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 |
|---|---|
| Slovak Data Protection MCP ansvar-systems/slovak-data-protection-mcp Query Slovak data protection regulations, decisions, and guidelines from ÚOOÚ SR directly via MCP-compatible clients like Claude or Cursor. | |
| Slovenian Competition MCP ansvar-systems/slovenian-competition-mcp Enables querying Slovenian competition data including AVK enforcement decisions, merger control decisions, and sector listings for AI compliance tools. | |
| spanish-cybersecurity-mcp ansvar-systems/spanish-cybersecurity-mcp Query Spanish cybersecurity regulations, guidelines, and advisories from CCN-CERT/INCIBE directly from AI assistants. | |
| Swedish Cybersecurity MCP ansvar-systems/swedish-cybersecurity-mcp Enables querying Swedish cybersecurity regulations, decisions, and requirements from CERT-SE directly from MCP-compatible clients like Claude and Cursor. | |
| Swedish Data Protection MCP ansvar-systems/swedish-data-protection-mcp Query Swedish data protection data — regulations, decisions, and requirements from IMY — directly from Claude, Cursor, or any MCP-compatible client. | |
| Swedish Financial Regulation MCP ansvar-systems/swedish-financial-regulation-mcp Query Swedish financial regulation data — regulations, decisions, and requirements from Finansinspektionen — directly from Claude, Cursor, or any MCP-compatible client. | |
| swiss-cybersecurity-mcp ansvar-systems/swiss-cybersecurity-mcp Enables querying Swiss cybersecurity regulations, guidance, advisories, and frameworks from NCSC.ch via any MCP-compatible client. | |
| Swiss Data Protection MCP ansvar-systems/swiss-data-protection-mcp Enables querying Swiss data protection regulations, FDPIC/EDOB decisions, and guidelines directly from MCP-compatible clients like Claude. | |
| cordslite-mcp answerdotai/cordslite-mcp Provides read-only Discord access, enabling listing guilds, mapping channels, reading and searching messages, following threads, and viewing attachments without posting. | |
| mcpmini answerdotai/mcpmini Minimal MCP server allowing Python functions to be served as MCP tools over stdio or HTTP, with a built-in client for connecting to MCP servers. | |
| answerhatch-mcp answerhatch/answerhatch-mcp Enables adding a cite-or-refuse answer box to your docs from your agent. | |
| MCP Workspace Server answerlink/mcp-workspace-server An all-in-one MCP server providing complete AI agent capabilities including file operations, code execution (Python/Node.js), one-click web deployment with wildcard domain support, Excel/CSV processing, and image generation in isolated mult | |
| Max MCP Server answerrocket/mcp-server Connects AI assistants to AnswerRocket's Max AI platform, enabling access to Max copilots and their skills through the Model Context Protocol. | |
| Ansys CFX-MCP ansys/pycfx-mcp An MCP server that enables AI assistants to interact with Ansys CFX through PyCFX, supporting natural-language-assisted CFX-Pre, CFX Solver, and CFD-Post workflows for setup, execution, and postprocessing. | |
| Garmin Coach MCP ant-0n3/garmin-coach-mcp Connects Claude to Garmin Connect data for personalized running coaching, including morning readiness checks, post-run analysis, weekly reviews, and goal tracking. | |
| goofish-mcp ant-cave/goofish-mcp Enables searching Xianyu (Goofish) listings, fetching item details, taking keyword-monitor snapshots, and publishing secondhand products through MCP tools with local-session authentication. | |
| QQ空间 MCP Server ant-cave/qqzone-mcp Enables authenticated querying of QQ Zone profiles, posts, statistics, albums, and message boards through MCP tools, with cookie management and optional HTTP/SSE access. | |
| Antom MCP Server ant-intl/global-antom-mcp A Model Context Protocol (MCP) compatible server that integrates Ant International's Antom payment APIs, enabling AI assistants to handle payment and refund operations seamlessly. | |
| lldb-mcp ant4g0nist/lisa.py Enables AI assistants to interact with LLDB debugging sessions through a standardized MCP interface, allowing natural language commands for debugging tasks like setting breakpoints, stepping, and evaluating expressions. | |
| draftly-wps antares422/draftly-wps AI chat sidebar inside WPS Office (Mac) that edits the live document through the real JS add-in object-model API — no keyboard/mouse simulation. Powered by the Claude Agent SDK, with streaming replies, session history, and per-document (Wor | |
| VoxMesh antaresqaq/voxmesh Enables voice-first interactions with AI agents and MCP tools, supporting speech input/output, STT/TTS, and a provider-independent agent core. | |
| Perfetto MCP antarikshc/perfetto-mcp Enables natural language analysis of Perfetto traces to diagnose Android app performance issues like ANRs, jank, CPU hotspots, memory leaks, and lock contention without writing SQL queries. | |
| cep-mcp-server antarpreetsinghbajwa/cep-mcp-server Enables AI agents to inspect and configure Chrome Enterprise Premium environments, including DLP rules, content detectors, connector policies, browser telemetry, and license management. | |
| RanchHand anteew/ranchhand Enables interaction with OpenAI-compatible APIs (like Ollama) through MCP tools. Provides access to chat completions, model listings, and embeddings generation from local or remote OpenAI-style endpoints. | |
| MMA MCP Server antegral/agent-for-agent Enables users to search and query information about military service alternative companies in South Korea through the Military Manpower Administration (MMA) API. Supports filtering by service type, industry, company size, location, and recr | |
| KPIC MCP Server antegral/kpic-mcp Enables users to search and retrieve detailed pharmaceutical drug information from the Korea Pharmaceutical Information Center (KPIC) API. Supports drug name searches and detailed lookups by drug code including ingredients, usage, precautio | |
| windows-universal-mcp antelope1992-cmyk/windows-universal-mcp A local MCP server for controlling Windows desktop applications through Win32 automation, enabling window listing, launching, clicking, typing, shortcuts, screenshots, and folder monitoring. | |
| keyscope-mcp antercreeper/keyscope-mcp AI-native oscilloscope control. A pure-Python MCP service that lets LLM agents control Keysight EDUX1052G oscilloscopes via a compact DSL. | |
| symbolic-reasoning anteriorai/symbolic-reasoning Enables AI agents to drive policy evaluation over MCP by starting executions, answering policy questions from case evidence, and reading deterministic outcomes with reasoning traces, while the runtime controls which questions are asked and | |
| OSC MCP Server anteriovieira/osc-mcp-server Enables control of digital mixers (Behringer X32, Midas M32) through natural language commands in Claude Desktop, supporting fader control, muting, EQ, dynamics, effects, scenes, routing, and more via OSC protocol. | |
| Avanza MCP Server antewall/avanza-mcp Provides access to Avanza's public API for real-time Swedish stock quotes, fund information, and comprehensive market data. It enables users to perform detailed stock analysis, compare funds, and retrieve portfolio holdings through natural | |
| MCP Server antfu/nuxt-mcp-dev A server that helps AI models better understand Vite/Nuxt applications, providing enhanced context awareness for development support. | |
| ServiceNow MCP Server antgatti/ava-servicenow-mcp-server Connects AI assistants and other MCP clients to one or many configured instances, enabling generic CRUD across any table, ITSM operations, schema discovery, update-set and workflow management, batch operations, natural-language search, and | |
| puter-claude-mcp anthelis/puter-claude-mcp Provides free, unlimited access to Claude AI models via Puter.js for AI coding agents and IDEs through the MCP protocol. | |
| codex-decision-layer anthony-maio/codex-decision-layer Enables Codex to run shadow-mode evidence selection by reading source files, scoring passage relevance with Jev or local Eve models, and returning original text with provisional exclusion decisions. | |
| halobot anthony-maio/halobot An MCP server that enables AI agents to communicate with humans through Discord. Agents can send messages, create threads, wait for replies, and manage conversations across any MCP client. | |
| pulldown anthony-maio/pulldown MCP server for retrieving web pages as clean Markdown, with configurable detail levels and optional Chromium rendering for JavaScript-heavy pages. | |
| claude-telegram-alerts anthony-potts/claude-telegram-alerts Sends Telegram alerts for Claude Code status updates, including notifications for task completion, user requests, and custom status updates with normal or urgent priority. | |
| garmin-cn-mcp anthony11122/garmin-hyperos-mcp Enables AI assistants to read Garmin Connect China health and fitness data, including activities, sleep, HRV, stress, SpO2, respiration, badges, and gear, via the Model Context Protocol. | |
| This server is published as **pfSense MCP Server**. anthony8452/pfsense-mcp-server It lets users manage a pfSense firewall conversationally from Claude Desktop, Claude Code, or any MCP client — creating and reordering firewall rules, NAT, VPN tunnels, DNS, DHCP, certificates, and running diagnostics. Every configuration c | |
| Skill Retriever anthonyalcaraz/skill-retriever A graph-based MCP server that discovers, resolves dependencies, and installs the minimal set of Claude Code components—including skills, agents, and commands—tailored to specific tasks. | |
| modlens-mcp anthonyandnancy/modlens-mcp-for-reasonix MCP server that provides text-only models structured JSON vision evidence via direct vision API calls, with tools for image analysis, OCR, comparison, and lookup. It persists full evidence to disk and returns slim summaries to fit Reasonix' | |
| Bun Fun MCP Server anthonybaldwin/bun-fun A simple example MCP server built with Bun that provides basic utility tools including current time retrieval, message echoing, and number addition. Serves as a template for building MCP servers with Bun runtime. | |
| ABSD DevOps MCP Server anthonybir/absd_mcp Enables secure local filesystem operations and interactive terminal sessions for AI assistants. Provides 12 tools for file management, directory operations, code searching, and running interactive REPLs with security protections. | |
| amazon-ads-mcp anthonyblazejack/amazon-ads-py Enables Claude to read and search an Amazon Ads account, pull suggested bids and reports, and propose changes as approved plans with rollback support. | |
| Signal MCP anthonybruno/signal-mcp Provides live integrations with GitHub, Spotify, and blog RSS feeds to power a dynamic portfolio. | |
| mcp-memory-keeper anthonycho-ux/unified-agent-context A local MCP server using SQLite to unify context and memory across multiple AI agents, enabling persistent decisions and preferences without re-explanation. | |
| Weather MCP Server anthonychu/20250711-node-mcp Provides weather information tools including alerts for US states and forecasts by coordinates using the National Weather Service API. Uses streamable HTTP transport for scalable, multi-session connections. | |
| Atlassian MCP Server anthonyd23/atlassian_mcp Enterprise-grade MCP server providing 102 production-ready tools for Jira, Confluence, and Bitbucket, enabling AI agents to manage issues, pages, repositories, and more via natural language. | |
| Fatia MCP anthonydaros/fatia-mcp Enables agents to prepare, analyze and tune STL/3MF projects for Bambu Studio: editing and inspecting meshes, slicing with the Bambu Studio CLI, checking 3MFs against slicing rules, tuning and saving templates, querying a shipped knowledge |
29,501–29,550 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.