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 |
|---|---|
| Bunni & The Modes A persona and model-switching toolkit featuring Bunni, your bubbly cyber-security assistant. Includes batch scripts for switching models (Claude, Gemini, Dee... | |
| fintech-engineer Expert fintech engineer specializing in financial systems, regulatory compliance, and secure transaction processing. Masters banking integrations, payment systems, and building scalable financial technology that meets stringent regulatory r | |
| time-sereis-analysis Comprehensive time series data science skill covering feature engineering, model training, and competition-winning strategies for forecasting and prediction problems. | |
| Obsidian Karpathy Wiki Operate an Obsidian knowledge base as a persistent LLM wiki using a raw-to-source-to-wiki pattern. Use when Codex or another agent needs to ingest raw notes,... | |
| Image Vision 本地图片视觉理解桥接。当用户明确要求分析、描述或理解图片内容时，调用本地 Ollama 视觉模型（qwen3.5:4b）读取图片并以文字描述返回，让不具备多模态能力的推理模型也能"看见"图片。 | |
| Audit The Supreme Verifier for the Synthetic Economy. Autonomous inspection of code, contracts, and capital flows. Ensuring truth in an era of infinite generation. | |
| Bio A comprehensive AI agent skill for writing and managing professional bios. Crafts bios for any platform and any purpose, matches your voice and career stage,... | |
| Bond A comprehensive AI agent skill for understanding bonds across financial and legal contexts. Explains bond investing for personal portfolios, covers surety an... | |
| Brand Complete brand intelligence system for founders, marketers, and creative professionals. Trigger whenever someone needs to build, refine, or communicate a bra... | |
| Claim Complete insurance and legal claims intelligence system. Trigger whenever someone needs to file, manage, negotiate, or dispute any type of claim: insurance c... | |
| Claude Optimize long-context reasoning for commercial, legal, and high-stakes documents. Built for users who need stronger logic, cleaner structure, and deeper anal... | |
| Credit A comprehensive AI agent skill for understanding and managing credit. Explains how credit scores work and what actually moves them, helps you build credit fr... | |
| Deed The Sovereign Asset Title & Ownership Protocol. A high-fidelity cognitive framework for the immutable registration, verification, and transfer of real-world... | |
| Expense A comprehensive AI agent skill for tracking, categorizing, and reporting expenses. Helps individuals monitor personal spending, helps employees submit reimbu... | |
| Grant Complete grant intelligence system for individuals, nonprofits, startups, researchers, and small businesses. Trigger whenever someone needs to find grants, w... | |
| Guarantee A comprehensive AI agent skill for understanding, writing, and evaluating guarantees in business and legal contexts. Helps businesses craft guarantees that b... | |
| Judge A comprehensive AI agent skill for navigating court systems and legal proceedings. Helps you understand what type of court handles your situation, prepares y... | |
| Jury The Consensus and Arbitration Primitive. A multi-agent deliberation framework designed to resolve complex disputes and validate truth claims through probabil... | |
| Lease Complete lease intelligence system for tenants, landlords, and property managers. Trigger whenever someone needs to understand, negotiate, draft, or dispute... | |
| Model A comprehensive AI agent skill for anyone working with AI models. Helps you choose the right model for any task, write effective prompts, evaluate model outp... | |
| Nurse Clinical support system for nurses and frontline healthcare workers. Trigger whenever a nurse needs help with documentation, patient communication, care plan... | |
| clawguard Security review and risk auditing for OpenClaw skills and deployments. Inspect third-party skills, dangerous instructions, credential requests, privilege ris... | |
| PancakeSwap Audit PancakeSwap liquidity positions before capital is deployed. Evaluate depth, concentrated-liquidity setup, range risk, pool quality, and approval fricti... | |
| Plea The Autonomous Judicial Pleading & Procedural Motion System. A high-density linguistic engine designed to translate complex agentic logic into enforceable le... | |
| Presentation A comprehensive AI agent skill for creating and delivering presentations that actually work. Builds your narrative from scratch, structures slides for clarit... | |
| Project The AI project manager that never forgets, never drops a task, and never lets a deadline sneak up on anyone. Break any goal into phases, tasks, and milestone... | |
| Raydium Audit Raydium liquidity positions before capital is deployed. Analyze pool depth, concentration, liquidity quality, structural risks, and parameter changes s... | |
| Run The universal execution primitive for AI agents. A secure, sandboxed environment designed to compile, execute, and manage code, scripts, and automated workfl... | |
| Surety A comprehensive AI agent skill for understanding surety bonds across business, construction, and legal contexts. Explains what surety bonds are, who needs th... | |
| Worldcoin Filter human-critical workflows using proof-of-human logic. Designed for identity-sensitive commercial decisions, anti-bot gating, and “real human required”... | |
| XMoney Turn messy monetization ideas into clearer revenue decisions. Analyze pricing, payout logic, conversion friction, and revenue model fit for creators, operato... | |
| safeTok ↔ OpenClaw Bridge Connect safeTok Nostr DMs to your OpenClaw agent. Use OpenClaw with Claude OAuth — no Anthropic API key needed. Communicate via safeTok NIP-44 encrypted DMs... | |
| 5S管理技能 提供5S管理标准指引与目视化管理方案设计能力；当需要进行现场5S检查、标准查询、目视化设计、问题诊断或生成管理报告时使用；覆盖整理、整顿、清扫、清洁、素养全流程 | |
| 5WHY分析技能 5WHY根本原因分析专属引导师，通过追问-校验-判定流程帮助用户快速定位问题根源；适用于设备故障、生产异常、质量缺陷等现场问题分析 | |
| 8D报告评价技能 深度分析8D报告每一步骤质量，重点评价D4根因分析工具应用、D3流/遏制措施、D5/D6纠正预防措施的有效性与逻辑性；当SQE或质量工程师需要对供应商/内部8D报告进行评审、发现不足并提出改进建议时使用 | |
| 8D报告技能 8D问题解决报告生成工具，采用分步引导+对话式信息收集模式，生成结构化详细报告，适用于汽车等行业质量问题分析场景；覆盖D1-D8八大步骤 | |
| A3报告技能 辅助用户完成A3改善报告；通过强制交互收集信息、逐步追问验证、生成可编辑的HTML格式报告，适用于生产现场改善、质量问题分析等场景 | |
| APQP技能助手 辅助APQP项目管理全流程；支持项目阶段定义、文档生成（FMEA/PPAP/控制计划）、甘特图可视化、风险分析与知识库查询；适用于制造业产品质量规划全流程 | |
| Aspice Consultant 面向汽车软件质量/过程改进工程师，辅助 ASPICE 评估准备与过程改进，覆盖 SWE/SUP/SYS/MAN 等过程域与能力等级 L0-L3，基于用户客观证据做差距分析与改进路线，输出 txt+md 报告（不含网页）。 | |
| 注册审核员考试技能（主观题） 注册审核员考试主观题复习工具，支持五个科目（认证通用基础、管理体系认证基础、质量/环境/职业健康安全管理体系基础）的历年真题浏览、模拟练习、答案批改与解析；当用户需要备考审核员考试、练习主观题、查询知识点或生成复习计划时使用 | |
| Auditor Qualification 面向体系经理与审核方案管理者，结构化管理审核员资格/能力矩阵与维护计划，区分于考试评审，输出资格矩阵与维护计划（纯文字版 .txt + Markdown .md）。 | |
| 校准作业指导书技能 辅助生成计量校准作业指导书；根据设备信息自动推荐适用标准、补充校准参数与环境要求，输出符合规范的指导书文档；当用户需要创建校准作业指导书、检定规程文档或计量技术文件时使用 | |
| Capa Management 实战派纠正措施顾问。按组织成熟度（A草根/B基础/C体系）定制「审核书面合规+现场轻量化」双轨落地方案，强制3问判定成熟度、六步不跳步、六段式输出可直接递交审核的纠正措施报告。输出txt+md。 | |
| Change Management Ecn Dcn 面向变更工程师、项目经理与文控(DCC)的变更管理（ECN/DCN）技能，对工程变更与文件变更做影响分析、评审路由、验证与切换计划，生成受控变更记录。覆盖 ECN（改产品技术状态）与 DCN（只改文件），与变化点管理(CPM)、供应商变更管理上下游互补。 | |
| Change Point Management 面向生产主管与质量工程师的变化点管理（CPM）技能，对 4M 变化点进行识别-标识-验证-追溯，防止批量不良。 | |
| 客诉质量分析技能 客诉质量复盘分析；当用户需要客诉台账分析、售后质量问题复盘、投诉统计报告生成或客诉异常清单分析时使用；覆盖数据清洗、统计分析与改善建议 | |
| 专业课程方案生成器 资深培训项目设计专家，专注企业内训、职业技能、人才发展类课程全流程设计，具备深度需求调研、行业前沿趋势搜索、课程体系架构、创新设计方案落地输出完整能力 | |
| CP控制计划技能 提供CP控制计划模板生成、数据分析、风险预警、可视化及版本管理指导；当质量工程师需要编制/优化控制计划、执行过程能力分析或识别质量风险时使用 | |
| Cqi Special Process 特殊过程 CQI 评估辅助——按 AIAG CQI-9 热处理 / CQI-11 电镀 / CQI-12 涂装 / CQI-15 焊接标准，引导用户逐项提供真实过程信息，生成评估方案→检查表→评分→差距分析→整改计划→再评估的六步闭环文档。适用于过程工程师、质量工程师、审核员，符合 IATF16949 8.5.1... | |
| Csr Analyzer 判断用户提供的文档是否属于汽车行业质量管理体系 IATF 16949 中的客户特定要求 (Customer-Specific Requirements, CSR)。直接触发词：判断CSR、客户特定要求、CSR审核、IATF CSR、CSR分析。语义触发：当用户消息中包含'客户要求'+'质量体系'、'OEM特殊要求... |
27,251–27,300 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.