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 |
|---|---|
| Agent Memory System v12 Agent 记忆系统 — 五路融合检索 + 双时间线 + 因果链 + Spirit管家 + 记忆回声 + 弹性配置 + Circuit Breaker + GDPR合规 + 192项安全审计修复 | |
| Skill Search & Create 在 ClawHub 上搜索现有技能，当找不到匹配时自动创建新的 OpenClaw 技能。 | |
| conecto Business tools for your OpenClaw agent through one MCP server: a CRM, email inboxes, phone numbers it answers, invoices and bookkeeping, a booking calendar, e-signatures and a help desk. Conecto is a paid service, charged per tool call from | |
| code-quality-guard Pair-style code quality reviewer: twelve book-grounded decay risks (R1–R6, T1–T6) plus release-safety and first-paint UX checks. Findings always use Iron Law (Symptom → Source → Consequence → Remedy) and a 0–100 review-index Health Score. T | |
| Safe Evolver A safe AI agent evolution engine that analyzes runtime history to identify improvements and applies protocol-constrained evolution with comprehensive safety... | |
| Safe Guardian A safe security layer plugin for OpenClaw that intercepts dangerous tool calls (exec, write, edit) through multi-layer blacklist/whitelist filtering and inte... | |
| Skill Vetter Optimized 🔒 优化版技能审查器 - 安全优先的AI代理技能审查工具。在从ClawHub、GitHub或其他来源安装任何技能前使用。检查红标、权限范围和可疑模式。包含实用工具和系统化审查清单。基于原始skill-vetter优化，添加了Python检查脚本和详细审查流程。 | |
| Tavily Search Optimized Web search via Tavily API (alternative to Brave). Use when the user asks to search the web / look up sources / find links and Brave web_search is unavailable... | |
| Smart Wake Prevent subagent timeout using checkpoint + cron wake + resume via session spawn mechanism. | |
| Agent Collab Protocol Standardized agent collaboration protocol for multi-agent systems. Defines L0/L1/L2 hierarchy, task contracts, error handling, agent templates, and a new-age... | |
| Personal Knowledge Base Lite Local file knowledge base with LLM-powered indexing and Q&A. Scans a directory for documents (.txt, .md, .pdf, .docx, .xlsx, .csv), extracts metadata (summar... | |
| weather 查询指定城市或地区的天气预报信息，包括温度、天气状况、降水概率、风力风向等。支持实时天气和未来多日预报查询。 | |
| Weather 查询指定城市或地区的天气预报信息，包括温度、天气状况、降水概率、风力风向等。支持实时天气和未来多日预报查询。 | |
| Fitbot Personal fitness coaching. Use when users ask about training, workouts, programs, progression, or fitness accountability. Onboards new users, deep-researches... | |
| startup-risk-radar Evaluate startup ideas, business models, and product strategies against the 7 deadly failure antipatterns extracted from 1,749 dead startups that burned $535... | |
| connskill-growth Buy market data and real-world actions per call with USDC (x402, no signup, no API key) from agent.connskill.com - keyword volume by location, Google SERP snapshots with AI-overview and PAA blocks, site audits with a real crawl, backlinks, | |
| Coinw Contract Skill Coinw Contract REST API skill: covers market data, order placement/cancellation, TP/SL, position and order queries, account assets, position modes, and lever... | |
| Coinw Spot Skill Coinw Spot REST API skill: covers market data, order placement/cancellation, order queries, account balances, and asset transfers. | |
| connie Search and update Records and Lists, import and export CSVs, run enrichment, and read workspace data in Connie, through Connie's hosted MCP server. Use whenever the user asks about their Connie workspace or wants to read or change Connie da | |
| connie Connect OpenClaw to Connie, a CRM and automation workspace, to find tools and skills and work with the user's authorized Connie workspace. | |
| Openclaw Voice Gpt Realtime Make real phone calls through your OpenClaw agent via OpenAI's Realtime API. ~200-300ms latency, natural voice, IVR navigation, voicemail detection. | |
| lantern-works Look up tracked hourly GPU rental prices (H100, A100, RTX 4090 and more) with vendor source links, check dates and day-over-day price changes, and search work-stack tool deals (compute, search, crawl, hosting, email) through the Lantern Wor | |
| skill-builder Build, review, or migrate an agent skill from a plain-language description — decides invocation control (disable-model-invocation vs user-invocable), arguments (argument-hint, $ARGUMENTS), and context cost, then scaffolds, validates, and te | |
| angel-diligence Pre-investment research and deal-memo generation for angel investors. Use when asked to "diligence [company]", "research this startup for an investment", "build a deal memo", or to prep for a founder call. Runs parallel web research with st | |
| Avoid AI Writing Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supp | |
| code-review Multi-agent deep review for code PRs in any repo. Use when asked to "deep review this PR," "multi-agent review," "review | |
| angel-diligence Pre-investment research and deal-memo generation for angel investors. Use when asked to "diligence [company]", "research this startup for an investment", "build a deal memo", or to prep for a founder call. Runs parallel web research with st | |
| code-review Multi-agent deep review for code PRs in any repo. Use when asked to "deep review this PR," "multi-agent review," "review | |
| eval-integrity Audit an LLM evaluation or benchmark repo for integrity and credibility practices. Use when asked to "audit my benchmark," "is my eval trustworthy," "check my leaderboard for contamination," "review this benchmark's methodology," or "what w | |
| guest-circuit Research podcast guest appearances to map their podcast timeline, identify repeated topics, find unclaimed angles, assess receptiveness, and suggest tailored... | |
| reconcile Tripwire check for multi-session drift. Scans state files, recent commits, and file conflicts caused by parallel Claude Code sessions. | |
| recover Scan for orphaned worktrees and stale branches after crashes or abandoned sessions. Offers safe cleanup options. | |
| session-management Structured session lifecycle for Claude Code — start, checkpoint, end, and daily heartbeat commands that maintain project state across conversations. | |
| ssot-check Single-source-of-truth drift auditor for documentation-heavy repos. Use when asked to "check for drift," "find copies of this number," "audit the docs for stale facts," or "set up an SSOT manifest." Finds facts hand-copied across files, bui | |
| Demo GIF Skill Record, render, optimize, and embed a demo GIF in a repo's README. Use when asked to add a demo gif, record a demo, show the tool in action, or make a README more visual. | |
| eval-integrity Audit an LLM evaluation or benchmark repo for integrity and credibility practices. Use when asked to "audit my benchmark," "is my eval trustworthy," "check my leaderboard for contamination," "review this benchmark's methodology," or "what w | |
| Guest Circuit Researches and maps a guest’s podcast appearance history to identify their last topics, unclaimed angles, and receptiveness for targeted outreach. | |
| reconcile Tripwire check for multi-session drift. Scans state files, recent commits, and file conflicts caused by parallel Claude Code sessions. | |
| recover Scan for orphaned worktrees and stale branches after crashes or abandoned sessions. Offers safe cleanup options. | |
| session-management Structured session lifecycle for Claude Code — start, checkpoint, end, and daily heartbeat commands that maintain project state across conversations. | |
| skill-creator Generate a new Claude Code skill from a plain-language description — decides invocation control (disable-model-invocation vs user-invocable), arguments (argument-hint, $ARGUMENTS), and context cost, then scaffolds and tests it. | |
| SSOT Check Single-source-of-truth drift auditor for documentation-heavy repos. Use when asked to "check for drift," "find copies of this number," "audit the docs for stale facts," or "set up an SSOT manifest." Finds facts hand-copied across files, bui | |
| OpenClaw GitHub Assistant Query and manage GitHub repositories - list repos, check CI status, create issues, search repos, and view recent activity. | |
| conquer-keyword Conquer a keyword: rewrite the connected WordPress site's best-matching page for it and propose the change as a reviewable diff with a before/after summary. Use to turn a target keyword into an actual page edit. Requires a connected Conquer | |
| conqueror-competitive-landscape Map who wins an SEO market: recurring domains, winning content themes, keyword coverage, backlink strength, and the openings. Use for a market-level view before picking targets. Requires a connected Conqueror MCP server. | |
| conqueror-competitor-analysis Analyze one named competitor's organic footprint, ranking keywords, content themes, backlinks, and weaknesses. Use for a deep dive on a single domain. Requires a connected Conqueror MCP server. | |
| conqueror-keyword-clustering Group keywords into page-level clusters and map each cluster to an existing or new page, flagging cannibalization. Use when you have a keyword list or Search Console data and need a content plan. Requires a connected Conqueror MCP server. | |
| conqueror-keyword-research Find keyword opportunities for a site: discover seeds, score volume, difficulty and intent, check SERPs, and save the winners. Use when deciding what to target. Requires a connected Conqueror MCP server. | |
| conqueror-link-prospecting Find link prospects from SERPs and competitor backlinks, discover public contact paths, and draft personalized outreach. Use when promoting a page, study, or tool. Requires a connected Conqueror MCP server. | |
| conqueror-seo-coach Friendly SEO coach mode: explain what each Conqueror workflow does, recommend the next step, and teach when to use MCP data versus web search. Use when unsure which workflow to run. Requires a connected Conqueror MCP server. |
22,351–22,400 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.