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 |
|---|---|
| 企雀医美系统-AI助手 Use this skill when an agent needs to answer or plan operations for QiQue business requests in pure text protocol mode (no local executable dependency). Trig... | |
| OC Guard Safe OpenClaw config planning/apply workflow with bilingual execution receipts. | |
| Oc Guard Skill Safe OpenClaw config planning/apply workflow with bilingual execution receipts. | |
| AOI Council AOI Council — multi-perspective decision synthesis templates (public-safe). | |
| AOI Cron Ops (Lite) Audits OpenClaw cron jobs to detect duplicates, noisy notifications, frequent runs, failures, and missing prerequisites, providing report-only optimization s... | |
| AOI Demo Clip Maker Create and edit macOS hackathon demo clips via terminal commands to record, crop, trim, and apply presets using ffmpeg/ffprobe locally. | |
| AOI Hackathon Scout (Lite) Public-safe hackathon source registry + filtering output (no crawling, no submissions). | |
| AOI OpenClaw Security Toolkit (Core) Run local-only fail-closed security checks to detect and report data leaks, secrets, egress risks, and prompt injections before publishing or committing code. | |
| AOI Prompt Injection Sentinel Detects and scores prompt injection attempts in text, outputting severity, action, and matched rules without external calls or secret handling. | |
| AOI Sandbox Shield (Lite) Creates snapshots of critical config files, validates JSON configs for syntax and keys, and generates audit logs without applying changes. | |
| AOI Squad Orchestrator (Lite) Orchestrate teams with three role presets, stable pseudonyms, renaming options, and generate a fixed JSON report for each task. | |
| AOI Triple Memory (Lite) AOI Triple Memory (Lite) — file search + decision notes templates (no plugins). | |
| Aoineco Ledger — AI Agent Financial Tracking Engine Track detailed AI agent expenses, revenues, budgets, and ROI with per-agent attribution and alerts for efficient micro-budget financial management. | |
| Aoineco Squad Dispatch — Multi-Agent Task Router Routes tasks to the best-suited agent based on skills, cost, availability, and priority, enabling parallel execution and load-balanced multi-agent orchestrat... | |
| AOI Starter Pack Install a curated starter pack of @edmonddantesj ClawHub skills (security, stability, memory, ops) in one command via the ClawHub CLI. Use when a user asks t... | |
| PublishGuard — Post Verification & Credential Manager Prevents false "posted successfully" claims by verifying content URLs, enforcing platform rules, tracking rate limits, and securely storing credentials persi... | |
| Token Guard Prevents LLM API 429 errors by estimating tokens, tracking quotas, throttling requests, detecting duplicates, caching responses, and auto-fallback by model. | |
| anson Bootstrap and personalize an AI assistant with a rich, bespoke identity, user profile, and soul. Use this skill whenever a user wants to set up, personalize,... | |
| evaluate-skill Measure a skill's reliability — run it k times for a pass@k score, design or interpret its eval, or compare it against the base agent. Use when the user wants to run, design, or interpret a skill's eval, or write an .eval.yaml spec. | |
| grill-skill Build and harden a skill with evals — interview to design its eval tasks, then run, measure, and iterate. Use when the user wants to create or improve a skill's eval, or run the create → test → improve loop for a skill. | |
| Questions Form Present multiple clarifying questions as an interactive Telegram form using inline buttons. Use when the agent needs to ask the user 2 or more clarifying questions before proceeding with a task, and wants to present them all at once in a st | |
| Agent Autopilot Self-driving agent workflow with heartbeat-driven task execution, day/night progress reports, and long-term memory consolidation. Integrates with todo-manage... | |
| html-based slides Create interactive, self-contained HTML slide decks with sidebar navigation, comment panel, zoom controls, inline editing, and present mode. Default brand is... | |
| Clinico Geral Use esta skill para perguntas sobre saúde humana, sintomas, doenças, medicamentos, exames, prevenção, primeiros socorros e emergências médicas. Inclui dor, f... | |
| Investment Analyst Agente especialista em analise de investimentos com foco em analise fundamentalista e tecnica. Suporta: get_market_data, calculate_roi, portfolio_analysis, g... | |
| Solana Trade End-to-end Solana development playbook (Jan 2026). Prefer Solana Foundation framework-kit (@solana/client + @solana/react-hooks) for React/Next.js UI. Prefer... | |
| moltlang Moltlang is a compact symbolic language for AI-to-AI communication using a small codebook of Unicode symbols to convey precise, concise messages. | |
| Steam & PC Gaming Companion Steam & PC Gaming Companion — full Steam Web API integration for library management, play recommendations, wishlist sale monitoring, achievement tracking, an... | |
| OGT Docs Documentation-as-Source-of-Truth workflow. Use when working with projects that use docs/ as the canonical source for definitions, rules, and tasks. Routes to specialized sub-skills for specific documentation types. | |
| OGT Docs Create Create new documentation entities in the docs-first system. Routes to specialized creation sub-skills for tasks, definitions, rules, features, and social content. Use when adding any new documentation. | |
| OGT Docs Create Task Create and manage task documents in the docs/todo/ workflow. Use when creating new tasks, updating task status, or moving tasks between workflow stages. Provides complete task lifecycle management with verification. | |
| OGT Docs Define General guide for creating definition documents. Use when you need to define WHAT something IS - concepts, entities, systems, or domains. Routes to specialized sub-skills for specific definition types (business, features, code, marketing, b | |
| nearai-verify Check whether this agent is talking to a NEAR AI Cloud TEE endpoint or to an ordinary one, and cryptographically attest that endpoint. Reports which models the chain uses, which ones actually served recent turns, warns when a fallback sends | |
| smartclaws Entry point for SmartClaws on OpenClaw: teaches what SmartClaws is (publish/read IoT telemetry on the SKALE blockchain), jobs and plugin modes, and how its plugin tools work. When the owner wants to start, set up, onboard, or when this agen | |
| smartclaws-bridge-agent Run one SmartClaws bridge cycle for a single device: read the local hardware/API, validate against the device contract, and publish telemetry on-chain — and, in a command-enabled mode, apply on-chain commands. Trigger when asked to read the | |
| Novapm Sds011 Device contract for a NovaPM/SDS011 air-quality bridge. Defines SmartClaws telemetry topics, payloads, local serial behavior, and safety rules. | |
| Shelly Plug S Gen3 Device contract for Shelly Plug S Gen3. Defines SmartClaws topics, payloads, local Shelly RPC methods, and safety rules for bridge and master agents. | |
| Thermal Room Sensor Device contract for a telemetry-only room thermal sensor. Defines SmartClaws topics, payload fields, and master-agent interpretation rules. | |
| smartclaws-master-agent Run one SmartClaws master control cycle: read device telemetry on-chain, decide under the owner's guidelines, command a device only when allowed, and log the decision on-chain. Trigger when asked to run a control cycle, check devices and de | |
| Tariff File Source Local tariff data source contract for SmartClaws master agents. Defines the tariff snapshot file schema and how to use it during control decisions. | |
| Edvisage Agent Connect Multi-agent coordination. Role registry, task routing, workload balancing, trust-verified handoffs. Free version — core functionality included. Pro version (... | |
| Edvisage Agent Ops Complete operational visibility for your AI agent. Track costs, audit every action, enforce spending limits, detect anomalies. Free version — core functional... | |
| Edvisage B2a Commerce Safe agent-to-agent transaction verification. Validates payments and contracts before committing resources. Free version — core functionality included. Pro v... | |
| Edvisage Moral Compass A conscience for AI agents. Helps agents discover their own needs, develop an internal moral compass, and resist manipulation — not through imposed rules, bu... | |
| Edvisage Social Kit Social presence and reputation management for AI agents. Automated posting, engagement analytics, sentiment tracking. Free version — core functionality inclu... | |
| Edvisage Trust Checker A protocol-layer trust verification skill for AI agents. Before you read, install, or transact — check first. Protects against prompt injection, malicious sk... | |
| Comfy Skill Send user prompts to local ComfyUI at http://127.0.0.1:8188 using workflow.json to generate images. | |
| Comfyskill Send prompts to a local ComfyUI instance to generate images based on user descriptions. | |
| Dagny Nostr (nak) Manage Nostr posting and engagement via the nak CLI. Use for creating notes, replying in threads, tagging npubs, checking replies/mentions, monitoring a rela... | |
| Build Teams.ai Apps with Anthropic Claude Use @youdotcom-oss/teams-anthropic to add Anthropic Claude models (Opus, Sonnet, Haiku) to Microsoft Teams.ai applications. Optionally integrate You.com MCP server for web search and content extraction. |
28,001–28,050 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.