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 |
|---|---|
| bitbucket-pr-review-mcp 6shihab/bitbucket-pr-review-mcp Enables a language model to read Bitbucket Cloud pull requests and post line-anchored comments with a summary, while deliberately preventing merge, decline, or approval actions. | |
| mcp-server-notify 6starlong/mcp-server-notify 一个轻量级的桌面通知工具，支持 MCP 协议集成和命令行直接调用，让 Agent 能够智能发送系统通知。 | |
| MCPHubs 7-e1even/mcphubs A unified gateway and web dashboard that aggregates multiple MCP servers into a single Streamable HTTP endpoint. It supports stdio, SSE, and HTTP protocols, featuring optimized tool exposure modes to reduce token consumption for AI clients. | |
| search-mcp 7-e1even/security-search-mcp Aggregates security research articles from WeChat, QAX Butian, and Xianzhi community, with optional KimiCode web search. Supports smart deduplication, article fetching, and anti-bot measures. | |
| DG Flame MCP 71233/dg-flame-mcp Enables AI agents to control Autodesk Flame through MCP using multiple execution paths such as the Flame Python API, native commands, raw Python, UI automation, and other tools, with observation and verification of results. | |
| Hermes MCP Server 718haxi/hermes-mcp-server A lightweight Node.js MCP server with zero dependencies offering 9 built-in tools for system info, web fetching, GitHub search, file operations, shell execution, and key-value memory, enabling AI agents to perform these tasks via the Model | |
| doubao-mcp-minis 729019004/doubao-mcp-minis Enables Minis/iOS agents to access Doubao's multimodal capabilities—including image generation, image variation, chat with deep thinking, video, and music—through a lightweight MCP STDIO interface using browser session cookies without an AP | |
| wiznote-mcp 735140144/wiznote-mcp Enables Claude to interact with a private WizNote server for document management, including creating, reading, searching, and updating notes. | |
| feature-separate-batch-eval-mcp 73882/feature-separate-batch-eval-mcp Enables users to analyze already-persisted single-patent evaluations to discover cross-patent batch issues such as language, technical-domain, input-structure sensitivity, and language-structure interactions, without modifying existing MCP, | |
| feature-separate-eval-mcp 73882/feature-separate-eval-mcp Enables evaluation of patent feature-separation results by listing records, checking alignment with claims and original text, and running deterministic quality gates plus a Judge audit. | |
| Zotero MCP Agent 744649181/zotero-mcp Enables research paper search and download, Zotero library management, and knowledge base export through natural language. | |
| browser-mcp 747486675/browsercontrolmcp Enables AI clients to control a real, visible Chrome via MCP for navigating, clicking, typing, downloading files, and reading page content. Supports isolated CDP and everyday-Chrome extension modes with user confirmations for risky actions. | |
| erp-billing 757607106/gjp-cyb-mcp MCP server that enables AI platforms to search products, customers, and warehouses, and prepare and submit sales orders to a fixed ERP endpoint with per-session bearer authentication. | |
| gjp-print-mcp 757607106/gjp-print-mcp MCP server for cloud printing that exposes three template style tools (get_print_info, new_style, save_style), enabling vision models to restore print templates from user images and save them to the business system with dynamic token authen | |
| blib-houdini-bridge 760849256/houdini-mcp-cli Enables AI assistants and CLI tools to read and control Houdini scenes with a safety model that separates read and write operations. | |
| mdm-mcp 767560479/mdm-mcp Provides 12 MCP tools to directly interact with DEM MDM backend API, enabling Cursor or AI agents to manage MDM data. | |
| Fetch MCP Server 769344359/worker-mcp Fetches web content and returns it in HTML, JSON, plain text, or Markdown format. | |
| Agent Notifications 777genius/agent-notifications A local MCP server that lets AI agents send desktop notifications during tasks, ask for attention, and report completion. Supports macOS, Linux, and Windows, with optional webhook delivery. | |
| jina-mcp-server 77and88/jina-mcp Enables clients to read web pages and PDFs as markdown, capture screenshots, search the web and academic sources, rerank/deduplicate content, and extract PDF elements. Supports API-key access, tool filtering, and response token limits. | |
| bilibili-mcp 77rickliu/bilibili-mcp An MCP server for interacting with Bilibili, enabling AI assistants to search videos, fetch comments and subtitles, publish content, and manage interactions. It also adds private message reading, stable TV login, and an automated comment wo | |
| Douyin Engagement MCP 77rickliu/douyin-engagement-mcp A local MCP server that enables Douyin keyword search and comment campaigns through the user's own logged-in Chrome, with human approval, cross-campaign deduplication, and resume after manual verification. | |
| MCP Calculator 78/mcp-calculator A protocol interface that extends AI capabilities by enabling models to interact with external systems for calculations, email operations, knowledge search, and more. | |
| Claude Team MCP 7836246/claude-team-mcp Enables collaboration between multiple AI models (GPT, Claude, Gemini) to work together on complex tasks, with intelligent task distribution and role-based expert assignment for code development, review, and optimization. | |
| Open-Meteo MCP 78tacos/open-meteo-mcp Provides MCP-compatible agent clients with current weather, forecasts, and place-name geocoding from the Open-Meteo API without requiring an API key. | |
| ChatGPT-Codex-Claude Bridge 78tyih/chatgpt-codex-claude-bridge Enables ChatGPT to remotely orchestrate local Codex and Claude Code agents for file editing and command execution via a secure Cloudflare tunnel, bridging cloud AI planning with local execution. | |
| AI 客服商城 MCP Server 790125/ai-customer-service-mcp Enables AI agents to provide e-commerce customer service with product search, RAG-based FAQ answers, human handoff, and automated security auditing with a review workflow. | |
| RE-MCP 79cbd8hmgj-wq/re-mcp A safety-first local MCP server for ROM reverse-engineering, enabling project status checks, file verification, Bakugan DS build/quality tasks, and read-only DeSmuME/ARM9 debugging. | |
| Coin Metrics MCP Server 7blocklabs/mcp-coin-metrics-demo Enables AI agents to query cryptocurrency network and market data through tools for time-series metrics, OHLCV candles, bid/ask quotes, index levels, and asset or market metadata. | |
| Cube MCP Server 7blocklabs/mcp-cube-demo Enables AI agents to interact directly with Cube's API, allowing them to list cubes/views and metadata, run queries, and retrieve generated SQL. | |
| FX Rates MCP Server 7blocklabs/mcp-fx-reference Enables AI agents and MCP clients to convert currency amounts, retrieve current, historical, and timeseries exchange rates, and list supported currencies from European Central Bank reference data. | |
| Mural Pay MCP Server 7blocklabs/mcp-mural-pay-demo Enables AI agents to interact with Mural Pay's API using the caller's own key for listing payout source accounts, estimating token-to-fiat payout fees, and searching or retrieving payout requests and account transactions. | |
| OpenRouter MCP Server 7blocklabs/mcp-openrouter-demo Enables MCP clients to browse and compare model catalogs, pick models by budget or context window, and run completions metered to the caller's own API key. | |
| Salt Edge MCP Server 7blocklabs/mcp-salt-edge-demo Enables AI agents to access banking data APIs and list customers, connections, accounts, and posted transactions, with metering tied to the caller’s own API key. | |
| The Data City MCP Server 7blocklabs/mcp-the-data-city-demo Enables AI agents to search and retrieve UK company data, including company details by Companies House number, group ownership structures, website associations, and Real-Time Industrial Classification definitions. | |
| claude-for-hermes 7d-codes/claude-for-agents A local MCP server that lets Hermes supervise Claude Code, delegating focused coding, research, or review tasks to the Claude Code CLI and managing worker sessions, background jobs, cancellations, and read-only reviews. | |
| Image Description MCP Server 7etsuo/image-description-mcp_server Enables AI assistants to analyze images from URLs or local files using xAI's Grok API. Provides detailed image descriptions, technical metadata extraction, and optical character recognition (OCR) capabilities. | |
| Trench Report 7evyr/trench-report-mcp Enables any MCP client to grade a Solana wallet's memecoin trading as a school-style report card, returning an overall score, five habit grades (entries, exits, patience, sizing, bag control), FIFO-based realized PnL, win rate and hold-time | |
| mcp-tty 7ez/mcp-tty Gives AI agents a persistent, interactive PTY shell with multiple concurrent named sessions, supporting SSH and interactive prompts instead of one-shot exec. | |
| notes-box 7fernando750/my-mcp-server-app Enables adding, retrieving, and listing notes with state persisted to a local JSON file. | |
| whistle-mcp 7gugu/whistle-mcp Whistle MCP Server is a Whistle proxy management tool based on the Model Context Protocol (MCP) protocol, which enables AI assistants to directly operate and control local Whistle proxy servers. Through this tool, AI can help users manage r | |
| ZIP-MCP 7gugu/zip-mcp An MCP tool that provides AI with the ability to compress and decompress local files. | |
| terminal-guardian-mcp 7majesty-m/terminal-guardian-mcp Provides secure, sandboxed terminal access for AI assistants via the Model Context Protocol, with multi-layer risk analysis and auditable command execution. | |
| Bilibili Video Research 7omb2006/bilibili-video-research MCP server for evidence-aware video research, providing tools to analyze local videos, inspect specific time windows, and analyze Bilibili videos with provenance tracking and optional audio removal for privacy. | |
| Catalyst 7omb2006/catalyst Enables AI agents to research Bilibili and YouTube videos through language, visual, or multimodal analysis, returning structured evidence with source-time ranges, availability states, and explicit analysis limits. Supports caption or audio- | |
| mcp-mindmesh 7ossamfarid/mcp-mindmesh Manages multiple Claude 3.7 Sonnet instances in a quantum-inspired swarm to produce optimally coherent responses through ensemble intelligence. | |
| Micro.blog Books MCP Server 7robots/micro-mcp-server Enables management of Micro.blog book collections through natural language, allowing users to organize bookshelves, add/move books, and track reading goals. Built with FastMCP for reliable integration with Claude Desktop. | |
| cloud71 MCP connector 7t1-studio/cloud71-mcp Enables AI assistants to deploy generated files (HTML, PDF, images, etc.) directly to cloud71 hosting, returning a public URL, and manage cloud71 sites via natural language. | |
| Commerce Ops MCP 7vignesh/commerce-ops-mcp Enables commerce operations teams to investigate missing-delivery complaints and resolve them through natural language, with policy-enforced refunds and escalations. | |
| codex-agent-workers 7xkkkkk/codex-agent-workers Turns bounded coding tasks into reviewable Git diffs using isolated worktrees, configurable worker models, and test execution. | |
| Joplin MCP Server 7xme/joplin-mcp-server An MCP server that gives AI assistants read/write access to Joplin notes through the local REST API, with 20 tools for managing folders, notes, todos, tags, and bulk operations. |
22,301–22,350 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.