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 |
|---|---|
| pinboard-mcp anton072/pinboard-mcp Enables Claude Desktop to save bookmarks to Pinboard by generating Japanese summaries and tags, with private saving and overwrite for existing URLs. | |
| Zenith MCP Server antonatanasovalekseev-coder/zenith-mcp Personal habit tracking MCP server for a 90-day mission, tracking 6 non-negotiable habits with Supabase backend, exposes tools for logging and viewing progress. | |
| Deliberation antonbabenko/deliberation Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures which models earn their seat. | |
| ashby-mcp antonber/ashby-mcp Enables integration with Ashby ATS to search candidates, view applications, submit interview feedback, and manage recruiting workflows through natural language. | |
| BrianKnows MCP Server antoncoding/mcp-brianknows An MCP server that connects Claude to BrianKnows' blockchain knowledge base, allowing users to search for blockchain/DeFi information and interact with a specialized agent across multiple knowledge bases. | |
| screenshot-mcp-server antondemidov/screenshot-mcp-server A reliable MCP server for taking screenshots with customizable timestamp overlays, region captures, and file management capabilities across macOS, Windows, and Linux. | |
| weekplan-mcp-server antonderegt/week-plan-mcp MCP server enabling AI assistants to manage recipes and ingredients in the WeekPlan app via its REST API. | |
| Ozon API MCP Server antondrpq/ozon-api-mcp-server Enables managing Ozon Seller and Performance APIs through MCP, covering products, stocks, prices, orders, finance, analytics, advertising, reviews, and chat operations. | |
| Wildberries API MCP Server antondrpq/wildberries-api-mcp-server MCP server that simplifies interaction with Wildberries API, providing unified access to analytics, promotion statistics, sales funnel data, search queries, stock reports, and EVIRMA PRO report imports. | |
| companies-house-mcp antongmorris/companies-house-mcp Production-grade MCP server for the UK Companies House API, enabling AI assistants to search companies, get profiles, list officers, filings, and PSCs. | |
| SpeedyIndex MCP antongulin/speedyindex-mcp Enables MCP clients to retrieve read-only SpeedyIndex account balances, including token, indexer, and checker wallets with an observation timestamp. | |
| Civil3D MCP Server antonhofstader/civil3d-mcp-python-com Connects Claude to a running Autodesk Civil 3D instance via COM automation to perform drawing, surface, alignment, COGO point, line, and corridor operations. | |
| Slack MCP antonhofstader/slack-mcp A .NET-based Model Context Protocol server and Python client for interacting with the Slack Web API. It enables AI models to manage channels, send messages, retrieve chat history, and handle emoji reactions. | |
| mcp-google antonio-byte10/mcp_google_public Local server that lets Claude Code and Claude Desktop drive NotebookLM and Google Flow through the user's own logged-in Edge or Chrome session instead of a paid API, covering notebooks, sources, cited answers, Studio outputs (audio/video ov | |
| idea-reality-mcp antonio-mello-ai/idea-reality-mcp Pre-build reality check for AI coding agents — searches 5 real databases (GitHub, Hacker News, npm, PyPI, Product Hunt) to check whether an idea already exists before you build it. | |
| mcp-google antonio-mello-ai/mcp-google MCP server for Google APIs — Gmail and Calendar tools for LLM agents. | |
| mcp-slack antonio-mello-ai/mcp-slack Enables Slack integration with tools to list channels, read messages, and post messages using a bot token. | |
| yt-dlp-mcp-server antonio-orionus/yt-dlp-mcp-server Enables AI agents to inspect, plan, download, and postprocess media from YouTube and other sites using yt-dlp, with safety and full option support. | |
| a11y-mcp antonio-rmrz/a11y-mcp Enables web accessibility audits using axe-core, allowing users to scan URLs, check WCAG compliance levels, and export reports. It uses an anti-detect browser to bypass Cloudflare and other bot protection. | |
| Smart Coding MCP antonio77786/smart-coding-mcp Enables AI coding assistants to search codebases by meaning using local AI embeddings, with tools for indexing, cache management, workspace switching, status checks, and package version lookup. It supports incremental and progressive indexi | |
| VisiblyAI MCP Server antonioblago/visiblyai-mcp-server Provides SEO tools for Claude Code, including free local tools and paid API-powered analysis for keyword research, traffic analysis, backlinks, OnPage audits, and more. | |
| TODO list MCP server (Exercício 4.2) antonioddiniz/todo-mcp-4.2 Local MCP server that exposes tools for a TODO list, acting as an adapter between an AI agent and a REST API (localhost:8000). | |
| LAPRAS MCP Server antoniodo8374/lapras-mcp-server Enables users to search job listings and retrieve or update LAPRAS career profile information, including work experiences, job summaries, career goals, and technical skills, through natural language. Requires an API key for profile-related | |
| Typst MCP Server antoniodo8374/typst-mcp Enables AI models to work with the Typst typesetting system by converting LaTeX snippets to Typst, validating Typst syntax, and rendering Typst code as PNG images. It also lets models browse and retrieve chapters of the Typst documentation | |
| Railway MCP Server antonioevans/railway-mcp Enables management of Railway.app infrastructure through natural language, including deploying services from GitHub repos or Docker images, managing environment variables, monitoring deployments, and configuring networking and volumes. | |
| RunPod MCP Server antonioevans/runpod-mcp-ts Enables interaction with the RunPod REST API to manage GPU pods, serverless endpoints, templates, network volumes, and container registry authentications through natural language. | |
| trackly antoniohreyes/trackly Enables AI clients to manage time tracking directly, including starting and stopping timers, handling workspaces, projects, and tags, and generating PDF/CSV reports and invoices. | |
| Gemini Image MCP Server antoniolg/gemini-image-mcp-server Enables image generation and editing using Google Gemini AI with support for multiple aspect ratios, context images, custom styles, and watermark overlays. Optimized for creating social media content with automatic file saving and flexible | |
| postiz-mcp antoniolg/postiz-mcp MCP server for managing social media posts across multiple platforms using the Postiz API. Supports creating, updating, deleting posts, and generating videos. | |
| claude-patent-creator antoniomartin947/claude-patent-creator Exposes 20+ MCP tools that let clients query MPEP/USC/CFR rules through hybrid vector and lexical search, run prior-art searches across 100M+ patents via Google BigQuery, flag compliance problems in draft claims and applications, and genera | |
| Medical MCP Server antoniomartin947/medical-mcp Enables AI assistants to query authoritative sources such as the FDA, WHO, PubMed, RxNorm, and ClinicalTrials.gov for drug information, health statistics, clinical guidelines, and literature with evidence grading. It runs locally with no AP | |
| freellmpool antonioozkan66/freellmpool Pools 178 enabled chat routes across 23 LLM providers behind a single OpenAI-compatible endpoint, letting compatible clients and coding agents query hundreds of cataloged models with automatic failover, local usage tracking, and a credentia | |
| Datadog Cost MCP Server antoniopablo/datadog-mcp-server Lets you inspect a Datadog organization's usage and answer cost questions in plain English, helping identify savings opportunities. | |
| AWS Advisor MCP Server antonioschaffert/my-dev-mcp Provides AWS service recommendations based on use case descriptions and allows browsing AWS services organized by categories. Helps users discover the most suitable AWS services for their specific technical requirements. | |
| S&P 500 MCP Server antoniostavrou320/sp500-mcp-server Enables querying S&P 500 company data from Supabase through MCP tools that cover company fundamentals, annual financial trends, historical OHLCV prices, news with sentiment filtering, executive officers and compensation, and SEC filing hist | |
| LunchMoney MCP Server antoniotamkoc/lunchmoney-mcp Enables AI assistants and other MCP clients to read and manage personal finance data, including transactions, categories, tags, budgets, recurring items, manual and Plaid accounts, crypto holdings, and balance history, with full CRUD operat | |
| MeshMind antoniovandijck/meshmind A single MCP server that merges three context-engineering ideas into one toolset for AI agents | |
| uml-atlas antoniovincenzo/uml-atlas Provides MCP tools to read, validate, propose, and review architecture models and UML diagrams in local workspaces. | |
| cartola-mcp antoniovuono/cartola-mcp Connects Claude to Cartola FC, enabling queries about matches, player scores, and market information through natural language. | |
| vibescience-mcp antonixo/vibescience-mcp A scientific experiment log MCP server for AI agents that stores predictions, causal claims, and verdicts, enabling queryable causal maps and calibration of intuition over diagnostics. | |
| Slack MCP Server antonkazlouski-orca/slack-mcp Provides complete Slack Web API integration with 9 tools for reading messages, managing channels, searching content, and interacting with Slack workspaces. | |
| MCP Security Tools Server antonlarimaraton/mcp-accses An MCP server that integrates multiple security and reconnaissance tools (Nmap, Cariddi, ParamSpider, Metasploit, web scraping) for AI systems, enabling automated network scanning, API discovery, vulnerability testing, and remote access via | |
| mcp-stealth-browser antonli-pm/mcp-stealth-browser Enables stealth web browsing and search with Cloudflare Turnstile bypass, dynamic residential proxy rotation, and token-optimized markdown extraction. | |
| Inkdex antonlunden/inkdex Enables semantic search over local markdown documentation by indexing files and ranking results using vector similarity and BM25 fusion. | |
| Vehicle MCP antonlunden/vehicle-mcp Enables AI assistants to control vehicles by checking battery status, managing climate, and locking/unlocking doors via Skoda Connect integration. | |
| kicad-mcp antonmadto/kicad-mcp MCP server that analyzes, reviews, and exports KiCad 9 designs, with live board editing via IPC and a built-in design-review engine. | |
| Tastecraft antonmareo10/tastecraft Exposes Qloo taste-graph analysis of a restaurant's audience as MCP tools, letting existing agents retrieve a restaurant's entity, cross-domain affinities, over-indexing dishes and vibes, and demographic skew, or generate a fully verified w | |
| brick-mcp antonod1988/brick-mcp Enables AI assistants to create, inspect, and edit LEGO models in BrickLink Studio and LDraw files, with atomic construction steps, validation, rollback, illustrated instructions, and native Studio stability checks. | |
| secure-telegram-mcp antonorlov/secure-telegram-mcp Allows AI clients to securely interact with Telegram accounts through scoped endpoints, with encrypted session storage and per-tool permission checks. | |
| workbench-mcp antonov2010/mcp-dev A Python-based MCP server for interactive PostgreSQL data exploration, schema discovery, and safe SQL execution with support for stored procedures. It also enables automation through external HTTP API requests and local bash script executio |
29,601–29,650 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.