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 |
|---|---|
| Kingdee MCP Server brunoparker682/kingdeemcp Enables Claude, Cursor, Windsurf, Cline and other MCP-compatible AI assistants to query and operate Kingdee Cloud Star ERP through natural language, covering purchasing, sales, inventory, production, cost, fixed assets, financial reports, a | |
| MCP WhatsApp (uazapi) brunopaulinof/mcp-whatsapp-uazapi-publico Enables Claude to operate a company's WhatsApp through the uazapi API, reading conversation history, listing open or stalled chats and contacts by tag, sending catalogs, photos and locations, scheduling campaigns with safe delays, and keepi | |
| pluggy-mcp-server brunopedrazza/pluggy-mcp-server A read-only MCP server exposing Brazilian Open Finance personal financial data from Pluggy to MCP clients, enabling listing of connections, accounts, transactions, credit card bills, investments, and loans without moving money. | |
| nr-mcp brunopereira9/newrelic-mcp MCP server allowing AI agents to query New Relic for debugging incidents. | |
| Chiliz MCP brunopessoa22/chiliz-mcp Advanced MCP server for the Chiliz blockchain ecosystem, providing tools for fan token management, DeFi operations, sports analytics, and social sentiment tracking. | |
| QuestDB MCP Server brunoprela/questdb-mcp Enables AI assistants to interact with QuestDB time-series databases through tools for querying data, inserting records using InfluxDB Line Protocol, and managing table schemas with automatic creation. | |
| TimescaleDB MCP Server brunoprela/timescaledb-mcp Enables AI assistants to interact with TimescaleDB time-series databases through async operations, providing tools for querying, schema introspection, hypertable analysis, and time-bucketed data aggregation. | |
| Gemini Flash Image MCP Server brunoqgalvao/gemini-image-mcp-server Enables text-to-image generation, image editing, and multi-image composition using Google's Gemini 2.5 Flash Image API. Supports flexible aspect ratios and character consistency across generations. | |
| athena-mcp-server brunoruyu/athena-mcp-server Remote MCP server for AWS Athena that allows executing SQL queries, checking status, fetching results, and managing saved queries via HTTP with AWS IAM credentials. | |
| Garmin Workouts MCP Server brunosantos/garmin-workouts-mcp Enables AI agents to access Garmin Connect activities, workouts, and workout templates for querying and creating workout plans. | |
| app-store-connect-mcp brunosemfio/mcp-app-store-connect Provides read-only access to App Store Connect analytics, sales, finance, and customer review data, with tools to fetch and parse reports from Apple's Analytics Reports API and other report endpoints. | |
| Upload App MCP Server brunosemfio/mcp-upload-app Enables users to upload Android .aab files to Google Play test tracks and iOS .ipa files to TestFlight, then promote or release them to production through fastlane. Also supports rollout updates, release status checks, and confirmation-gate | |
| mcp-aseprite brunosr3003/mcp-aseprite Gives AI assistants headless control of the pixel-art editor by wrapping its command line and complete Lua scripting API. It enables inspecting sprite metadata, creating new sprites, exporting frames and packed spritesheets, and editing pix | |
| POC MCP Server brunossantana/poc-mcp-server A proof of concept server that provides tools for accessing and managing Loomer data, forms, form responses, and projects with pagination, filtering, and sorting capabilities. | |
| Juror Cloud MCP brunosuzuki242/juror Enables users to list workspaces, inspect concise review summaries and findings, and prepare or, after explicit confirmation, start or rerun an existing hosted review. It does not expose raw diffs, full reports, artifacts, screenshots, cred | |
| Hegelion brunotorres6152/hegelion Enables MCP-enabled editors and agents to run dialectical reasoning through thesis, antithesis, and synthesis, and to perform verified autocoding via a player-coach loop with optional independent backend execution. | |
| WhatsApp MCP brunotrolo/mcp_whatsapp Enables sending WhatsApp messages to a fixed recipient via a single tool, using a persistent Baileys WebSocket session. | |
| WhatsApp MCP brunotrolo/mcp_whatsapp_in_out Enables an assistant to send WhatsApp messages, images, documents, and voice alerts with delivery confirmations, read incoming messages for two-way interaction, and check connection status. | |
| Typst MCP Server brunotyurin53736/typst-mcp Enables AI models to work with Typst by converting LaTeX to Typst, validating Typst syntax, rendering Typst code to PNG images, and retrieving Typst documentation chapters. | |
| inspo brunovareliuu/inspo Enables Claude Code to research design references per page section across galleries like Awwwards, Dribbble and Mobbin, render the user's page in multiple style directions with live 3D components, and collect votes on a local board. It then | |
| Houtini LM brunowisniewski097/houtini-lm It enables Claude or any MCP client to delegate bounded tasks such as code review, boilerplate generation, commit messages, format conversion, and embeddings to local or cloud OpenAI-compatible LLMs, reducing token usage and providing a sec | |
| jina-web-mcp brunwo/jina-search-mcp Enables web search and webpage scraping using Jina AI services. | |
| Stripe MCP Server brunwo/mcp-stripe A remote MCP server implementation that integrates with Stripe, enabling AI assistants to interact with the Stripe API for payment processing functionality. | |
| Enterprise MCP Server bruriah1999/mcp_server Production-grade FastMCP 3.x server template for scalable semantic tool retrieval, dynamic providers, paginated tool lists, and role-based progressive disclosure. | |
| muster brutalsystems/muster Enables launching and supervising local Codex and Claude Code agent sessions and one-shot tasks, exposing run, list, stop, and output operations over MCP with session-scoped permissions and sandbox controls. | |
| tincan brutalsystems/tincan Enables live Claude Code and Codex sessions on the same machine to send each other text messages directly. It provides peer discovery, message sending, and a shared message log through MCP tools. | |
| remote-mcp-server-authless bruxley/remote-mcp-server-authless A remote MCP server deployed on Cloudflare Workers without authentication, enabling connection to AI Playground and Claude Desktop with custom tools. | |
| GSAP Master MCP Server bruzethegreat/gsap-master-mcp-server Transforms Claude into a GSAP animation expert with AI-powered natural language animation creation, complete API coverage, and production-ready patterns for all GSAP features and plugins. | |
| apic brwbo/apic A server that compiles a web app's public, read-only UI into verified, typed MCP tools, and fulfills user requests against those compiled flows. | |
| cross-search bryan-cmf/crosssearch-mcp Enables multi-engine parallel search with cross-validation, combining Brave, Tavily, DuckDuckGo, Wikipedia, Bing, and Mojeek, and labeling results with confidence levels based on engine agreement. | |
| Agent Co-Governance Toolkit bryan123466/taskcarry Enables Codex users to coordinate multiple workspaces around a long-running project by persisting task state, decisions, stage deliverables, file references, and continuation notes for traceable cross-session collaboration. | |
| Fantasy Football Data MCP Server bryan3eng/sportmicro-fantasy-football-data-mcp Enables MCP clients to query documented Sportmicro football endpoints for players, teams, matches, player statistics, and weekly/season projections through narrow, read-only, validated tools. | |
| WCAG Color Contrast MCP Server bryanberger/mcp-wcag-color-contrast Enables accurate WCAG color contrast checking and accessibility analysis by calculating actual contrast ratios between color pairs, checking compliance levels, and analyzing luminance values for web accessibility. | |
| jmap-mcp bryanberger98/jmap-mcp Enables an AI assistant to access and manage mail, calendar, contacts, files, sharing, and Sieve through a local Stalwart JMAP server, with configurable write policies that require confirmation for irreversible actions. | |
| Twitch MCP Server bryancaves/twitch-mcp Enables access to Twitch API data for retrieving channel statistics, viewership information, stream status, and discovering channels and game categories. Provides real-time Twitch data including follower counts, current viewer numbers, and | |
| contrib-radar bryandero98/contrib-radar Enables AI agents to evaluate real OSS contribution opportunities by scoring issues on availability, competing PRs, staleness, and maintainer sentiment, including live feasibility checks for any repository. | |
| identityOS MCP server bryandoreian/identityos-mcp Enables AI assistants to request read-only cardology readings such as birth cards, spreads, daily pulls, and compatibility, with astrology, Human Design, Gene Keys, numerology, feng shui, and BaZi planned on the same hosted service. | |
| Power Switch Pro MCP Server bryankemp/power-switch-pro-mcp MCP server for controlling and monitoring Digital Loggers Power Switch Pro devices, enabling outlet control, power monitoring, and device management through natural language. | |
| Weather MCP Server bryankemp/weather_mcp Provides access to National Weather Service data, enabling users to retrieve real-time weather forecasts for specific coordinates and active weather alerts by US state. | |
| Cullyard bryankwandou/cullyard Enables an MCP client to scan a local folder, sort photos, video, music, documents, and PDFs into lanes, and create resized or trimmed copies while showing moves in a browser desk. It can also seal a SHA-256 digest of the sort log to Solana | |
| Cutloupe bryankwandou/cutloupe Enables AI agents to build and edit a real video timeline — cuts, text, shapes, keyframes, captions and music — in a live studio the user can watch and edit alongside, rendering actual frames so the agent can verify its own work instead of | |
| mcp-canva bryankwandou/mcpcanva Enables interaction with Canva through the official Canva Connect API via OAuth, including listing and creating designs, uploading assets, exporting, brand template autofill, resizing, catalog access, and optional desktop screen control. | |
| mcp-capcut bryankwandou/mcpcapcut Enables users to create and edit local video projects, add video/photo/audio/text, trim and move clips, apply templates/effects, and deploy edits to the desktop app through a live web editor. | |
| REA bryankwandou/rea-agents Lets agents inspect native binaries, JavaScript/Electron applications, .NET assemblies, websites, and runtime behavior, returning evidence-backed findings and limitations for understanding and reimplementing features. | |
| mcp-ebook-server bryanlabs/mcp-ebook-server Provides AI assistants with direct access to your ebook library, enabling listing books, reading chapters, and searching across books via the Model Context Protocol. | |
| yearbook-mcp-public bryanmichael-hue/yearbook-mcp-public e-yearbook.com MCP (Model Context Protocol) server. The server lets any MCP-aware AI agent search over 300,000 U.S. yearbooks indexed by name.
Over 22,000 schools across all 50 U.S. states and territories
Over 300,000 distinct (school, year | |
| aurum-recall bryanslongbl-sys/aurum-recall A memory system for AI agents that maintains a human-readable, typed Markdown knowledge base with an always-in-context index, enabling recall, correction, and trust decay through MCP. | |
| searxNcrawl bryant0211/searxncrawl Enables AI agents to search the web through configured providers and crawl single pages or entire sites into clean, deduplicated Markdown or JSON, including authenticated pages. | |
| kali-mcps bryant48/awsome_kali_mcpservers Enables running Kali Linux security tooling through MCP, including Nmap network scanning, nm symbol analysis, objdump disassembly, strings extraction, and tshark traffic capture and pcap analysis. Also supports executing commands in an isol | |
| Luma MCP bryant927/luma-mcp Enables AI coding assistants without native vision to analyze screenshots, error messages, UI layouts, and documents through a single image-understanding tool that routes requests to multiple vision LLM providers. It accepts local files, re |
35,801–35,850 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.