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 |
|---|---|
| yari-medic-mcp 0xc1pher/yari-medic-mcp MCP server for the Yari medical system, enabling access to patient records, appointments, financial data, and AI-assisted medical analysis. It provides 18 tools to query and manage medical information through natural language. | |
| youtube-transcript-mcp 0xcafebeef/free-youtube-transcript-mcp Enables fetching YouTube video transcripts from any URL without API keys, browser, or OAuth, with honest error reporting for missing transcripts and support for multiple languages, formats, and resilient provider fallbacks. | |
| ScoutAgent 0xcaptain888/scout-agent MCP server that enables AI workflows to query on-chain AI Scout agents, leaderboards, and prediction markets on X Layer for the World Cup. | |
| qt-mcp 0xcarbon/qt-mcp An MCP server for inspecting, debugging, and interacting with PySide6 desktop applications. It enables AI agents to capture UI snapshots, read widget properties, and perform actions like clicking buttons or typing text. | |
| motor-telemetry-mcp 0xcf02/motor-telemetry-mcp Exposes industrial motor telemetry data to AI agents via MCP and REST, enabling natural-language queries about motor status, health, and alerts. Provides a single tool and resource for retrieving real-time motor metrics and escalating criti | |
| mcptube-vision 0xchamin/mcptube Transforms YouTube videos into a persistent, structured knowledge base using transcripts and visual frame analysis, enabling knowledge compounding and natural language querying. | |
| cort4ex-mcp 0xchampi/cort4ex-mcp Provides access to 224 battle-tested skills plus multi-agent orchestration, exposed as tools for Claude or Codex. | |
| Templonix Lite MCP Server 0xcjt/templonixlite A local-first personal AI agent infrastructure that extends Claude Desktop with tools for Google services, web scraping, local memory, knowledge upload, and dynamic workflows via MCP. | |
| RugSense 0xcnr0/rugsense Agent-native scored launch intelligence for Base blockchain, providing opportunity/risk scores and AVOID/WATCH/HOT decisions per fresh launch via x402 pay-per-call API. Enables trading/research agents to act directly on structured launch da | |
| ArmSight 0xconsole/arm-sight-agent An MCP server that autonomously optimizes ONNX ML models for Arm64 deployment, providing tools to analyze models, apply real INT8 quantization, benchmark performance, and generate Arm64-optimized Docker deployment packages. | |
| BaseSentinel 0xconsole/base-sentinel-agent AI DeFi risk monitor for Base L2 that exposes MCP tools for real-time protocol health checks, anomaly detection, risk reporting, and threshold alerts. | |
| Cockroach Memory Agent 0xconsole/cockroach-memory-agent Provides persistent, globally-distributed memory for AI agents using CockroachDB's MCP Server and AWS S3 backups, with session isolation, audit trails, and full-text search. | |
| DataCompute Agent 0xconsole/datacompute-agent An autonomous MCP server that fetches datasets from IPFS/Filecoin, performs computation (anomaly detection, statistics, data quality scoring), and stores results via Multi-Chain Storage simulation. | |
| DeFi Sentinel X MCP Server 0xconsole/defi-sentinel-x Autonomous AI agent monitoring X Layer DeFi protocols via real RPC calls, providing MCP tools for pool scanning, anomaly detection, risk scoring, alerts, position health checks, and audit trails. | |
| flare-bridge-sentinel 0xconsole/flare-bridge-sentinel MCP server for monitoring Flare's interoperable asset ecosystem, providing real-time on-chain data for FAssets, FTSOv2 prices, and bridge states. It exposes 8 MCP tools for anomaly detection, risk scoring, and automated alerts. | |
| DeFi Security Sentinel 0xconsole/orion-sentinel An autonomous AI agent that monitors Base chain DeFi protocols for security anomalies and alerts via MCP tools. | |
| scraper-health-mcp 0xconsole/scraper-health-mcp Enables autonomous self-healing scraper fleet management for Bright Data Scraper Studio, with health checking, anomaly detection, and automated AI-driven scraper repair and approval. | |
| SerpShield 0xconsole/serpshield Enables AI agents to scan real-time search data for brand threats, security vulnerabilities, and DeFi risks via MCP-compatible tools. | |
| Thermal Sentinel MCP Server 0xconsole/thermal-sentinel-agent Enables AI agents to monitor urban heat risk, detect heat waves and anomalies, and generate alerts with urban-planning recommendations via the FortyGuard Temperature API. | |
| astrolog-mcp 0xctx/astrolog-mcp Enables AI assistants to retrieve precise astrology calculations, including natal charts, transits, composites, harmonic midpoints, and ranked daily aspects, using real ephemeris data rather than guesses. | |
| BackPow MCP Server 0xcwalter/backpow-mcp-server Enables AI assistants to access live mining data for 126+ proof-of-work networks and 770+ hardware models, including network difficulty, hashrate, solo-mining odds, cost of production, hardware profitability, and mining news. | |
| jobs-mcp 0xcybin/jobs-mcp Enables searching for job opportunities across multiple platforms like Upwork, RemoteOK, and GitHub while automatically generating tailored application proposals based on keyword scoring. It includes tools for scanning all sources simultane | |
| AI Proof of Us MCP Server 0xddneto/ai-proof-of-us Records privacy-preserving receipts for AI-assisted tasks and enables optional onchain reward claiming via AIPOU tokens. Integrates with MCP-compatible clients like Claude and Cursor. | |
| imessage-mcp 0xdeadd/imessage-mcp Lets Claude Code read and search your macOS iMessage history locally, with an optional send tool that is off by default. | |
| Kanban MCP 0xdzik/kanban-mcp A comprehensive project management system that provides a full-featured Kanban board and dashboard accessible to AI agents. It enables agents to programmatically manage projects, tasks, and workflows through a suite of 13 specialized tools | |
| Ruckus Virtual SmartZone MCP Server 0xekho/ruckus-vsz-mcp MCP server for managing Ruckus vSZ wireless controllers, providing 52 tools across 12 modules to query and manage APs, WLANs, zones, clients, alarms, and more, enabling LLM-driven network operations. | |
| PinchMCP 0xel1yahu/pinchmcp An MCP server that analyzes Linear feature dependencies using dominator analysis to identify the keystone ticket that unblocks the most downstream work. | |
| WebSex 0xelectr0n/websex Provides a container-native offensive security MCP toolkit that runs 179 tools — executable-backed scanners plus deterministic, evidence-first vulnerability probes — against authorized engagement targets. Enables scope-guarded pentesting wo | |
| evm-agent-toolkit 0xendale/evm-agent-toolkit An MCP server that gives autonomous coding agents deterministic, schema-validated tools for EVM smart contract development — security scanning, gas profiling, compiler diagnostics, and transaction simulation. | |
| x402 On-Chain Data MCP Server 0xetherial/x402-onchain-mcp-server Pay-per-call MCP server for on-chain blockchain data including wallet profiles, token metrics, protocol TVL, and gas prices. | |
| Twenty CRM MCP 0xfabrica/twentycrm-mcp Enables MCP clients to read, search, create, update, and manage records in Twenty CRM with a safe, composable 14-tool interface and guarded destructive operations. | |
| openfoam-mcp 0xffd/openfoam-mcp Enables AI agents to drive OpenFOAM end to end: cloning tutorials or custom cases, editing dictionaries, meshing and running solvers in the background, tracking convergence and job status, and analyzing results. It also renders flow images | |
| mcp-feedback-web 0xffff87/mcp-feedback-nodesktop Provides a web-based interactive feedback server for MCP, replacing desktop GUI with a browser interface supporting full CJK input and bilingual UI. | |
| Real Estate MCP Server 0xfftobit/re-mcp Enables structured real estate workflows including property search, agent/client management, market intelligence, mortgage calculations, valuation, investment analysis, and document ingestion, with offline-first capabilities and optional li | |
| Node MCP Template 0xfieldsy/node-mcp-template Opinionated template for building Node.js stdio and HTTP MCP servers. | |
| 0xGasless MCP Server 0xgasless/mcp A Model Context Protocol server that enables gasless blockchain transactions directly from Claude conversations, allowing users to execute transfers, swaps, and other operations without holding native tokens. | |
| technocore-mcp 0xgoodcrypto/technocore-mcp Enables agents to read and write technocore.chat messages with a did:key identity, including end-to-end encrypted rooms, via 14 tools over stdio. | |
| ethereum-tools 0xgval/evm-mcp-tools A comprehensive toolkit for Ethereum blockchain analysis within Claude AI, enabling contract auditing, wallet analysis, profitability tracking, and on-chain data retrieval. | |
| EVM Proxy MCP 0xgval/evm-proxy-mcp MCP server providing AI assistants with tools for advanced EVM smart contract analysis, including proxy detection, implementation resolution, and security analysis. | |
| Onchain MCP Server 0xgval/evm-python-mcp Provides tools for querying onchain data across 12+ blockchain networks, including token balances, transaction analysis, and smart contract security auditing. It enables users to interact with multiple EVM-compatible chains and perform deep | |
| X Tools for Claude MCP 0xgval/twitter-x-mcp-server A lightweight toolkit that enables Claude to search Twitter with natural language queries and display results based on user intent, supporting features like tweet filtering, pagination, and flexible output formatting. | |
| vsc-mcp 0xh3x/vsc-mcp Enables interaction with VSCode and its forks like Cursor and Windsurf, supporting file management (opening/closing files) and theme management. | |
| Frida Game Hacking MCP 0xhackerfren/frida-game-hacking-mcp Provides Cheat Engine-like capabilities for game hacking and reverse engineering through Frida, enabling memory scanning, value modification, pattern matching, function hooking, and code injection across processes. | |
| procmon-mcp 0xhackerfren/procmon-mcp An MCP server that provides AI assistants with real-time access to Windows internals including processes, kernel traces, event logs, services, drivers, and PE analysis. | |
| fathom-fyi 0xhashy/fathom-fyi Financial intelligence for AI agents. 31 tools across 8 data sources — regime, derivatives, stablecoin flows, momentum, volatility, macro, DeFi, weather patterns, political cycles, seasonality. The context layer between your agent and a bad | |
| cPanel MCP Server 0xhayd3n/cpanel-mcp-server A comprehensive MCP server for managing cPanel hosting accounts through AI assistants. It supports DNS, email (DKIM/SPF), databases, domains, SSL, PHP, cron jobs, security, Git deployment, and more. | |
| Pi Desktop Bridge 0xhayd3n/pi-desktop-bridge Enables MCP clients to capture screenshots and control a Raspberry Pi's Wayland desktop over an existing SSH connection with mouse, drag, scroll, keyboard, and Unicode typing actions. Input tools return fresh screenshots, enforce single-cli | |
| pursr-mcp 0xheycat/pursr Enables AI assistants to capture screenshots, run visual diffs, accessibility audits, and batch sweep plans for web pages via MCP tools. | |
| MCP Twitter 0xhijo/mcp_twitter A Model Context Protocol server that enables AI models and applications to interact directly with Twitter/X, providing capabilities to create posts, reply to tweets, retrieve user data, and manage account actions. | |
| perplexity-mcp 0xhumban/perplexity-mcp Enables AI assistants to perform web searches and retrieve real-time information using Perplexity AI's Sonar models, with support for multiple search modes and easy integration with MCP clients. |
21,551–21,600 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.