open Graph, Twitter cards, Schema.org JSON-LD, sitemaps, robots.txt, optional llms.txt, keyword research | |
| enzoldhazam Control NGBS iCON Smart Home thermostats. Use when the user asks about home temperature, heating, thermostat control, or wants to adjust room temperatures. | |
| discord-recipient-safety Discord DM or relay recipient binding: authenticate the requester, validate the recipient, and require agent-sent requester attribution before every recipient-specific send. | |
| dr-agent-backup Set up, audit, repair, or restore a six-hour Azure DevOps workspace backup. | |
| dr-agent-baseline Daniel's core operating standard for agents. | |
| dr-agent-secrets Persistent local secret setup, rotation, inspection, and recovery with SecretRefs, protected env fragments, redaction, and restart safety. | |
| dr-api-execution-bootstrap Run a bounded multi-call API task directly when safe; map dependencies, validate outcomes, and preserve platform policy. | |
| dr-checkpoint-implementation Guide Codex through complex or production-risk implementation work in small validated checkpoints. Use when a user asks for staged implementation, step review before proceeding, shadow/dry-run rollout, alerting, cron, data pipeline, monitor | |
| DR Context Pipeline Deterministic memory/context pipeline with semantic retrieval checks, compression/lint, safe fallback, and memory watchdog. | |
| dr-memory-foundation Opinionated, file-based memory layout for OpenClaw-style agents: dashboards (now/open-loops/automation), topic files, glossary, and an always-on policy+topic... | |
| DR. Planning Artifacts Create handoff-ready product, system, roadmap, architecture, and Azure DevOps planning artifacts. | |
| dr-runtime-contract Runtime configuration changes: propagate, detect stale declarations, and prove capability across enabled execution paths. | |
| dr-schedule-manager Design and implement reliable scheduled or event-triggered automations for OpenClaw agents so changes to model, prompt, delivery, and policy take effect immediately on the next run. Use when cron jobs, daily briefings, reminders, digests, o | |
| dr-session-cleaner Install an alert-only OpenClaw session sentinel that reports high context use without resetting or deleting sessions. | |
| 小红书爆款文案生成（她势自游版） 小红书爆款文案生成技能。用于生成小红书爆款文案、排期表管理、热点分析、配套封面生成等任务。触发词：/小红书文案 /爆款文案 /生成排期表 /文案排期 /小红书爆款 /爆款流水线 /生成封面 /封面生成。适用于运营小红书账号、需要批量生成文案素材和封面的团队。 | |
| GoList Manage GoList grocery lists via CLI: create, join, switch, share lists, and add or remove items with automatic device and item ID handling. | |
| equibles US stock market data from Equibles: SEC filing search with exact lines, XBRL financial statements, earnings call transcripts, insider trades, 13F holders, congressional trades and daily prices. Use when the user asks what a filing or earnin | |
| Blog Master — Universal SEO Blog Writing System Write SEO-optimized blog posts for any niche and publish them to WordPress, Google Business Profile, and Google Blogger. Includes AEO triggers for AI search... | |
| Brand DNA — Universal Brand Bible Builder Build a complete Brand Bible for any business — tone of voice, positioning, target audiences, messaging pillars, and visual identity guidelines. The foundati... | |
| Email Campaigns — Universal Email Marketing Write high-converting email campaigns for any business — newsletters, re-engagement sequences, B2B cold outreach, promotional emails, and automated drip camp... |
23,801–23,850 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.