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-ssh albertm88/mcp-ssh 轻量级跨平台 SSH MCP 服务器，复用本地 SSH 配置实现远程命令执行、文件传输和主机管理。 | |
| pdf-rescue-mcp albertm88/pdf-rescue-mcp Enables OCR text extraction and quality management for Chinese PDF books, including batch processing, resume capabilities, and diagnostic tools. | |
| odoo-mcp-bridge alberto-cabale/odoo-mcp-bridge Enables Claude to read and write data in an Odoo instance, including stock, invoices, clients, and reminders, through a secure MCP connector. | |
| mcp-server-odoo alberto-re/mcp-server-odoo An extensible MCP server that integrates Odoo with LLMs to enable querying and managing business data like partners, quotations, and sales orders. It supports custom tool registration and multiple transport protocols for both local and remo | |
| AWS Cost Explorer and Amazon Bedrock Model Invocation Logs MCP Server alberto4011/aws-cost-explorer-mcp-server Enables users to query and analyze cloud spending, EC2 cost breakdowns, service-level spend, and model usage logs through natural-language interactions. It also supports cross-account spend retrieval when configured. | |
| wanderlog-mcp alberto4011/wanderlog-mcp Enables MCP-compatible agents to view and build Wanderlog trip itineraries conversationally, including places, notes, hotels, transit, checklists, and expenses. | |
| MCPMempool alberto4442/mcpmempool Provides auto-scalable management with priority-based scheduling for everyday use. | |
| lattice-mcp alberto7998/matryoshka Enables token-efficient analysis of documents far larger than an LLM context window by executing constrained symbolic commands against server-side handles instead of chunking or vector databases. It supports recursive queries, multi-documen | |
| Vectorize MCP Server albertoa18011/vectorize-mcp-server Enables vector search and document retrieval, extraction and chunking of any file into Markdown, and private deep research generation through Vectorize pipelines. It connects MCP clients such as Claude, Cursor, and VS Code to these Vectoriz | |
| ESP32-CYD Wi-Fi Analyzer MCP albertobalsalm0/esp32-cyd-wifi-analyzer-mcp Enables AI assistants to scan and analyze nearby Wi-Fi networks for security vulnerabilities, control an ESP32-CYD device's display and RGB LED, and receive real-time threat alerts via USB serial communication. | |
| Remote MCP Server Authless albertobonanni/remote-mcp-server-authless Deploys a remote MCP server on Cloudflare Workers without authentication, enabling tools via SSE endpoint for use with AI clients like Cloudflare Playground or Claude Desktop. | |
| CamoFox MCP albertoduong446/camofox-mcp Enables MCP-compatible AI agents to automate anti-detection browser sessions with navigation, interaction, search, extraction, downloads, multi-tab workflows, and session reuse. | |
| clipboard-image albertoelopez/claudecode-copy-img-mcp Enables Claude Code to paste images from the system clipboard for instant analysis and processing. | |
| Business Design MCP Server albertogferrario/business-design-mcp Enables the creation and management of business design artifacts including Business Model Canvases, SWOT analyses, and user personas. It features project organization and AI-powered research tools to automatically populate frameworks with m | |
| Mellos Mapping albertolambert26121/mellos-mapping Enables coding agents to publish a layered dependency map of a system as ghost nodes, then light each node up as it is built and verified, with cracks and faults propagating visibly to upper layers. It exposes tools for declaring ranks, edg | |
| devos-intelligence-mcp albertomitroi/devos-intelligence-mcp Enables AI coding agents to query the semantic graph, observations, and context packs generated for their repository, receiving compact answers with file:line evidence and redacted snippets instead of raw generations. It resolves generation | |
| Joplin MCP Server albertomuller1679/joplin-mcp Enables AI assistants to browse, search, create, update, organize, tag, import, and delete notes, notebooks, and tags in the Joplin note-taking app through its API. It also supports reading attached resources, managing trash, and enforcing | |
| Jira QMetry MCP Server albertor03/jira-qmetry-mcp MCP server to interact with the QMetry for Jira API, enabling management of test cases, test cycles, test plans, and more through well-defined tools. | |
| job-seeker albertorsesc/job-seeker Profile-driven job search engine that aggregates postings, scores them against a user's profile, filters by eligibility (location, timezone, work authorization), and exposes find_jobs, list_sources, and describe_engine to local AI agents ov | |
| ddg-search-mcp albertous007/ddg-search-mcp DuckDuckGo Search MCP Server. Scrapes DuckDuckGo Lite directly — no API key required, no rate limits, robust anti-bot protection. | |
| aladin-mcp albertrim/aladin-mcp Enables real-time book search, detailed information, and bestsellers from the Aladin OpenAPI, integrated with Claude Desktop via MCP. | |
| Wiki MCP Server albertshao/wiki_mcp_server An MCP Server implementation that enables managing Confluence wiki pages through natural language queries, supporting operations like creating, updating, deleting, and searching pages across different knowledge bases. | |
| brain-mcp albertvalleeduval/brain-mcp Connects claude.ai to a private GitHub repo of markdown files as a personal second brain, providing guarded read and write tools for knowledge management. | |
| ai-agents-mcp-itsops albeus/ai-agents-mcp-itsops Enables MCP-compatible clients to search approved local Markdown runbooks, retrieve selected local host health details, and get bounded Kubernetes pod-status summaries for allowlisted clusters and namespaces. | |
| Dropbox MCP Server albiemark/dbx-mcp-server A Model Context Protocol server that enables AI applications to interact with Dropbox, providing tools for file operations, metadata retrieval, searching, and account management through Dropbox's API. | |
| Render & Verify MCP albinchristo14/render-verify-mcp Enables AI coding agents to open and exercise web applications in an isolated Chromium browser, capture screenshots and runtime/network diagnostics, and run deterministic page checks with linked evidence. | |
| multi-agent-debate-mcp albinjal/multi-agent-debate-mcp Facilitates structured multi-agent debates with arguments, rebuttals, and judgments across multiple rounds, enabling diverse AI personas to engage in formal debate and collaborative problem-solving. | |
| TrackLab MCP Ultimate Edition albiruby/mcpintervals.icualbireo Turns any AI assistant into a physiological AI running coach by abstracting fitness APIs and exposing 70+ structured analytical MCP tools based on endurance models. | |
| MCP TypeScript Tools Server albo3/mcp-server Provides calculator, datetime, and note-taking tools for LLMs like Claude via the Model Context Protocol. | |
| QuoteOfTheDay albu231311/remote-mcp-server Serves famous quotes over the Internet, enabling retrieval of random quotes, searching quotes by author or keyword, and checking remote server time via MCP. | |
| PLTM-Claude alby2007/pltm-claude-repost- An MCP server that gives Claude Desktop persistent memory, self-awareness, epistemic hygiene, and genuine agency across conversations with a typed memory system, embedding-based semantic search, a 3-judge memory jury, and a real-time dashbo | |
| PLTM MCP Server alby2007/pltm-mcp Provides 78 tools for AGI experiments based on universal physics principles like entropy and criticality. It enables advanced long-term memory management, diversity-focused information retrieval, and meta-cognitive monitoring for self-impro | |
| mergestat-mcp alc0der/mergestat-mcp Enables SQL queries against git repositories via MergeStat, allowing users to analyze commits, authors, and files using natural language. | |
| Playwright MCP Cursor alceniralcantara/playwright-mcp-cursor Demonstrates using Playwright with the Model Context Protocol (MCP) to enable large language models to automate browser interactions, with an example of cursor-based pagination against the GitHub GraphQL API. | |
| vyos-mcp alch3mistdev/vyos-mcp MCP server for managing VyOS routers via the VyOS HTTP API, allowing AI assistants to read config, set interfaces, firewall rules, VPNs, and more. | |
| huashu-chrome alchaincyf/huashu-chrome Enables any MCP-compatible AI agent to drive your own Chrome browser with your existing login state, filling forms, clicking elements, fetching data, and handling captchas without API keys or re-authentication. | |
| doubao-search-mcp alchaincyf/huashu-doubao-search MCP server for Doubao Search that enables real web search in any MCP client, backed by ByteDance-exclusive Chinese sources and the open web. | |
| Weather MCP Server alchaincyf/mcp A Model Context Protocol server that provides weather information and forecasts based on user location or address input. | |
| kofic-mcp-server alcheminos/kofic-mcp-server MCP server wrapping the Korean Film Council (KOFIC) Box Office API, enabling retrieval of daily/weekly box office data, movie search, and detailed movie information for use with Claude via a custom connector. | |
| Calculator MCP Server alchemist-code07/researchflow-mcp This MCP server provides calculator tools, resources, and prompts for arithmetic operations, and serves as a minimal template for learning NitroStack fundamentals. | |
| Zone Two alchemist-s/zonetwo Enables querying your own Garmin Connect health, sleep, training, and activity data, and creating or scheduling workout plans through natural language conversation. | |
| Alchemist for SOLIDWORKS alchemistcache/alchemist-solidworks-mcp Enables Claude and other MCP clients to create and modify SOLIDWORKS parts, assemblies, sheet metal, weldments, drawings, and bills of materials from natural-language requests, run strength simulations, and receive model views and stress ma | |
| show-me-mcp alchemistklk/show-me-mcp Enables agents to create display-quality visual content across HTML, Mermaid, pseudocode, text trees, and diffs, with automatic layout repair and rendering verification to prevent overlaps, overflow, and connection conflicts. | |
| BTC Intraday Market Data MCP alchemy666888/intraday-mcp Read-only MCP server providing BTC intraday quantitative market data via tools like snapshots, timeframes, liquidations, and options surface, designed for Vercel Hobby and ChatGPT custom MCP apps. | |
| Autoeval alchemyincode/plumloom-autoeval-oss Enables evaluating AI applications, inspecting reliability evidence, and gating releases from development and CI workflows. | |
| laravel-tasks alchiebinan21/task_management_mcp MCP server that connects to a Laravel Tasks API, enabling AI assistants to perform CRUD operations on tasks. | |
| traktor-mcp alchimestre/traktor-mcp Exposes a Traktor collection's reconciliation over stdio, enabling an MCP client to report status, preview entry-by-entry changes, repoint or add entries, and purge records whose files are gone. Writes are backed up and gated behind an expl | |
| deixis alcides-collective/deixis A visual surface for terminal Claude Code that provides a persistent dashboard the agent curates itself, per-session telemetry with cost, and a menu bar glyph for status. | |
| ComfyUI MCP/REST Gateway alcoholmajuu/dsh-comfyui Enables users to drive a connected ComfyUI instance from a chat client, submitting generations, reviewing results, and adjusting workflow parameters, while exposing OAuth-protected MCP and REST endpoints for remote, authenticated control. | |
| archivist-mcp alcor6502/archivist-mcp A self-hosted MCP server that provides Claude with a git-versioned document vault, featuring dataset-based access control with keys, OAuth authentication via GitHub, and automatic commits on every write. |
25,851–25,900 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.