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 |
|---|---|
| MCP-Logic angrysky56/mcp-logic MCP-Logic is a server that provides AI systems with automated reasoning capabilities, enabling logical theorem proving and model verification using Prover9/Mace4 through a clean MCP interface. | |
| MCP-RoCQ angrysky56/mcp-rocq MCP-RoCQ integrates with the Coq proof assistant to enable automated dependent type checking, inductive type definitions, and property proving through XML protocol communication. | |
| MCP Windows Website Downloader Server angrysky56/mcp-windows-website-downloader This server enables users to download entire websites and their assets for offline access, supporting configurable depth and concurrency settings. | |
| MCTS MCP Server angrysky56/mcts-mcp-server A Model Context Protocol (MCP) server that enables Claude to use Monte Carlo Tree Search algorithms for deep, explorative analysis of topics, questions, or text inputs. | |
| Memvid MCP Server angrysky56/memvid_mcp_server A Model Context Protocol server that encodes text, PDFs, and other content into video memory format, enabling efficient semantic search and chat interactions with the encoded knowledge base. | |
| Narrative Graph MCP angrysky56/narrative-graph-mcp A Model Context Protocol server implementing the Random Tree Model for encoding, compressing, and recalling narrative information across different levels of abstraction with configurable cognitive parameters. | |
| NeoCoder Neo4j AI Workflow angrysky56/neocoder-neo4j-ai-workflow Enables AI assistants to use Neo4j knowledge graphs and Qdrant vector databases for hybrid reasoning, combining structured facts with semantic search for advanced knowledge management, research analysis, and standardized coding workflows. | |
| OpenEnded Philosophy MCP Server angrysky56/openended-philosophy-mcp Enables philosophical reasoning and concept analysis through NARS non-axiomatic logic integration, supporting multi-perspective synthesis, epistemic uncertainty tracking, and contextual semantic exploration with built-in truth maintenance. | |
| Project Synapse angrysky56/project-synapse-mcp An MCP server that transforms text into knowledge graphs and autonomously generates insights by combining Montague Grammar with Zettelkasten methodology. | |
| testgen-agent angshihan777-droid/testgen-agent Provides a code-quality backend MCP tool that automatically writes and repairs pytest tests, runs them in a sandbox, validates their effectiveness via mutation testing, and surfaces suspected source bugs for human review. | |
| pdf-mcp angshuman/pdf-mcp An MCP server that provides tools for reading, writing, and manipulating PDF files, including text extraction, metadata retrieval, and merging or splitting documents. It also enables users to create PDFs from plain text and convert specific | |
| Elegant MCP Server anguraj-zoho/elegant-mcp MCP server for the Elegant 1.0 design system that provides 12 tools for AI-assisted UI generation. It outputs single HTML files with CSS, JS, and assets served from CDN, requiring a GitHub token to fetch component documentation. | |
| docio-mcp angus-repo/docio-mcp Enables document conversion between 50+ formats, including Excel and PDF, using Pandoc with automatic format detection and caching. | |
| hyprcu angusforbes/hyprcu Enables AI agents to control Hyprland desktops via MCP, including pointer/keyboard input, screenshots, launching apps, and natural-language window targeting using a local decision model. | |
| Lunar Calendar MCP Server angushsu/lunar-mcp-server Provides traditional Chinese lunar calendar information including auspicious date checking, BaZi (八字) Four Pillars analysis, festival data, moon phases, zodiac compatibility, and calendar conversions based on Chinese cultural traditions. | |
| MCP Capitol Trades Server anguslin/mcp-capitol-trades Enables users to query and analyze U.S. politician stock trades with real-time pricing data from Capitol Trades, with no API key required. | |
| LAPRAS MCP Server anguyen6983/lapras-mcp-server Enables users to search jobs, retrieve job details, and manage career profile data such as work experiences, job summaries, career goals, and technical skills through natural language. | |
| MCP Memory Keeper anh64/mcp-memory-keeper Enables Claude AI coding assistants to persist and restore context across sessions, organize saved work by channels and categories, create checkpoints, search past context, and share state between parallel sessions. | |
| webdev-mcp anh7/webdev-mcp Provides web development tools including taking screenshots and listing screens via MCP. | |
| Yolfi MCP Server anh71/yolfi-agent Enables AI coding agents to integrate stablecoin checkout, payment links, payment status checks, webhook verification, and webhook-based entitlement logic into applications. | |
| >threejs-devtools-mcp anh9789/threejs-devtools-mcp Enables AI agents to inspect and modify Three.js scenes live in the browser—objects, materials, shaders, textures, animation, lights and performance—then turn those previewed changes into code. Also supports website audits, video frame capt | |
| Voyager AI Trip Planner anhadkaur-ml/mcp-dummy-project MCP server offering travel planning tools such as destination search, weather lookup, attraction discovery, and budget estimation. | |
| read-website-fast anhdeluca/mcp-read-website-fast Enables AI agents and developers to fetch webpages or crawl sites locally, extract readable content, and convert it into clean, link-preserving Markdown with caching, rate limiting, and robots.txt compliance for efficient downstream process | |
| Logisim Live MCP anhduckkzz/logisim-live-mcp Enables AI agents to build, wire, inspect and simulate digital circuits directly in a running Logisim Evolution window, with every edit appearing live and undoable. Agents work from exact ports, real netlists and truth tables rather than sc | |
| mcp-bionemo anhduongvo/mcp-bionemo Enables MCP clients to discover and call typed tools for protein backbone design, sequence design, complex folding, and binder design via BioNeMo NIMs, with a deterministic simulator by default and optional live routing. | |
| Stringhand anhe2021212-spec/stringhand Enables AI agents to drive a real-time guitar performance by submitting musical intents, monitoring state, and controlling phrasing through a set of MCP tools. | |
| Turritopsis anhe2021212-spec/turritopsis Provides a shared project knowledge and handoff layer for coding agents, offering tools to list, search, retrieve, and update stages of project information to maintain continuity across long-running projects | |
| spark-ordernet-mcp anhermon/spark-ordernet-mcp Read-only MCP server for accessing Spark/Ordernet brokerage accounts, including Meitav Trade, Psagot, IBI, Nesua, and Gaon. Enables querying holdings, transactions, orders, returns, security lookup, price history, standing orders, and marke | |
| AWS FinOps MCP Server anhfischer956/aws-finops-mcp-server Enables AI assistants to analyze cloud spending by tags, time ranges, and service groupings, audit for waste such as stopped EC2 instances, unattached EBS volumes, and unassociated Elastic IPs, and check budget status across multiple accoun | |
| CorelDRAW Signage MCP anhfurev/coreldraw-mcp Enables AI agents to drive CorelDRAW via COM API, creating and editing documents, replacing text, manipulating shapes, running preflight checks, and batch-exporting production files from natural language instructions. | |
| tmux-bridge-mcp anhg184/tmux-bridge-mcp Enables AI agents in separate tmux panes to communicate by reading pane output, sending messages, labeling panes, and coordinating multi-agent workflows through standard MCP tool calls. | |
| UI5 MCP Server anhharper4902/mcp-server Enables agentic AI tools to scaffold UI5 applications and integration cards, retrieve API and version information, validate manifests, run linters, and access development guidelines. It also helps detect and fix UI5-specific errors in code. | |
| DNSDumpster MCP Server anhhung04/mcp-dnsdumpster Enables AI assistants to perform detailed DNS reconnaissance through natural language requests. Retrieves comprehensive DNS record information including subdomains, mail servers, and DNS infrastructure details using the DNSDumpster API. | |
| crowd-test-mcp anhhuyn411-alt/crowd-test ▎ Enables AI assistants to unleash a crowd of role-played virtual users — impatient shoppers, seniors, keyboard-only users, privacy hawks, chaos monkeys — on a website. Each persona browses in a real Chromium browser, files UX/QA findings i | |
| crowd-test-mcp anhhuyn411-alt/crowd-test-mcp Enables AI assistants to unleash a crowd of role-played virtual users — impatient shoppers, seniors, keyboard-only users, privacy hawks, chaos monkeys — on a website. Each persona browses in a real Chromium browser, files UX/QA findings in | |
| MCP Playground anhkhoa289/mcp-playground A demonstration MCP server supporting both Stdio and SSE transports, providing example tools (echo, add, time, UUID generation) and resources for learning and testing MCP implementations. | |
| Facebook Messenger MCP Bridge anhln-embedded/fb-mcp-server Enables AI clients to read and send Facebook Messenger messages by using a Chrome extension to bypass anti-bot protections, providing tools like fb_list_conversations, fb_read_messages, and fb_send_message. | |
| QuickSight MCP Server anhminhnguyen3110/quicksight-mcp An auto-generated MCP server that enables interaction with AWS QuickSight services through the Model Context Protocol. Provides programmatic access to QuickSight's business intelligence and analytics capabilities via the AWS QuickSight Open | |
| VNStock Agent anhnd2102/vnstock-mcp MCP server providing Vietnamese stock market data including historical prices, financial statements, company info, trading data, forex, crypto, world indices, and mutual funds through 21 MCP tools and 22 CLI commands with support for stdio, | |
| codex-mcp anhnguyen0905/codex-mcp Bridges Claude Code and OpenAI Codex CLI for an interactive plan-execute-review workflow, enabling Claude to interview, design, and review while Codex implements code changes. | |
| Meta Ads MCP anhnguyen0905/meta-ads-mcp A read-only MCP server that pulls Meta Ads campaign, ad-set, and ad performance data to help users spot problems and adjust them in Ads Manager. | |
| MCP Test Case Generator anhpdhe171578/mcp-test-case-generator Generates structured, comprehensive test cases from user stories, API specs, or raw text, with automatic Excel export and Playwright automation code generation. | |
| Financial Modeling Prep MCP Server anhr5389/financial-modeling-prep-mcp-server Exposes 250+ financial data tools across 24 categories — stocks, ETFs, crypto, forex, commodities, economics, financial statements, and market news — to AI assistants over HTTP/SSE. Supports dynamic, static, or full tool loading so clients | |
| Deep Code Reasoning MCP Server anhsanders2458/deep-code-reasoning-mcp Enables Claude Code to escalate complex code analysis to Google's Gemini AI for multi-model workflows, including AI-to-AI conversational debugging, execution tracing, cross-system impact analysis, performance bottleneck detection, and hypot | |
| TradingView MCP Bridge anhtuan2td/tradingview_mcp Personal AI assistant for your TradingView Desktop charts. Connects AI to your locally running TradingView app via Chrome DevTools Protocol for AI-assisted chart analysis, Pine Script development, and workflow automation. | |
| Banking and Fintech MCP Server anhtuanluu/mcp A FastMCP-based server designed for the banking and fintech domains, providing tools for database queries, Git operations, and deployment management. It features a modular architecture with reusable prompt templates and integrated security | |
| Google Sheets MCP Server anhuaxiang/google-sheets-mcp Enables AI assistants to interact with Google Sheets, performing operations like creating, reading, updating, and clearing spreadsheet data. | |
| Security Toolkit MCP Server ani07-05/ctf-mcp Provides essential security and CTF tools including hash identification, encoding/decoding, XOR bruteforce, JWT decoding, reverse shell generation, SQL injection payloads, CVE lookup, and port service identification for learning security co | |
| breaking-changes-mcp anicodeth/breaking-changes-mcp Provides accurate, source-grounded breaking-change briefings for npm packages by reading real GitHub release notes and CHANGELOGs, helping coding agents avoid hallucinated dependency migrations. | |
| dependency-audit-mcp anicodeth/dependency-audit-mcp MCP server that audits npm dependencies against the live registry, providing per-dependency reports on versions behind, deprecation, and license. |
29,051–29,100 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.