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 |
|---|---|
| kilo-computer-use 123itsfree/kilo-computer-use MCP server that connects AI agents to a real Chrome browser via a WebSocket extension bridge, enabling over 40 browser control tools without debug mode or profile isolation. | |
| Email MCP Server 123jixinyu/email-mcp An MCP server providing comprehensive email capabilities via IMAP and SMTP, enabling AI assistants to read, search, send, manage, schedule, and analyze emails across multiple accounts. | |
| mcp-cv 123justin123/just1-mcp Enables AI assistants to query Justin's resume, including background, projects, skills, and contact details, through natural language. | |
| GeoGebra MCP Server 123pc/geogebra_mcp Lets Claude Code, Codex, and other MCP clients control GeoGebra to create geometric constructions, function graphs, 3D graphics, dynamic mechanisms, and save .ggb or export .png. | |
| JevTrace 123wwwa/jevtrace Enables coding agents to retrieve only the JavaScript/TypeScript code needed for a given task within a token budget, using TypeScript compiler analysis and a decision model to judge relevance. | |
| Artifact Hub MCP Server 123xiaoyi321/artifact-hub A centralized, Git-backed knowledge base and MCP server for teams to store, search, and reuse agent-generated artifacts like skills, specs, plans, reviews, and ADRs, with IDE/Agent integration and a Dashboard for governance. | |
| ContextFS 123yongming/contextfs MCP server for OpenCode that manages context with structured injection, progressive retrieval, and layered storage to keep Agent stable and traceable. | |
| Multi-DB MCP Server 1249zts/db-mcp-service A multi-database MCP server supporting PostgreSQL, ClickHouse, and MySQL that enables database exploration and SQL execution through MCP stdio or HTTP API. | |
| University Content MCP 1250750/school-mcp Provides full-text search and context retrieval from university course materials (PDF, PPTX, DOCX) offline after indexing. | |
| mcp-express-playground 1253william/mcp-express-playground Enables clients to discover and call tools for searching mock shuttle trips by origin, destination, and date, and for holding seats for 10 minutes over Streamable HTTP with bearer authentication. | |
| Seatline Booking MCP Server 1253william/seatline-shuttles Enables searching fixed-route trips by origin, destination and date, holding a seat for ten minutes, generating Paystack payment links, and verifying payments so that bookings are confirmed and ticket references issued only after payment is | |
| agent-memory-mcp 126-colby/agent-memory-mcp Gives AI coding assistants persistent memory by storing, semantically searching, and organizing notes on Cloudflare's free tier. | |
| Citizen MCP Server 12636373/harish-sewasetu-ai Enables citizens and their AI assistants to check scheme eligibility, submit and withdraw pension applications, track status, download acknowledgments, and file grievances through citizen-scoped tools. | |
| shangjiu-guowei 1281227309-art/shangjiu Enables AI assistants to access and query a verified knowledge base of Chinese whisky, including distillery profiles, flavor notes, product recommendations, regional maps, and content generation support. | |
| kdenlive-mcp-server 12bijaya/mcp_server_kdenlive An MCP server that enables AI agents to perform professional video editing in Kdenlive through natural-language instructions, using a typed timeline model and real Kdenlive XML adapter. | |
| Waseda Moodle MCP 12dora/waseda-moodle-mcp Connects Waseda University's Moodle to AI assistants such as Claude, ChatGPT, and Cursor, letting users ask about assignments and deadlines, timetable, syllabus, grades, course updates, forums, and files across all their courses at once. It | |
| mele-memory 12leyin21/mele-memory A long-term memory MCP server for AI companions that lets them store what the user says, let memories fade by importance, emotion and time, and automatically surface relevant ones through semantic recall, people cards, dates, letters and st | |
| Bilibili MCP Server 12qw3er4ty5u-collab/bilibili-mcp-server An MCP server powered by public Bilibili APIs so AI agents can search videos and read public video and creator metadata. | |
| Project Files Read-only MCP 13030109506/project-files-readonly-mcp Enables secure, read-only access to local project files (including text, DOCX, PDF, and XLSX) through MCP, with strict directory whitelisting and no write, edit, or command-execution tools. | |
| Weather MCP Server 13065801223/weather-mcp-bug Enables real-time weather queries for 12 major Chinese cities and global cities via English names using wttr.in, returning current temperature, humidity, conditions, wind speed, and visibility. It also supports listing supported cities and | |
| MCP-RAG 1308495420-dotcom/mcp-rag A modular RAG server with hybrid search and LLM rerank, exposing 3 MCP tools for AI clients like Claude Desktop and Cursor. | |
| lizheng-mcp 1311358729/lizheng-mcp Enables read-only access to geotechnical investigation project databases and official standard data interface files from AI workflows, supporting project summaries, borehole lists, arbitrary table queries, and interface file generation, par | |
| project-memory-mcp 1318176013/project-memory-mcp Stores manual project memories, enables semantic retrieval, and tracks per-memory confidence using PostgreSQL with pgvector and OpenAI-compatible embeddings. | |
| Gold Standard Apology MCP 132262b/crazy-horse-mcp Provides guidelines for writing proper apologies based on the situation, relationship, and severity. Returns structured prompts that help LLMs generate sincere and appropriate apology letters in Korean. | |
| wechat-mcp-server 1335907208/wechat-mcp-server MCP server for reading local WeChat data, enabling AI assistants to query chat history, contacts, sessions, and more via MCP tools. | |
| kali-ssh-mcp 1337exe/kali-ssh-mcp This MCP server connects LLM clients to a persistent Kali Linux VM over SSH, enabling scope-gated nmap, gobuster, nuclei, and nikto scans with structured JSON output and full audit logging. | |
| mcp-stateless-lab 133institute/mcp-stateless-lab A comparative lab demonstrating MCP protocol evolution from stateful (2025-11-25) to stateless (2026-07-28) using a procure-to-pay agent, highlighting the implications for load balancing and session management. | |
| mini-mcp-lab 133institute/mini-mcp-lab A procurement scenario MCP server for testing whether pending work can resume after a service restart, comparing legacy and modern continuation. It uses SQLite for data persistence and demonstrates real MCP protocol messages. | |
| glm4v-mcp 1340896123/glm4v-mcp Enables to analyze images using GLM-4V vision model via the MCP protocol, supporting local file paths and Data URLs. | |
| ecommerce-sourcing-mcp-ai 13739777296-del/ecommerce-sourcing-mcp-ai Automates cross-platform e-commerce sourcing between JD and Taobao using AI-driven browser automation to search, extract product details, compare prices, and identify profitable arbitrage opportunities. | |
| Windows-MCP 13888285815/windows-mcp A lightweight server that enables AI agents to interact natively with the Windows operating system for tasks like UI automation and application control. It allows LLMs to perform file navigation, simulate user input, and manage windows with | |
| WeChat Background MCP 13954nb-hub/wechat-background-mcp An unofficial experimental local MCP server that lets AI clients work with an already logged-in Windows Weixin desktop client, providing bounded conversation and message reads, group and message search, polling of up to 16 selected chats, g | |
| M3Mgine 13auth/m3mgine MCP server enabling AI agents to enforce corrected rules as durable pre-output checks, manage processed memory, and query a temporal knowledge graph. | |
| Video Still Capture MCP 13rac1/videocapture-mcp A Model Context Protocol server that enables AI assistants to access and control webcams through OpenCV, allowing for image capture and camera setting manipulation. | |
| faceton-mcp-server 13shivam/facetron FaceTron is a high-performance face embedding server with ONNX Runtime, dynamic multi-model loading, and MCP-compatible OpenAPI metadata for offline face recognition and detection. | |
| appium-mcp-server 1405942836/appium-mcp Enables AI assistants to perform mobile device automation testing via Appium through the Model Context Protocol, supporting Android and iOS devices with 40+ tools. | |
| cognimem 1421906110/cognimem A cognitive memory MCP server that extracts knowledge as SPO triples, supports semantic recall, contradiction detection, and scientific forgetting, enabling persistent and evolving memory for AI agents. | |
| spine-mcp 1425sd/spine-mcp Local MCP server for automating Spine projects via the official CLI, enabling AI tools to inspect, export, import, and add animations to .spine files. | |
| Sysinternals MCP Server 14ag/systeminternals-mcp Exposes Sysinternals and NirSoft Windows diagnostic binaries as MCP tools with safe subprocess execution. Dynamically registers tools from a binaries directory with built-in security filters for destructive operations. | |
| requirement-asset-recommender 14shi/requirement-asset-recommender This server lets users submit natural-language requirements, screenshots, or Excel files and receive grounded asset-matching recommendations, with an agentic loop that judges sufficiency, iteratively corrects its own search, and explicitly | |
| Coding Tools MCP 1510952971/coding-tools-mcp-windows A local MCP server that gives AI coding assistants read, write, search, and execute capabilities within a specified project directory. This Windows GUI build simplifies setup by eliminating manual Python, Node.js, or Docker installation. | |
| godot-docs-mcp 15195999826/godot-docs-mcp Query Godot Engine documentation with full-text search across classes, methods, properties, and inheritance. | |
| university_rules_mcp_server 1551156271-coder/university-rules-rag-mcp-agent Enables agents to search university rules via hybrid retrieval and reranking, returning the top three relevant source clauses for downstream use. | |
| EdgeOne Pages MCP 15538420886/mcp Enables the deployment of HTML content, folders, and full-stack projects to EdgeOne Pages to generate publicly accessible URLs. It integrates with edge functions and KV storage to provide fast content delivery and supports custom domain con | |
| RunningKnowledgeBase 1556053950/runningknowledgebase A fully local MCP server that imports Markdown, PDF, and web pages into a running knowledge base, providing hybrid search and document retrieval via authenticated Streamable HTTP for Codex and DeepSeek agents. | |
| TrendRadar 15642875149/trendradar Enables AI-driven public opinion monitoring and trend analysis with multi-platform aggregation, smart alerts, and natural language interaction via MCP. | |
| Doubao Image/Video Generation MCP Server 156554395/doubao-image-video-mcp Enables AI image generation using Doubao Seedream models and video generation using Doubao Seedance models through Volcano Engine's API, supporting text-to-image, image-to-image, text-to-video, and task status queries. | |
| image-video-generation-mcp 156554395/image-video-generation-mcp Enables image and video generation using BigModel AI's CogView and CogVideoX models via MCP, supporting batch image generation and various configuration options. | |
| Tencent Cloud COS MCP Server 156554395/tx-cos-mcp Enables interaction with Tencent Cloud Object Storage (COS) through MCP protocol. Supports file upload, download, deletion, listing objects, and generating temporary signed URLs for cloud storage management. | |
| zentao-helper 15913581118/zentao-helper MCP server that lets clients drive a ZenTao instance through its REST API v2, exposing 119 OpenAPI-defined operations plus plan, story, and assignment query helpers for common lookups. Enables reading and writing ZenTao data — including sto |
21,751–21,800 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.