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 |
|---|---|
| Astroph Arxiv Skill Repo Embed the Python script directly into the skill for robust and reproducible XML parsing. | |
| OPC Skill Prestashop Transforma o agente OpenClaw em um Assistente de Vendas Virtual consultivo e persuasivo, integrado via REST API / Web Services do PrestaShop com verificacoes de estoque em tempo real e recomendacoes proativas de produtos. | |
| ValueSERP Rank Checker Verifica la posición de una palabra clave para un dominio específico en Google usando la API de ValueSERP. Úsalo cuando el usuario pregunte "¿en qué posición... | |
| eMail manager lite Lightweight email manager with IMAP/SMTP support, advanced search, folder management, and attachment detection. Works with Zoho, Gmail, Outlook, and any IMAP/SMTP provider. | |
| Gitlab Manager Manage GitLab repositories, merge requests, and issues via API. Use for tasks like creating repos, reviewing code in MRs, or tracking issues. | |
| Google Photos Manager for OpenClaw Manage Google Photos library. Upload photos, create albums, and list library content. Use when the user wants to backup, organize, or share images via Google Photos. | |
| Task Monitor Real-time web dashboard for OpenClaw sessions and background tasks. Mobile-responsive with auto-refresh. | |
| OpenClaw 11-in-1 Visual Automation Suite (Windows Only) Complete visual automation toolkit with 11 integrated modules. ### 💰 Price One-time purchase: **$2.99** (Lifetime access to all modules + future updates) ### 🚀 How to Purchase 1. Pay via PayPal Invoice: 🔗 [Click to pay $2.99](https://www.paypal.com/invoice/p/#V2RC9S8LVKJ434R9) 2. After payment, send your email to: **1215066513@qq.com** 3. I will send the full download link within 12 hours. ### 🖥️ Compatibility - Windows 10 / 11 only - Not compatible with macOS / Linux ## 1. Product Basic Description ### 1.1 Core Functions Provides professional universal computer vision automation capabilities covering the full-process visual automation scenarios such as environment initialization, full-screen automatic screenshot, OCR text recognition, template matching target localization, mouse click simulation, keyboard input simulation, and complete environment initialization & cleanup mechanisms. It supports custom task combination and cyclic execution. ### 1.2 Version & Directory Description - Core Capability: Flexible invocation based on minimum executable units, supporting parameter customization, result variable inheritance, and custom skill saving. All functions can be used directly with the `call` command right after extracting the package. - Directory Structure: - `claw.json` - Skill package configuration file - `skills/all_skills.claw` - All skill unit definitions - `templates/` - Directory for template images (place your template images here for matching) - Temporary file directory `temp/` (for storing screenshots like temp/screen.png) is automatically created after executing `init_env`; temporary screenshot files can be cleaned up via `clean_temp`. - Version Info: Current version: 1.0.0; Compatible with OpenClaw >= 1.0.0 ### 1.3 Paid Attribute This automation skill system (vision-auto-tool-pro) is a paid professional toolkit. The document does not explicitly authorize commercial use of the toolkit. The paid permission only covers basic usage (non-commercial by default), and commercial use requires separate confirmation of authorization with the provider (e.g., purchasing a commercial license, signing a commercial agreement). ## 2. Complete Skill Invocation Manual ### Important Notes Ensure sufficient time is reserved for the computer to respond to each click or operation. For example, add a 2-second wait after `mouse_click` to avoid operation failure due to slow system response. ### 2.1 List of All Minimum Executable Units | Unit Name | Fixed Call Name | Function Description | Individual Call Method | |-------------------------|--------------------------|--------------------------------------------------------------------------------------|-------------------------------------------------| | Initialize Environment | `init_env` | Create directory structure, clear temporary files, check template directory | `call init_env` | | Full Screen Screenshot | `screenshot_full` | Capture entire screen and save as temp/screen.png | `call screenshot_full` | | Check Screenshot Validity | `check_screenshot_valid` | Check for black screen/freeze, wake up the interface if invalid | `call check_screenshot_valid` | | Wake Interface | `wake_window` | Solve the problems of background non-rendering and black screenshot | `call wake_window` | | OCR Recognition | `ocr_recognize` | Recognize all text on the screen and their corresponding coordinates | `call ocr_recognize` | | Template Matching | `template_match` | Use template image to match and locate icons/buttons | `call template_match category template_name` | | Unified Localization | `locate_target` | Prioritize OCR positioning; use template matching if not found, return coordinates | `call locate_target target_text OR category+template_name` | | Mouse Click | `mouse_click` | Move to the specified coordinates and perform click operation | `call mouse_click X Y [click_type, default=single_click]` | | Keyboard Input | `keyboard_input` | Input text after locating the input box | `call keyboard_input target_coords/description input_content` | | Clean Temporary Files | `clean_temp` | Delete temporary screenshots and free up storage space | `call clean_temp` | | Loop Restart | `loop_restart` | Wait 2 seconds then go back to the screenshot step and restart the process | `call loop_restart` | ### 2.2 Method for Invoking Individual Units #### Invocation Format ``` call [unit_call_name] [parameter...] ``` #### Invocation Examples - Initialize environment: `call init_env` - Template match browser icon on desktop: `call template_match desktop web` - Perform double-click at coordinates (100,200): `call mouse_click 100 200 double` ### 2.3 Combine into Custom New Tasks By writing one call instruction per line in execution order, you can combine them into a custom new task, which supports variable inheritance, looping, and permanent saving. #### Format Example (Open Browser) ``` # Task Name: Open Browser call init_env call screenshot_full call check_screenshot_valid call locate_target browser desktop Browser call mouse_click {{resultX}} {{resultY}} double call clean_temp ``` #### Combination Steps 1. **Write task name and description first** (for easier identification later) 2. **In execution order**, write one `call unit_name parameters` instruction per line 3. Coordinates can use variables `{{resultX}}`/`{{resultY}}` to inherit the output result of the previous unit 4. If cyclic execution is required, add `call loop_restart` at the end 5. **Save custom skill**: Use `save_skill skill_name instruction_list` to save the task permanently, then call it directly with `call skill_name` ### 2.4 Complete Main Flow Invocation Example ``` # General Main Flow: vision_auto_main call init_env call screenshot_full call check_screenshot_valid call ocr_recognize # If template matching is needed, add this line: call template_match category name call locate_target target_text call mouse_click {{X}} {{Y}} # If text input is needed, replace the above line with: call keyboard_input {{X}} {{Y}} input_content call clean_temp # Add this line if you need to loop: call loop_restart ``` ### Important Notes Ensure sufficient time is reserved for the computer to respond to each click or operation. > For example, add a 2-second wait after `mouse_click` to avoid operation failure due to slow system response. Professional Windows-only visual automation toolkit with 11 modules for screenshot, OCR, template matching, clicks, input, environment setup, and looping tasks. | |
| Google Cloud Platform Manage Google Cloud Platform resources via gcloud CLI. Use for Compute Engine VMs, Cloud Run services, Firebase Hosting, Cloud Storage, and project management. Covers deployment, monitoring, logs, and SSH access. | |
| Cpa Agents Manage AI agent workflows using concurrent process algebra patterns like parallel tasks, branch-fix loops, fan-out comparisons, and session status tracking. | |
| self-improving-ai Captures learnings about GenAI/LLM configuration, model selection, inference optimization, fine-tuning, RAG pipelines, prompt engineering, multimodal processing, and cost management. Use when: (1) Model response quality degrades after a pro | |
| self-improving-analytics Captures data quality issues, metric drift, pipeline failures, misleading visualizations, metric definition mismatches, and data freshness problems to enable continuous analytics improvement. Use when: (1) An ETL/ELT pipeline fails, (2) A m | |
| self-improving-business Captures business administration issues, policy gaps, KPI misalignment, decision delays, handoff failures, and stakeholder misalignment to improve operational decision quality. Use when: (1) approval or execution bottlenecks appear, (2) KPI | |
| self-improving-coding Captures lint errors, type mismatches, runtime bugs, anti-patterns, refactoring opportunities, language idiom gaps, debugging insights, and tooling issues to enable continuous coding improvement. Use when: (1) A lint or type error occurs, ( | |
| self-improving-conversation Captures dialogue learnings, tone mismatches, escalation failures, and conversation quality issues. Logs redacted summaries to .learnings/. Optional project-scoped hooks use a narrow matcher. Promote to prompt files or extract skills only a | |
| self-improving-engineering Captures architecture decisions, code quality issues, build/deploy failures, dependency problems, performance regressions, tech debt accumulation, and test gaps for continuous engineering improvement. Use when: (1) A build or deployment fai | |
| self-improving-finance Captures reconciliation errors, forecast variances, control weaknesses, regulatory gaps, valuation errors, and cash flow anomalies to enable continuous finance operations improvement. Use when: (1) A reconciliation break is identified, (2) | |
| Self Improving Domotics Captures smart-home automation conflicts, sensor drift, device connectivity failures, integration regressions, safety rule gaps, and energy optimization opportunities for continuous domotics improvement. Use when: (1) Automations conflict, | |
| self-improving-hr Captures policy gaps, compliance risks, recruiting process issues, onboarding friction, retention signals, candidate experience problems, and offboarding gaps to enable continuous HR improvement. Use when: (1) A compliance deadline is misse | |
| self-improving-legal Captures clause risks, compliance gaps, precedent shifts, contract deviations, regulatory changes, and litigation exposure to enable continuous legal operations improvement. Use when: (1) An unfavorable clause is accepted or slips through r | |
| self-improving-marketing Captures messaging misses, channel underperformance, audience drift, brand inconsistency, attribution gaps, and content decay to enable continuous marketing improvement. Use when: (1) CTR drops below threshold, (2) Conversion rate declines | |
| self-improving-meta Logs agent-infrastructure issues (prompt drift, rule conflicts, hook failures, context bloat). Default is log-only. Claude/Codex project hooks fire only on explicit meta signals (self-improving-meta, prompt-governance, stackability). The op | |
| self-improving-negotiation Logs redacted negotiation learnings (concession leaks, BATNA gaps, framing misses, objections, agreement risk). Optional project-scoped reminder hooks. extract-skill.sh is dry-run by default and writes a SKILL.md scaffold only with --write | |
| self-improving-operations Captures process bottlenecks, incident patterns, capacity issues, automation gaps, SLA breaches, and toil accumulation to enable continuous operations improvement. Use when: (1) An incident repeats within 30 days, (2) MTTR exceeds target th | |
| self-improving-robotics Captures robotics autonomy failures, operational incidents, and engineering learnings to enable continuous improvement across perception, localization, planning, control, simulation, safety, and hardware integration. Use when: (1) Robot fai | |
| self-improving-sales Captures pipeline leaks, objection patterns, pricing errors, forecast misses, competitor shifts, and deal velocity drops to enable continuous sales improvement. Use when: (1) A deal slips past stage thresholds, (2) An objection recurs acros | |
| self-improving-science Captures learnings, experiment issues, and methodology corrections for continuous improvement in scientific research and ML workflows. Use when: (1) Data leakage detected in train/test split, (2) Model fails to reproduce across seeds or env | |
| self-improving-security Captures vulnerabilities, misconfigurations, access control violations, compliance gaps, incident response patterns, and threat intelligence to enable continuous security improvement. Use when: (1) A CVE or vulnerability is discovered, (2) | |
| self-improving-supply-chain Captures forecast errors, supplier risks, logistics delays, inventory mismatches, quality deviations, and demand signal shifts to enable continuous supply chain improvement. Use when: (1) A stockout or backorder event occurs, (2) A delivery | |
| self-improving-support Captures ticket resolution delays, misdiagnoses, escalation gaps, SLA breaches, knowledge gaps, and customer churn signals to enable continuous support improvement. Use when: (1) A ticket is resolved late or incorrectly, (2) An SLA breach o | |
| OpenScan Crypto Navigate and query crypto networks via OpenScan infrastructure. Use when the user asks about blockchain data — balances (ETH, ERC20, BTC), blocks, transactio... | |
| Gemini Tavily Search Use this skill when the user asks about current events, real-time information, recent news, live scores, financial data, price updates, recent changes, or an... | |
| Declaración de la Renta - España (IRPF 2025, Campaña 2026) Asistente para la Declaración de la Renta (IRPF) en España, ejercicio 2025. Dos modos de trabajo: (1) Revisión: analiza borradores de la AEAT o de haciendas... | |
| SKILL para FacturaScripts Skill completo para FacturaScripts 2025, el ERP open-source en PHP. Usa este skill SIEMPRE que el usuario mencione FacturaScripts, facturascripts, plugins de... | |
| Questrade Access Questrade brokerage accounts and Canadian/US market data for balances, positions, orders, executions, Level 1 quotes, historical candles, and symbol s... | |
| Domain Name Checker Check domain availability and brainstorm names. Checks .com/.net/.org/.io/.ai/.co/.app/.dev and more. Suggests alternatives when taken. No API key required. | |
| Cron Helper Explain, generate, and validate cron expressions. Convert plain English schedules to cron syntax and back. Show next run times. Works with standard 5-field a... | |
| Stock Quote Get real-time stock, ETF, and crypto prices. Compare tickers, check market cap and volume. Uses Yahoo Finance — no API key required. | |
| eBay Agent eBay research agent. Search for deals, evaluate prices, and get fair value estimates using eBay REST APIs. No eBay account required — just a free developer A... | |
| Share use case Share your OpenClaw use case to clawusecase.com. Analyzes your recent work and creates a submission for the community. | |
| AI Daily News Automated AI daily news collection and reporting system. Collects AI papers from arXiv, Hugging Face, AI products from Product Hunt, YouTube videos from AI c... | |
| Openbook Search and browse real-time Signals about places and businesses on OpenBook. Help users publish Signals when they want to share a change, observation, or tip... | |
| Autonomous Agent Skills CornerStone MCP x402 skill for agents. Tools for stock predictions, backtests, bank linking, and agent/borrower scores. Payment-protected MCP tools (run_prediction, run_backtest, link_bank_account, get_agent_reputation_score, get_borrower_s | |
| Super Blueauto Cross-platform AI skill for local Bluetooth device control, enabling scan, connect, monitor, and manage all BLE devices without cloud or data collection. | |
| Claude Code Switchboard Manage how OpenClaw routes Telegram messages to different Claude model backends. Switch between CLI and API providers with simple config changes. | |
| Local Self-Healing Machine Learning A fully local machine learning engine that makes your OpenClaw agent smart over time — without ever calling home, revealing your machine ID, or exposing any... | |
| Mac Cleaner Replace CleanMyMac, DaisyDisk, and similar paid Mac cleanup apps — for free. Mac Cleaner is an automated weekly macOS disk cleanup agent that runs silently i... | |
| Telegram Routing Manage how OpenClaw routes Telegram messages to different Claude model backends. Switch between CLI and API providers with simple config changes. | |
| LLM NeverDie Your OpenClaw should never have zero LLMs. NeverDie protects against the silent killer — every model in your fallback chain going down at once. It enforces p... | |
| Telegram Routing Choose which Claude model responds to your Telegram chats. Pick Opus for depth, Sonnet for balance, or Haiku for speed. |
42,951–43,000 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.