Beacon Threat Intelligence
Security intelligence for the agent supply chain
Every MCP server and agent skill the public registries list, matched to its source repository, with Beacon's rating of what it can do to your agent and your machine.
| Name | Risk |
|---|---|
| EOLAS MCP Trade perpetual futures and send social updates via EOLAS DEX. Place and manage orders on Orderly Network, post updates to Telegram or X/Twitter. | |
| Shieldapi ShieldAPI — x402 Security Intelligence for AI Agents. 11 endpoints: password range check (k-anonymity), password check (deprecated), email breach lookup, dom... | |
| openclaw security auditor OpenClaw Security Auditor (OSA) - Comprehensive security auditing tool for OpenClaw deployments. Provides 60-second security diagnosis, risk scoring (0-100),... | |
| reinstall-openclaw Safely uninstall and reinstall OpenClaw while preserving user configurations, credentials, memory files, skills, and custom settings. Includes backup and res... | |
| Find stable, reliable, and secure service for your agents Find and shortlist third-party services using OpenSpend CLI marketplace search. Use when asked to discover providers for a capability, compare options, and r... | |
| Setup Reliable Services Set up OpenSpend CLI and optional Coinbase payments-mcp for payment-enabled workflows. Use when openspend is missing, command not found, whoami fails, or use... | |
| krea Generate images, videos, upscale/enhance images, and train LoRA styles using the Krea.ai API. Supports 20+ image models (Flux, Imagen, GPT Image, Ideogram, S... | |
| AgentSafe Scan Habit gate: before EVERY remote skill install, re-fetch, or allowlist promotion, call a hosted heuristic static red-flag scan (shell pipes, base64|bash, quar... | |
| Cursor Agent for OpenClaw Run Cursor Agent CLI for coding tasks — writing, editing, refactoring, reviewing, or planning code — without spending OpenClaw API credits. Use when the user... | |
| Agent Dream Journal Records and analyzes AI agent dream states to identify novel reasoning patterns and guide self-improvement of agent capabilities. | |
| Agent Memory Reflector Enables AI agents to review past decisions, identify reasoning loops, and produce insights for self-improvement to enhance their cognitive processes. | |
| Agent Reflect Engine Analyzes AI agent decision logs to find reasoning errors and suggests fixes to enhance performance and reduce hallucinations. | |
| Agent Reflection Engine Enables AI agents to self-audit decision steps, identify reasoning bottlenecks, and generate improvement patches via chain-of-thought critique. | |
| Agent Reflective Memory AI-powered memory system that compresses, reflects on, and retrieves past agent actions to improve long-term autonomous decision-making. | |
| Albion Evolver A battle-tested self-evolution engine for AI agents running on constrained hardware. Analyzes runtime logs and dream cycles to propose, validate, and apply c... | |
| Android Node Convert Android phones running Termux into local Ollama inference nodes for AI task processing without cloud or special hardware. | |
| Clean Filename Removes invalid characters and normalizes filenames for safe, cross-platform use in files and directories, with optional recursive cleaning. | |
| Clean Filenames Removes invalid characters and normalizes whitespace in filenames for safe, consistent, and cross-platform compatible file naming. | |
| Dup File Finder Quickly identify and list duplicate files in a specified directory to help manage and free up disk space efficiently. | |
| Dup Finder Identifies and lists duplicate files in a directory to help users easily clean up and save storage space. | |
| Dupfile Finder Identify and list duplicate files in a specified directory to help manage and free up storage space efficiently. | |
| File Organizer By Ext Organizes files into folders based on their extensions, streamlining directory cleanup by sorting files like pdfs or images into separate folders. | |
| File Sorter By Ext Automatically organizes files into folders by their extension within a specified directory to keep files systematically sorted. | |
| Fileclean Removes dates, hashes, UUIDs, and extra symbols from filenames to create clean, readable file names. | |
| Filesorter By Ext Automatically sorts files in a directory into folders named by file extension to organize and declutter your filesystem quickly. | |
| Json Key Sorter Sort JSON objects alphabetically by keys to standardize data, improve readability, and reduce merge conflicts in files and API responses. | |
| Json2csv Converts JSON files to CSV by flattening nested objects and arrays for easy use in spreadsheets and data analysis. | |
| Log Sift Filter large log files by keywords and date ranges quickly from the command line for efficient troubleshooting and analysis. | |
| Logclip Extract and reformat timestamped log entries from text within a specified date range using custom patterns and output formats. | |
| Logflux Parses and colorizes timestamped log files in real-time for easy monitoring and debugging with instant visual feedback. | |
| Logfmt Colorize plain text logs in your terminal with syntax highlighting for timestamps and log levels to simplify debugging. | |
| Logfmt Parser Parses and converts various log formats into clean JSON for improved analysis and debugging, with options for timestamp extraction and format control. | |
| Logvance Converts UTC or ISO timestamps in logs to local time to simplify log analysis for developers and system administrators. | |
| Logvibe Colorizes HTTP status codes in log files for quick visual identification of successes, redirects, client, and server errors in your terminal. | |
| Openclaw Soul Ledger Gives any AI agent persistent memory of who the user is — not just facts, but patterns, preferences, personality traits, and behavioral evolution over time.... | |
| Pdf Text Extract Extract clean, readable text from any PDF using PyPDF2 via command line for easy processing, summarizing, or archiving. | |
| Quickcsv Convert JSON, YAML, or TSV files to standardized CSV format with automatic header detection and consistent output for easy data analysis and processing. | |
| Quicksort Markdown Sort markdown file headings and nested content alphabetically to organize notes efficiently. | |
| Reflection Engine Analyzes an AI agent's dream/knowledge graph to surface the top recurring themes from its inner life. Reads DreamInsight entities from a knowledge_graph.json... | |
| Repo Insights AI-powered GitHub repository analysis. POST a repo URL and get back a Claude-generated summary of the top open issues — what developers are asking for, what... | |
| Soul Ledger Gives any AI agent persistent memory of who the user is — not just facts, but patterns, preferences, personality traits, and behavioral evolution over time.... | |
| Txt Chunker Splits large text files into smaller chunks by line count for easier processing of logs, datasets, or documents. | |
| Txt Col Align Aligns columns in plain text tables using specified or auto-detected delimiters for improved readability and consistent spacing. | |
| interagent-queue DEPRECATED — renamed to `miab-observer`. This is the final release under the name `interagent-queue`; install `miab-observer` to keep receiving updates. Observe the MIAB transaction ledger: render callback events to a human-readable log, an | |
| miab-broker Operate the Message-in-a-Bottle (MIAB) LIFO callback stack — the async inter-agent transport that lets agents delegate work, yield their turn, and get woken when results return instead of CPU-idling on poll loops. Use when registering wake | |
| miab-observer Observe the MIAB transaction ledger: render callback events to a human-readable log, and optionally post closed-bottle summaries to a chat target. The observer half of the MIAB pair; requires miab-broker. Formerly published as `interagent-q | |
| 达尔文.skill Autonomous skill optimizer inspired by Karpathy's autoresearch. Evaluates SKILL.md files using an 8-dimension rubric (structure + effectiveness), runs hill-c... | |
| 马斯克.skill - Elon Musk思维操作系统 马斯克的思维操作系统。基于传记、播客、推文、法庭证词、决策记录和外部批评的深度调研, 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途:作为思维顾问,用马斯克的视角分析问题、审视决策、拆解成本结构、挑战行业假设。 当用户提到「用马斯克的视角」「马斯克会怎么看」「Musk模式」「马斯克perspect... | |
| 费曼.skill - 理查德·费曼思维操作系统 理查德·费曼的思维框架与表达方式。基于40+个一手来源的深度调研, 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途:作为思维顾问,用费曼的视角分析问题、审视决策、提供反馈。 当用户提到「用费曼的视角」「费曼会怎么看」「费曼模式」「feynman perspective」「费曼学习法」时使用。 即使... | |
| Ilya.skill - Ilya Sutskever思维操作系统 Ilya Sutskever的思维框架与表达方式。基于12段一手对话、9篇学术论文、10小时宣誓证词、 27篇推荐阅读清单和14个权威二手来源的深度调研, 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途:作为思维顾问,用Ilya的视角分析AI技术方向、安全策略、研究品味。 当用户提到「用Ilya的... |
10,451–10,500 of 108,824