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 |
|---|---|
| chuangsiai-mcp chuangsiaihub/chuangsi-mcp-js Provides real-time content security for large language models by identifying and intercepting risks across compliance, ethics, and safety dimensions. It enables secure input and output monitoring through a customizable policy engine using a | |
| ChuangSi AI Model Content Protection chuangsiaihub/chuangsi-mcp-python Provides real-time content safety protection for large language models by detecting and preventing risks in both input and output content across multiple dimensions including compliance, ethics, and security. | |
| MCP Web Research Server chuanmingliu/mcp-webresearch A Model Context Protocol server that enables Claude to perform web research by integrating Google search, extracting webpage content, and capturing screenshots. | |
| antigravity-browser chuanxu742-glitch/antigravity-browser Enables policy-gated browser automation with persistent Firefox/Chromium profile isolation, version-locked fingerprint consistency, and auditable local session management. | |
| h3yun-sql-troubleshooter chuck9090/h3yun-sql-troubleshooter MCP server for querying H3Yun SQL data, enabling AI to execute read-only SQL queries and troubleshoot H3Yun business issues. | |
| hello-mcp chuckmeyer/hello-mcp A minimal learning-focused MCP server that demonstrates core primitives like tools and resources through simple greeting functions. It provides a foundational example for connecting AI models to external data using both Streamable HTTP and | |
| nhtsa-recalls-mcp chucks-lab/nhtsa-recalls-mcp Enables MCP clients to look up US vehicle-safety data read-only — decoding VINs, and retrieving recalls, owner complaints, and 5-Star NCAP safety ratings by make, model, and year through NHTSA's public APIs. | |
| MCP Server with Docker, Redis, and TimescaleDB chuckwilliams37/mcp-server-docker A FastAPI-based MCP server orchestrated with Docker Compose, integrating Redis caching and TimescaleDB for time-series data management. | |
| MESS chuckyatsuk/mess-mcp Inventory of your service accounts, kept current by your coding agents. Metadata only, no secrets. | |
| db-mcp chud-lori/db-mcp Provides read-only database access for AI agents across multiple databases (Postgres, MySQL, MongoDB, Elasticsearch) with enforced read-only guarantees and separate tools for prod and non-prod environments. | |
| attest-mcp-server chudah1/attest-dev An MCP server that exposes tools for issuing scoped agent credentials, delegating narrower child credentials, handling approvals, revoking task trees, and retrieving audit trails and evidence packets. | |
| Sparky Crypto Prices Oracle chuddyrudd/sparky-crypto-prices Free real-time cached CoinGecko USD prices + 24h change. No key, no signup, 15/min rate limit. x402 paid v2 soon. Perfect for trading/research agents. | |
| Gemini-Imagen4 chug2k/gemini-imagen4 Generate high-quality images from text descriptions using Google's Imagen 4.0 models with multiple quality variants, flexible aspect ratios, and local file storage. | |
| LINE OA MCP Ultimate chughes67400/line-oa-mcp-ultimate Enables AI agents to operate one or many LINE Official Accounts through natural language — sending broadcasts, Flex and tappable Rich Messages, building Thai-ready rich menus, managing coupons, audiences, insights, and LINE Shopping storefr | |
| TradingView MCP Bridge chugo-beep/tradingview-mcp Enables AI assistants to connect to a locally running TradingView Desktop app for chart analysis, Pine Script development, and workflow automation via Chrome DevTools Protocol. | |
| Task Manager MCP Server chukaibejih/mcp-task-manager A comprehensive task management MCP server built with FastMCP, featuring full CRUD operations, intelligent filtering, and productivity-focused prompts. | |
| DroidRun MCP Server chukfinley/droidrun-mcp-server Enables text-based control of Android devices through Claude Code using accessibility tree automation. Supports UI interaction, app launching, text input, gestures, and navigation without requiring screenshots. | |
| GitHub Issue Relationships MCP Server chuks-qua/github-issues-mcp-server An MCP server that provides tools for managing GitHub issue relationships, including tracking dependencies, blockers, and sub-issues. | |
| AI Tutoring RAG System chukwuebuka-2003/ebuka_mcps Enables personalized AI tutoring by allowing students to upload PDF/DOCX study materials that are processed and indexed for semantic search. Provides intelligent responses based on the student's own learning materials using RAG technology. | |
| EVM MCP Server chulanpro5/evm-mcp-server A comprehensive server that enables AI agents to interact with multiple EVM-compatible blockchain networks through a unified interface, supporting ENS resolution, token operations, and smart contract interactions. | |
| TypeScript MCP Server Boilerplate chuljung/mcp-sever A starter project designed to quickly build and deploy Model Context Protocol (MCP) servers using the TypeScript SDK and Zod for schema validation. It features example implementations for tools and resources, providing a solid foundation fo | |
| QQ Mail Read-only MCP chuluumgl/qqmail-readonly-mcp Review QQ Mail subscription, renewal and billing notices locally on macOS through a read-only stdio MCP server. Strict TLS and PEEK reads; no sending or mailbox changes. Requires Python 3.13+ and session-only credentials entered through nat | |
| fishing-mcp-server chunfangzou8-lang/fishing-mcp-server MCP server for a text-based fishing game that allows Claude to play remotely via the Model Context Protocol, with features like casting, buying bait, selling fish, and exploring different locations. | |
| abaqus-mcp-server chunfeng6619-pixel/abaqus-mcp-plugin Enables external AI assistants and MCP clients to communicate with Abaqus/CAE via file-based IPC, supporting remote Python script execution, model and job queries, ODB inspection, and viewport screenshots. | |
| Jev MCP chungsubeen0/jevmcp Enables frontier coding agents to delegate routine probabilistic judgments to TypeSafe Jev, providing calibrated triage signals for failures, attempts, completion, context ranking, findings, risk, and generic evidence-grounded questions. | |
| ChunkHound chunkhound/chunkhound A local-first codebase intelligence tool that enables AI assistants to research codebases using semantic search, multi-hop relationship discovery, and structural parsing. It allows users to extract architectural patterns and institutional k | |
| Chunk MCP Server chunknet/mcp-server Enables querying median feeds and metrics from the Chunk network via MCP tools, including listing metrics, getting quotes, and checking contract health. | |
| screenshot-mcp chunlea/screenshot-mcp A cross-platform MCP server that allows AI agents to capture screenshots of specific windows, displays, or regions for native application testing. It provides tools to list active windows and monitors, enabling precise visual verification a | |
| office-mcp-server chunleiding/office-mcp-server MCP server for Office document automation, enabling AI assistants to create, read, and clone Word/Excel/PPT templates while preserving formatting. | |
| md2pdf-mcp chunliu/md2pdf MCP Server for Markdown to PDF conversion. | |
| KnowCoder MCP chunmao-zhang/knowcoder_mcp Turns deep-research questions into reusable, source-grounded Workspaces with review checkpoints and background tasks, enabling structured research and reporting. | |
| hex-mcp-server chuotdelongchamp/hex-mcp-server Enables AI assistants and other MCP clients to audit and manage Hex workspaces through the Hex API, covering projects, users, data connections, runs, cells, groups, collections, guides, and agent threads. | |
| yandex-vision-ocr-mcp chupre/yandex-vision-ocr-mcp Provides OCR capabilities for images and PDFs using Yandex Vision API. Supports multiple recognition models and output formats. | |
| mcp-ukrainian-calendar chuprinadaria/mcp-ukrainian-calendar Provides access to Ukrainian pagan calendar with holidays, deities, folk wisdom, and birth charms, enabling users to query today's holidays, upcoming events, deity details, and personal birth charms. | |
| outlook-mcp-server churikovsv/outlook-mcp-server Enables local Microsoft Outlook automation on Windows, including checking account status, creating drafts, and sending individual or bulk emails with attachments and recipient lists from TXT, CSV, or Excel files. | |
| dsh-harness-mcp-server chushixixin/dsh-harness-mcp-server Exposes DeepSeek Harness agent capabilities as an MCP server, letting any MCP client drive Harness to execute real coding tasks with structured results, context isolation, and parallel execution. | |
| sully-termux-mcp chushiyu111-design/sully-termux-mcp A secure MCP gateway for Termux that exposes filesystem, shell, and Termux:API tools over a local HTTP endpoint with admin controls, job management, and upstream support. | |
| mt5ctl chust-dev/mt5ctl An MCP server for operating headless MetaTrader 5 terminals — over SSH, from your agent. | |
| Agent Cockpit chutingyean/agent-cockpit Enables MCP-speaking AI research agents to coordinate plans, tasks, experiment runs, and claims on a shared evidence board, tracing each claim to the code that produced it and flagging results that need rechecking when dependencies change. | |
| MCP Study Agent chutinrop/mcp-study-agent An MCP server that enables users to interact with local documents for educational purposes through tools for listing and reading files. It features an integrated agent capable of automatically generating document summaries and study flashca | |
| Scaffold MCP Server chuxiaoguo/scaffold-mcp-server Enables generating frontend project scaffolding for multiple frameworks (React, Vue, UmiJS, Electron) via natural language commands. | |
| IMAP/SMTP Email MCP Server chuxin0304/imap-smtp-mcp Enables email management via IMAP/SMTP, supporting list emails, read emails, send emails, and save drafts. | |
| nekoworker chuxinneko/nekoworker Enables AI agents to operate a complete Linux desktop through MCP, including applications, system windows, file managers, terminals, and browsers via AT-SPI element trees. It also provides noVNC access for humans to observe and take over th | |
| qzone-mcp chuyansir/qzone-mcp A QQ toolbox MCP server that lets an agent manage Qzone posts (publish, list, like, comment, delete, set visibility), friend feeds, visitors, confession-wall submissions and scheduled posts, while also editing the bot's profile (avatar, nic | |
| Weather MCP Server chuyiy128-a11y/weather-mcp-server Provides real-time weather information for major Chinese cities and global locations using the wttr.in API. Supports weather queries, listing supported cities, and server info via MCP tools. | |
| deepseek-mcp-image chuyuxuan0v0/deepseek-mcp-image Provides image recognition for text-only LLMs like DeepSeek by bridging to SenseNova multimodal model, enabling image description via the describe_image tool. | |
| Link Scan MCP Server chweyun/mcp-link-scan Automatically scans and summarizes video links (YouTube, Instagram Reels) and text links (blogs, articles) using AI-powered transcription and summarization. Provides concise 3-sentence summaries without requiring API keys. | |
| Nonpayment Health MCP Server chweyun/mcp-nonpayment-health Enables querying and analyzing non-reimbursable medical treatment costs in South Korea using the Health Insurance Review & Assessment Service API. Supports searching treatment codes, comparing hospital prices, regional statistics analysis, | |
| reporelay chwoerz/reporelay Self-hosted MCP server for indexing and searching code repositories via hybrid search and deep code understanding. | |
| mcp-kg-server chwsvveuiygbfiw/mcp-kg-server MCP server exposing a medical knowledge graph (289 Western drugs, 204 TCM drugs, diseases, symptoms) as MCP tools. Enables AI agents to search drugs, check drug compatibility, and query symptoms-to-medication recommendations locally. |
38,851–38,900 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.