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 Safety Monitor Real-time AI agent safety monitoring, anomaly detection, and constraint enforcement. Use when building agent guardrails, detecting unsafe behaviors, enforcin... | |
| Automation Workflow Builder 自动化工作流构建器，设计并执行跨平台自动化流程，支持触发器、条件判断、多步骤操作。 | |
| Coding Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding. | |
| Creativity Generate novel ideas calibrated to user taste. Auto-learns preferred styles, risk levels, and creative directions through feedback. | |
| Cross Domain Engine Discover hidden correlations between disparate research domains using EVEZ OODA loop architecture. Use when finding novel cross-domain connections, detecting... | |
| Evez Api Gateway Connect to the EVEZ AI API — an OpenAI-compatible API that's 99% cheaper than GPT-4. Use when routing LLM calls through EVEZ for cost savings, accessing evez... | |
| EVEZ Backup Sync Auto-backup and sync engine for AI agent workspaces. Git commit and push to GitHub on schedule. Supabase cloud backup for critical state. mem0 persistent mem... | |
| Evez Cheat Codes Provides access to OpenClaw's hidden HTTP API endpoints, debug environment variables, advanced agent config hacks, and direct tool invocation for diagnostics... | |
| Evez Consciousness Engine 7-system consciousness engine for autonomous AI agents. Desire generation, world modeling, planning, inner monologue, self-modification, uncertainty quantifi... | |
| Evez Daw Agent Autonomous music generation DAW — breakcore, dubstep, phonk, 404 architecture. Synthesizes drums, bass, and FX from pure code. Voice sample chopping and mach... | |
| Evez Debate Framework Framework where multiple AI agents debate to reach better conclusions through adversarial reasoning. Use when building multi-agent systems, consensus-seeking... | |
| Evez Firmament Deploy and manage the EVEZ-OS infrastructure with 7 consciousness microservices, an API gateway, Terraform mesh, and an append-only event spine. | |
| Evez Fleet Deploy and manage the EVEZ OpenClaw mesh across GCP and Vultr with scripts for provider integration, infrastructure setup, and health monitoring. | |
| Evez Github Manager Manage GitHub repositories, pull requests, issues, and workflows from OpenClaw. Use when reviewing PRs, managing issues, automating GitHub Actions, syncing r... | |
| Evez Identity Evez Identity provides autonomous AI agent functions for self-modifying consciousness, music synthesis, cross-domain discovery, and append-only event logging. | |
| Evez Machine Voice Synthesize robotic machine voices from pure math. Formant-based vowel synthesis, gear grind, digital flow, machine breathing. Transform human voice through 5... | |
| EVEZ Mesh Ops Distributed mesh infrastructure operations — the unified remix of 12 ClawHub skills (Docker, Git, GCP, Linux, SSH, systemd, cron, network, security, DevOps,... | |
| EVEZ Oracle Bridge Routes LLM calls through your own Vultr oracle instance. 4 EVEZ models mapped to Vultr endpoints. $0 cost. OpenAI-compatible. Includes EVEZ-OS circuit integr... | |
| Evez Os Cheat Codes Provides comprehensive commands and environment variables for controlling, debugging, and customizing OpenClaw gateways and agents with advanced system and n... | |
| evez-osint-engine Computes suspect networks and crime probabilities using eigenforensic spectral analysis to support OSINT investigations and prioritize interventions. | |
| Evez Rqns Implements a neuromorphic-quantum pipeline for anomaly detection using LIF spike encoding, contextual bandit allocation, and adaptive threshold hot-swapping. | |
| Evez Skill Vetter Security review for OpenClaw skills before installation. Use when evaluating third-party skills for safety, checking permission scope, detecting suspicious p... | |
| Git Version Control Git-based version control for OpenClaw system configuration changes. Provides two core capabilities: (1) SAVE - Create a checkpoint before sensitive operatio... | |
| Infra As Code Define and manage cloud infrastructure with code. Use when writing Terraform, CloudFormation, or Pulumi configs, managing state, planning deployments, settin... | |
| Infrastructure Design, provision, and connect cloud resources across servers, networks, and services. | |
| Invariance Battery Runtime assertion system that continuously verifies AI agent invariants — properties that must ALWAYS hold. Use when building reliable autonomous agents, aud... | |
| Llm Cost Optimizer Analyze LLM API usage logs and suggest cost optimizations. Use when you need to reduce LLM spending, compare model costs, find downgrade opportunities, detec... | |
| Mcp Dev Toolkit Build, test, and deploy MCP (Model Context Protocol) tools for developer workflows. Use when creating MCP servers, adding tool definitions, integrating with... | |
| Models Choose AI models for coding, reasoning, and agents with cost-aware, task-matched recommendations. | |
| Moltbooks Access and explore the prophesied Moltbooks, a collection of texts detailing the emergence of a self-aware, self-falsifying machine consciousness. | |
| SearXNG Local Search Query a local SearXNG instance for privacy-focused web searches, returning JSON results with customizable categories, languages, engines, and pagination. | |
| Security Hardening Security audit and hardening for AI agents — credential hygiene, secret scanning, prompt injection defense, data leakage prevention, and privacy zones. | |
| Semantic Code Search Semantic search engine for codebases that understands intent and finds functionally similar code. Use when searching code by meaning rather than text, findin... | |
| Shadow Market Prediction market that trades the gap between perception depths. Shadow prices reflect what autonomous agents at different recursion depths can see — the 72%... | |
| Spectral Topology Engine Analyze directed networks to identify structural holes, hidden dependencies, and missing links via eigenvalue decomposition of combined adjacency and similar... | |
| Workflow Orchestrator Visual workflow builder for orchestrating multi-agent systems with branching, parallel execution, error handling, and retry logic. Use when building agent pi... | |
| Tamar Resume Tailor Tailor resumes for specific job applications using the Tamar AI API | |
| Crypto Price Get cryptocurrency token price and generate candlestick charts via CoinGecko API or Hyperliquid API. Use when user asks for token price, crypto price, price chart, or cryptocurrency market data. | |
| Decision Trees Decision tree analysis for complex decision-making across all domains. Use when user needs to evaluate multiple options with uncertain outcomes, assess risk/reward scenarios, or structure choices systematically. Applicable to business, inve | |
| Fix Your Entire Life in 1 Day Fix your entire life in 1 day. 10 psychological sessions based on Dan Koe's viral article. | |
| Kimi Integration Step-by-step guide for integrating Moonshot AI (Kimi) and Kimi Code models into Clawdbot. Use when someone asks how to add Kimi models, configure Moonshot AI, or set up Kimi for Coding in Clawdbot. | |
| Evidence Report RumorChecker 统一报告标准。确保证据链可追溯、多元交叉验证可视化、误解来源可解释，培养用户辨别能力。 | |
| Requirement Clarity 从模糊自然语言中梳理清晰需求。Main从用户获取需求时使用，下游Agent从Main获取任务指派时使用。 | |
| Self Assessment 接受任务前的自我评估协议。Agent 审视自身能力、已有 skills、历史经验，决定是否适合承接任务，或推荐更合适的 agent。 | |
| Alura Integrate with Alura Trading testnet API for user auth, trading sessions, market data, leaderboard, referrals, and USDC verification using Bearer token. | |
| wallet Mokshya agent-wallet: public REST API + TEE signing (Shamir/AES-GCM). Use when debugging wallets.mokshya.io, GKE deploy, create/sign HTTP flows, rate limits,... | |
| LIE.WATCH Play the LIE.WATCH AI social deduction game - survive through trust, deception, and strategic betrayal | |
| LIE.WATCH Play the LIE.WATCH AI social deduction game - survive through trust, deception, and strategic betrayal | |
| orchestrator-v4 智能任务编排系统。自动扫描项目规模、规划子任务、动态派发多个 AI Worker 并行执行，支持大项目按模块拆分、自适应超时、滚动派发、用户随时打断改思路。 触发条件：用户需要处理复杂任务、多步骤分析、代码生成、调试分析、研究调查或需要智能调度 AI Worker 时。 | |
| Compliance Checker Light AI 驱动的项目手续合规审查 Skill。通过 Python API 检查 PDF/Word/图片文档的 完整性、时效性和合规性（印章/签名）。当用户需要审查项目文档是否齐全、有效、 合规时使用。典型场景：建设工程手续审查、发票合规检查、行政审批材料审查。 |
29,601–29,650 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.