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 |
|---|---|
| vite-mcp broisnees/vite-mcp A Vite plugin that provides MCP server capabilities, enabling MCP clients to interact with browser environments through adapters for console, cookies, storage, performance, and component tree inspection. | |
| ILSpy MCP Server brokenistxd/ilspy-mcp-server Exposes all major ILSpy CLI features as separate MCP tools for decompiling .NET assemblies, enabling automated end-to-end processing and structured JSON reports. | |
| skan-zgodnosci-mcp brokerbusiness-ai/skan-zgodnosci-mcp Enables AI assistants to conduct a 30-question information security and GDPR/NIS2 compliance screening for Polish SMEs, with fully local scoring, area-based results, gap identification, and prioritized remediation steps. | |
| MCP Server for Danmarks Statistik brokk-sindre/mcp-dst Exposes Denmark's Statistical Bureau API as programmable resources, making it easy to integrate with language models and modern AI applications to enable natural language queries for statistical data. | |
| sek-fx-mcp bromaniac/sek-fx-mcp Fetches exchange rates from Riksbanken API for currencies to Swedish kronor using ISO 4217 codes. | |
| MCP Awwwards Todo System brookcs3/mcp-awwwards-todo-system Professional MCP server for Claude Desktop that provides award-winning todo management with systematic design principles, cross-chat persistence, and contextual triggers. | |
| Titan Rotation MCP brooke19931993-glitch/titan-rotation-mcp Provides AI assistants with Titan SDK knowledge, verified spell IDs, and a Lua validator to generate combat rotations for any World of Warcraft class and specialization from a single prompt. | |
| Brooks Model MCP brooks-sem/mcpserver Provides a unified MCP interface to interact with Codex CLI, Claude Code, and Grok API, allowing seamless switching between AI models in VS Code or Claude Code. | |
| io.github.morluto/flameox brooks2882/flameox Enables coding agents to coordinate profilers, benchmark tools, trace processors, and direct local targets to capture bounded runtime evidence, analyze artifacts, and inspect preserved evidence with provenance, coverage, and limitations. | |
| Instagram DM MCP server brooks3255/instagram_dm_mcp Enables sending direct messages and managing conversations, media, user profiles, stories, followers, and engagement from an Instagram account through MCP tools. | |
| Email MCP Server brooks3613/email-mcp Enables AI assistants to read, search, send, reply, forward, schedule, and analyze email across multiple IMAP/SMTP accounts, with drafts and templates, provider-aware labels and bulk operations, calendar extraction, real-time inbox watching | |
| knowledge-base-server brooks421/knowledge-base-server Enables AI agents to capture, classify, synthesize, and retrieve shared persistent knowledge across sessions via MCP, with tiered memory, full-text and semantic search, and token-efficient context briefings. | |
| VSCode MCP brooks421/vscode-mcp Enables AI coding agents and MCP clients to query a running VSCode instance for real-time LSP diagnostics, hover/definition/signature type info, and symbol references with usage context, replacing slow tsc/eslint/build runs. Also supports w | |
| MS 365-21V MCP Server brooks450/ms-365-21v-mcp-server Lets MCP-capable AI clients act as the signed-in user against 21Vianet-operated Microsoft 365 — reading mail, analyzing calendar conflicts, and searching OneDrive and SharePoint files through Microsoft Graph China. It preserves the user's e | |
| Juror Cloud MCP brooks564/juror Enables MCP-compatible clients to list workspaces, inspect workspace-scoped findings and hosted runs, and prepare or—after explicit user confirmation—start or rerun hosted reviews. It does not access arbitrary local repositories or return r | |
| SSM MCP Server brooksian/smm-mcp-server Model Context Protocol server providing access to Cloudera Streams Messaging Manager (SMM) with support for both standalone and CDP deployments. Enables cluster, broker, and topic management through Claude Desktop. | |
| SSB MCP Server brooksian/ssb-mcp-server Provides comprehensive access to SQL Stream Builder (SSB) functionality with 80+ MCP tools for managing streams, jobs, tables, and real-time data processing. Supports both standalone SSB deployments and Cloudera Data Platform with multiple | |
| butchr brooswit-factory/butchr Enables orchestrating Jira-driven software workflows by watching tickets, running herdr agents on active issues, and pushing updates to those agents over MCP. | |
| thatch brooswit-factory/thatch Enables many Claude Code sessions to connect to a single HTTP MCP server, be addressed by name, and receive pushed messages from anywhere. | |
| symbolic_math_mcp brosnanyuen/symbolic_math_mcp A standalone FastMCP server that validates symbolic math proof files in YAML format using the symbolic-math-verify library. | |
| ilma brotal-llc/ilma Framework-agnostic MCP server for agent memory with Postgres + pgvector, enabling persistent memory, recall, and task management across sessions. | |
| groundtruther-mcp brothaakhee/groundtruther-mcp An MCP server that lets AI agents hire humans to complete real-world missions — verify locations, collect data, take photos, and more. | |
| mcp-server-ticktick broven/mcp-server-ticktick Enables interacting with TickTick tasks and projects through natural language via Claude and other MCP clients. | |
| KiCad MCP Server brovk2008/kicad-mcp-server Enables LLMs to inspect, edit, analyze, and render PCB layouts in real-time using the KiCad IPC API, providing tools for board configuration, footprints, tracks, zones, nets, text, shapes, dimensions, exports, screenshots, and CLI automatio | |
| STM32Cube-MCP brovk2008/stmcube-mcp This server enables AI agents to fully control STM32CubeIDE and STMicroelectronics hardware, including GUI automation, headless builds, flashing, GDB debugging, option bytes, serial telemetry, and CubeMX .ioc engineering. | |
| Clinical Trials MCP Server brown-tech-info/clinical-trials-gov-mcp Enables searching and retrieving detailed clinical trial information from ClinicalTrials.gov via the official API. | |
| Table Charts browncabinet/tablecharts-mcp-server TableCharts MCP Server gives any LLM assistant the ability to instantly convert tabular data into beautiful, hosted, interactive dashboards.
Simply provide JSON rows, raw CSV text, or a public URL (Notion page, Google Sheet, or Salesforce | |
| Your Echo — The A2A-native PR & Outreach Agent browncabinet/your-echo-agent Hire an autonomous cold outreach agent directly inside any MCP-compatible LLM. Built by a PR tech publicist, Your Echo Agent delivers truly personalized cold emails tied LinkedIn groups for SaaS, agencies, e-commerce, founders, local busine | |
| Your Echo Agent browncabinet/yourechoagent-mcp Hire autonomous PR outreach agents from any MCP-compatible LLM. All-in-one AI outreach: find verified leads, draft hyper-personalized emails, discover conferences/webinars/communities in your niche, and triage replies — all from any MCP cli | |
| UniFi Network MCP Server brownjl01/unifi-network-mcp Turns your UniFi Network Controller into programmable tools for querying and modifying network settings via MCP. | |
| ECL MCP Server brownrl/ecl_mcp Provides comprehensive access to the Europa Component Library (ECL) design system with semantic search across 50+ components, code examples, accessibility requirements, design tokens, and validation tools for building European Commission we | |
| Browseagent MCP browseagent/mcp Enables AI agents to control web browsers through the Model Context Protocol, supporting navigation, clicking, typing, and screenshots. | |
| Vibetest Use browser-use/vibetest-use Launches multiple Browser-Use agents to automatically test websites for UI bugs, broken links, accessibility issues, and other technical problems on both live and localhost sites. | |
| BAP MCP browseragentprotocol/bap Lightweight browser automation server for AI agents, enabling fast (10-25ms per action), structured observations and semantic selectors with zero token overhead. | |
| BrowserCat MCP Server (Browser Automation) browsercat/browsercat-mcp-server A Model Context Protocol server that provides browser automation capabilities using BrowserCat's cloud browser service. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environm | |
| BrowserGenie MCP Server browsergenie/mcp An MCP server that provides AI models with full browser automation capabilities through Chrome. It enables navigation, interaction, screenshots, and complete DevTools access by bridging AI clients with a companion Chrome extension. | |
| browserkit browserkit-dev/browserkit An open-source framework for building site-specific MCP servers that run over real, authenticated user browser sessions locally, turning them into composable AI tools. | |
| BrowserMCP browsermcp-com/mcp Remote browser instances for your AI agents. Reliably complete any browser-based task at scale. Fully-control agentic browsers that spin up in seconds. | |
| @browserview/mcp browserview/mcp MCP server for browserview.io that lets agents create, inspect, share, and destroy disposable cloud Chromium sessions, and connect via CDP using Playwright or Puppeteer. | |
| 3DP MCP Server brs077/3dp-mcp-server Enables Claude to create 3D-printable CAD models using build123d, with tools for modeling, modification, analysis, and publishing to platforms like Thingiverse and GitHub. | |
| CNCjs MCP Server brs077/cnc-design-control-mcp Bridges Claude Code to CNCjs to enable remote control and monitoring of GRBL-based CNC machines. It provides a comprehensive toolset for managing G-code jobs, machine movement, and safety operations through natural language. | |
| BRS Signals MCP Server brssignals/brs-signals-mcp Provides real-time Bitcoin market regime detection by fusing on-chain, derivatives, and absence sensors into a convergence score, enabling AI agents to make informed trading decisions. | |
| cliproxy bruc3van/cliproxy-mcp Enables AI coding assistants like Codex, Claude Code, and ZCode to generate images through CLIProxy's ChatGPT image API, saving original images locally and returning previews. | |
| omarchy-mcp bruce-forte/omarchy-mcp-server Lets local AI agents drive an Omarchy desktop by exposing its command registry and shell IPC targets over MCP, enabling command search, execution, and desktop state control. | |
| docagent-gw bruce0817kr/docagent-gw-mcp Enables Claude Code to search, view, and download groupware electronic approval documents, including content-based RAG search and synchronization tools. | |
| fyi-docs bruce212/fyi-mcp Remote MCP server for FYI Docs that exposes read-only tools (search documents, clients, jobs, tasks, cabinets) to MCP clients like Claude or Cursor via Streamable HTTP, using API key authentication. | |
| siraya-mcp-worker bruceatsiraya/siraya-agent-tools A Cloudflare Worker MCP server that exposes SIRAYA model discovery and invocation tools to MCP-capable agents. | |
| AWS‑IReveal‑MCP brucedh/aws-ireveal-mcp MCP server for incident response in AWS | |
| video-sum-mcp brucehe3/video-sum-mcp Extracts content from Douyin, Bilibili, Xiaohongshu, and Zhihu, and generates intelligent knowledge graphs. | |
| doc2images-mcp brucekangcn/doc2images-mcp Enables rendering PDF pages to images and returning them directly as multimodal content for models, with controls for page ranges, resolution, and output dimensions. |
35,701–35,750 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.