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 |
|---|---|
| context-forensics-mcp angelfmoncada/context-forensics-mcp Enables offline, read-only forensic analysis of Claude Code session transcripts, providing exact token usage, cost estimates, context growth, and compaction suggestions. | |
| Maxify MCP angelfmoncada/maxify-mcp Enables Claude Code and other MCP clients to retrieve exact, budgeted code context from a local TypeScript/JavaScript repository and compress command output while preserving critical lines and recoverable originals. | |
| finance-data-mcp angeliaz/finance-data-mcp Unified financial data access for US, A-share, HK stocks, and FX rates with automatic fallback across multiple data sources. | |
| BharatPay MCP angelina10504/bharatpay-mcp Provides AI agents with Indian fintech utilities including IFSC bank lookups, PAN/GSTIN validation, mutual fund NAVs, UPI VPA identification, pincode lookups, and INR formatting, all with zero authentication and zero cost. | |
| salesforce-verified-mcp angeljd25-ctrl/salesforce-verified-mcp A read-only MCP server for Salesforce that returns verified answers or says it cannot, with an evaluation suite that measures its correctness. | |
| ppa-mcp angelkurten/ppa-mcp Anti-procrastination MCP server using ClickUp for task management. Enables capture, planning, micro-steps, and reflection through tools and prompts. | |
| Google Workspace Directory MCP angeln-halo/google-mcp Read-only MCP server for narrowly scoped Google Workspace user lookups via the Admin SDK Directory API, providing user status, search, aliases, and summary tools with strict domain and trust-boundary controls. | |
| mcp-netdisco angeln-halo/mcp-netdisco Enables MCP clients to perform read-only queries against a Netdisco network management system via its REST API, supporting device searches and other GET requests while handling authentication automatically. | |
| MCP Web Search Pro angeln-halo/mcp-web-search-pro An extended, self-hosted web research server for MCP-compatible clients that provides tools for web search, page fetching, JavaScript rendering, Internet Archive snapshots, and YouTube transcripts. | |
| jianying-draft-mcp angelo236/jianying-draft-mcp A local MCP server that compiles structured editing plans with real media paths and time ranges into validated, editable Jianying drafts. It provides tools for probing media, validating plans, creating drafts, checking status, and installin | |
| DaVinci Resolve MCP Server angelonly/davincimcp Control DaVinci Resolve Studio from MCP clients. Provides tools and resources for editing, color grading, Fusion compositing, audio, playback, and rendering. | |
| DavinciVideoMcp angelonly/davincivideomcp MCP server for DaVinci Resolve video editing, enabling AI agents to execute editing operations, manage creative libraries, and analyze media content. | |
| mcp-whmcs angelorc/mcp-whmcs Enables Claude or any MCP client to manage WHMCS clients, services, orders, invoices, quotes, domains, tickets and system settings through the WHMCS External API, with 128 typed tools plus a generic caller for any of the 162 API actions. In | |
| figma-drive angelostark/stark-figma-drive-mcp Exports frames from Figma and uploads them to Google Drive, with automated folder creation. | |
| fitbit-health-mcp angelovg624/fitbit-health-mcp Exposes Fitbit sleep and recovery data to Claude via the Google Health API, with tools for sleep sessions, sleep summaries, recovery vitals, and raw health data queries. | |
| GSC Analyst Connector angelsmolyaninova-design/gsc-analyst-connector Enables querying Google Search Console data via natural language, providing tools for site traffic analysis, page changes, and optimization opportunities. | |
| Emby.MCP angeltek/emby.mcp Connects an Emby media server to AI clients like Claude Desktop, enabling natural language control of media playback, library browsing, playlist management, and search across your personal media collection. | |
| Image Generation MCP Server angelthebestone/image-gen-mcp Enables image generation and editing via ChatGPT web without API keys, saving images locally with conversation-aware editing. | |
| International Gambling Regulations MCP Server angeltooth/international-gambling-regulations-mcp Enables Claude to search, analyze, and provide detailed information about gambling regulations across multiple jurisdictions, starting with Denmark. | |
| US Gambling Regulations MCP Server angeltooth/us-gambling-regulations-mcp Provides comprehensive gambling licensing information, fee calculations, compliance requirements, and regulatory comparisons across 32 US states and select international jurisdictions for legal professionals and gaming operators. | |
| Playwright MCP angeluis001/playwright-mcp A Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages through structured accessibility snapshots without needing screenshots or visually-tuned models. | |
| PagerDuty MCP Server angelus-h/angelush-pagerduty-mcp-server Enables AI assistants to manage PagerDuty incidents, view alerts, and check on-call schedules with both read-only and write operations. | |
| reader3000-mcp angelux/reader3000-mcp Enables sharing Markdown documents for collaborative review with inline annotations and structured change requests. | |
| arcgis-pro-mcp angelz-yt/arcgis-pro-mcp Drives a live ArcGIS Pro session from Claude via arcpy, enabling layer listing, dataset description, geoprocessing, and project inspection directly against an open project. | |
| rclone-mcp-server angenge/rclone-mcp-server MCP server for the Rclone RC API that enables AI assistants to manage cloud storage remotes, copy/sync files, and list directories through natural language. | |
| SmartCommerce Agent MCP Server angerchen/smartcommerce-agent Provides order, payment, refund, logistics-ticket, and human-handoff tools for e-commerce customer service, enabling agents to query order data, validate access, and create tickets through FastMCP. | |
| SonarQube MCP Server anggakawa/sonarqube-ce-mcp A read-only MCP server that provides AI assistants with structured access to SonarQube projects, issues, metrics, and rules. It enables safe analysis of code quality and security findings through a set of validated, safety-first tools. | |
| MCP-Insomnia anggasct/mcp-insomnia Enables AI agents to create, manage, and execute API collections, requests, and environments in Insomnia-compatible formats. It supports direct synchronization with the local Insomnia app database and importing from OpenAPI, Postman, and cU | |
| Chatbot MCP para gestión de reservas de salas de reuniones anggelie/mcp-local-gesti-n-de-reservas-de-salas-de-reuniones Enables managing meeting room reservations through a conversational interface using Claude's language model and the MCP protocol. | |
| UVG Local MCP Server anggelie/mcp-local-server-uvg Enables local text analysis, statistical calculations, and system information retrieval via the Model Context Protocol over stdio. | |
| Frappe LMS MCP Server anggun-indra/frape-lms-mcp-tools An MCP server that enables AI agents to manage a Frappe LMS instance, including creating courses, chapters, lessons, quizzes, enrollments, batches, and certificates. | |
| social-media-mcp angheljf/social-media-mcp A Model Context Protocol (MCP) server for managing social media posts, currently supporting X (formerly Twitter). | |
| MCP Selenium angiejones/mcp-selenium Enables browser automation using the Selenium WebDriver through MCP, supporting browser management, element location, and both basic and advanced user interactions. | |
| ui-screenshot-mcp angioz/ui-screenshot-mcp Enables searching public UI design libraries (Refero, Mobbin, ScreensDesign, Dribbble) for real app and website screens, downloading them into a category-organized local library that can be searched offline, and capturing screenshots of any | |
| chess-esca-mcp anglerfishchess/esca Hands esca's chess answers to an LLM as JSON: the full state of a position, whether a move is legal and every reason it is not, the named facts, the ECO name, opening-book moves, and PGN read and written. It carries no engine and does no se | |
| Network AI Assistant angoran/git-netai Asynchronous MCP server for unified multi-platform network infrastructure management, providing 97 tools across 10 connectors including SSH, MikroTik, Palo Alto, Aruba, Graylog, LibreNMS, Cisco APIC/NDFC, and Panorama. | |
| Professional Penetration Testing MCP Server angry-althaf/pentest-mcp Provides access to over 40 industry-standard penetration testing tools, including Nmap, SQLMap, and Metasploit, within an isolated Kali Linux Docker container. It enables security professionals to perform comprehensive network reconnaissanc | |
| ACE MCP Server angry-robot-deals/ace-mcp Implements Agentic Context Engineering to create self-improving AI coding assistants that learn from execution feedback and build persistent knowledge playbooks. Reduces token usage by 86.9% while improving code accuracy by 10.6% through in | |
| Sys8 MCP Server angry-robot-deals/mcp-sys8 Provides deterministic system information and developer utilities including date/time operations, OS details, math calculations, random data generation, hashing, text formatting, data validation, encoding/decoding, and log analysis. | |
| Advanced Reasoning MCP Server angrysky56/advanced-reasoning-mcp An MCP server that enhances sequential thinking with meta-cognitive capabilities including confidence tracking, hypothesis testing, and organized memory storage through graph-based libraries and structured JSON documents. | |
| ASEKE Compass Engine MCP Server angrysky56/aseke-compass-mcp Provides structured behavioral analysis grounded in Panksepp's affective neuroscience and pattern matching to understand human intent and behavior through primary emotional systems and transition dynamics. | |
| AST MCP Server angrysky56/ast-mcp-server Provides advanced code structure and semantic analysis through Abstract Syntax Trees (AST) and Abstract Semantic Graphs (ASG) across multiple programming languages. It enables tasks like incremental parsing, complexity analysis, and AST dif | |
| AsterMind-ELM MCP Server angrysky56/astermind-elm-mcp Enables fast, on-device machine learning with production-grade persistence through the Model Context Protocol. It allows instant training of text classifiers using Extreme Learning Machines, with SurrealDB-backed persistence and monitoring. | |
| Cognitive Diagram Navigation MCP Server angrysky56/cognitive-diagram-nav-mcp An advanced MCP server implementing diagrammatic reasoning with memory-augmented spatial exploration, enabling structured chain-of-thought reasoning through visual reasoning spaces. | |
| Coinbase Trade Assistant MCP angrysky56/coinbase-trade-assistant-mcp Provides intelligent cryptocurrency trading assistance using Coinbase Advanced Trade API, with automated technical analysis screening and real-time market insights. | |
| Docker SWISH MCP Server angrysky56/docker-swish-mcp Provides Prolog logic programming integration for Claude via a Docker SWISH container, with persistent notebooks and cognitive architecture support. | |
| LocalREPL MCP Server angrysky56/local-repl-mcp A locally-running Python REPL server that integrates with Claude Desktop through the Model Context Protocol, offering shell bridge, streaming, and operational memory features for secure code experimentation and system automation. | |
| mcp_coordinator angrysky56/mcp_coordinator A self-improving coding agent MCP server that enables code execution, semantic memory, and reusable skills via sub-agents, turning your AI client into a meta-operating system. | |
| MCP-Creator-MCP angrysky56/mcp-creator-mcp A meta-MCP server that helps users create new MCP servers through AI guidance, templates, and streamlined workflows, transforming ideas into production-ready implementations with minimal effort. | |
| MCP Diagram Server angrysky56/mcp-diagram-server Enables creating, manipulating, and managing Mermaid diagrams with automatic saving and multi-format conversion from JSON, CSV, Python, Markdown, and plain text. |
29,001–29,050 of 115,409
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.