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 |
|---|---|
| Weather MCP Server azwawy/mymcp1 A demo MCP server that provides AI assistants access to live US weather data via the free National Weather Service API, offering forecast and alert tools without requiring an API key. | |
| harvest-forecast-mcp azx-pbc-oss/harvest-forecast-mcp An MCP server that integrates Harvest time tracking and Forecast resource scheduling APIs, enabling AI agents to track time, manage projects, and handle assignments and scheduling. | |
| band-bridge azyywanan/band-bridge Enables AI frontends to read Xiaomi Smart Band 10 Pro health data (heart rate, sleep, steps, battery) and send haptic notifications to the wrist via the knock tool. | |
| Kali MCP Server azza39925/kali-mcp-server Enables AI assistants to perform authorized penetration testing and security assessments by exposing 20+ Kali Linux security tools (nmap, sqlmap, gobuster, hydra, etc.) through a safe, validated interface with command allowlists, rate limit | |
| YouTube Music MCP azzacalvin/youtube-music-mcp Enables managing YouTube Music playlists and searching songs via the YouTube Data API v3, deployed as a free Cloudflare Worker. | |
| logistics-mcp azzaraell/logistics-mcp Enables AI assistants to query and manage logistics shipment data, supporting operations like tracking, quoting, and performance analysis via nine tools backed by a demo dataset or a REST API. | |
| pgguard-mcp azzaraell/pgguard-mcp Read-only Postgres access with a policy gate that blocks writes and restricts visible tables and columns. | |
| MCP_Documents azzindani/mcp_documents Enables local, offline document extraction and manipulation—PDF first but also HTML, DOCX, XLSX, PPTX, EML, EPUB, Markdown, and plain text—through tools for probing, locating, extracting, converting, assembling, OCR, protecting, and redacti | |
| Finance MCP Server azznggu/finance-mcp-server Provides real-time financial data including exchange rates, Bitcoin prices, gold prices, and S&P 500 index via MCP tools and resources. | |
| Signal MCP b-1000r4/signal-mcp Provides a durable SQLite-backed work queue for AI agents, enabling creation, claiming, starting, handing off, failing, and completing work items via MCP tools. | |
| Kontrol b-a-m-n/kontrol A self-hosted MCP server that enables AI coding agents to read, edit, search, and run code in local projects with human review loops and policy controls. | |
| TophatMCP b-a-m-n/tophatmcp An authenticated OpenAI-compatible inference gateway with an async job broker that bridges a coding agent to a ChatGPT MCP worker, enabling ChatGPT to process inference requests via a tunnel. | |
| Project Intelligence MCP Server b-bhupendra/fastapi-mcp-server Enables AI clients to search and analyze code/docs through a central Pinecone-backed vector store, inspect project inventories and git sync status, rank work by urgency, and perform deep architectural audits via MCP. | |
| HexStrike AI MCP Server b-bogus/hexstrike-ai_mcp_server AI-powered cybersecurity automation platform with 150+ security tools and 12+ autonomous AI agents for penetration testing, vulnerability assessment, and bug bounty hunting. Enables comprehensive security testing through intelligent tool se | |
| AWS Cost Explorer MCP Server b-deepak/aws-mcp-cost-explorer Enables querying AWS costs and usage data from Claude Desktop through the Cost Explorer API. | |
| MCP System Tools Server b-dinesh9/mcp-system-tools Provides AI agents with tools to retrieve live system statistics (CPU, memory) and safely evaluate basic arithmetic expressions. | |
| message-container b-hs/message-container Enables AI clients to read and search macOS Messages history through a read-only MCP interface. | |
| Edenred Plus MCP b-mahdj/edenred-plus-mcp Read-only MCP server for Edenred Plus that enables checking benefit balances, transactions, and deals via local browser authentication. | |
| MLflow Prompt Registry MCP Server b-step62/mcp-server-mlflow Enables access to prompt templates managed in MLflow through Claude Desktop, allowing users to instruct Claude with saved templates for repetitive tasks or common workflows. | |
| mcp-steampipe b0ttle-neck/mcp-steampipe This is an MCP written for steampipe. This Steampipe MCP tool allows Claude to interact directly with your Steampipe installation using natural language requests. It executes provided SQL queries via the Steampipe CLI and returns the data r | |
| Super-Productivity-MCP b0x42/super-productivity-mcp An MCP server that connects AI assistants to Super Productivity for managing tasks, projects, and tags. Supports quick capture, batch triage, and full planning sessions through natural language. | |
| pgwarden b0yko/pgwarden Enables AI assistants to query Postgres as the signed-in person through OAuth 2.1/OIDC, with database-enforced read-only queries, PII masking, human-approved writes, and a tamper-evident audit log. | |
| Website Generator b12io/website-generator-mcp-server B12's model context protocol server for generating websites with AI | |
| Cloudflare Image MCP b19805652/cloudflare-image-mcp-s3 Image generation MCP server running on Cloudflare Workers, supporting multiple models like FLUX and SDXL with OpenAI-compatible endpoints. | |
| Kali MCP Sandbox b1a0k/kali-mcp-sandbox Enables MCP-compatible AI clients to run curated Kali Linux security tools such as nmap, gobuster, nikto, sqlmap and netcat inside an isolated microVM sandbox. Commands execute as asynchronous jobs with readable output, cancellation and per | |
| Helix MCP Server b1krams/helix-mcp A local-first MCP server providing secure workspace file operations, offline full-text search, and web search/fetch capabilities without requiring API keys. | |
| dubbo-mcp b1n9bna/dubbo-mcp * Connects AI coding agents (Cursor, Claude Desktop, Codex CLI) to Apache Dubbo RPC microservices. Native generic
invocation, dual ZooKeeper & Dubbo Admin routing, sub-millisecond call caching, zero JAR dependencies. | |
| 010editor-mcp b1tninja/010editor-mcp Enables agents to run SweetScape 010 Editor Binary Templates and Scripts headlessly against local files. It provides tools to locate the editor binary, execute templates or scripts, and use controlled exit behavior for compile and runtime f | |
| Scrapy MCP b1unt-alt/scrapy-mcp A general-purpose MCP server for crawling and extracting structured data from any website. Supports tools for crawling, single-page extraction, search-and-crawl, and schema extraction. | |
| @b2b-saas-inc/olli-mcp-server b2b-saas-inc/olli-social-mcp Lets LLMs manage social media presence via olli.social API, with tools for campaigns, drafts, analytics, and more. | |
| uc-remote-mcp b2dmx/uc-remote-mcp Enables natural language interaction with Unfolded Circle Remote 3/Remote Two for configuration, button mapping, UI editing, and backup/restore. | |
| tm-finder-mcp b2tm/tm-finder-mcp MCP server that enables trademark searches through the TM Finder Public API, with support for API key authentication and idempotency for retries. | |
| Vestibule b34nst4lk/vestibule A plugin-based MCP server that securely exposes custom tools to AI agents, keeping sensitive information hidden while enabling operations like email whitelisting through pluggable plugins. | |
| Hot-MCPManager b3i4hu/hot-mcpmanager Aggregates multiple MCP servers into a single unified endpoint with hot-plugging, multi-protocol support, and management via web and CLI. | |
| hydrawise-mcp b3nw/hydrawise-mcp MCP server for Hunter Hydrawise irrigation controllers, exposing the Hydrawise REST API as tools for AI agents to manage watering schedules and controller settings. | |
| Playwright MCP Server b3nw/playwright-browserless-mcp A Model Context Protocol server that enables AI assistants to perform web automation tasks by connecting to remote Playwright/browserless instances, supporting navigation, screenshots, HTML extraction, and element interaction. | |
| Intervals.icu MCP Server b3r3z/intervals-mcp-server Enables Claude and ChatGPT to access and manage Intervals.icu data, including activities, events, wellness metrics, power curves, and custom items through natural language. | |
| Dynamic Shell Command MCP Server b48f8f5xg2-blip/dynamic-shell-server Enables secure execution of shell commands through a dynamic approval system that prompts for user authorization on first use, with persistent command storage and comprehensive audit logging. | |
| reqtrace-mcp b4ked/reqtrace-mcp Enables tracing every code change to a requirement and every requirement to a test that actually exercises it, with gap analysis, coverage, change-impact mapping, and evidence reports for Python and C/C++. Enforces human-only sign-off and a | |
| cpanel-mcp-server b4rt3kk/cpanel-mcp-server MCP server for managing cPanel accounts and WHM servers via UAPI/WHM APIs. Supports domains, DNS, email, MySQL, files, cron, SSL, PHP, backups, and hosting accounts across multiple environments with read-only mode and security controls. | |
| awesome-base-mcp b5-software/awesome-base-mcp Enables an autonomous agent wallet on Base to make payments, approve tokens, swap on Uniswap V3, Aerodrome, 0x and CoW Protocol, lend/borrow via Aave V3 and Morpho Blue, trade perps on Hyperliquid, and enforce risk policies via blacklists, | |
| MCP Nightscout b77ai/nightscout Connects AI assistants to Nightscout for real-time glucose monitoring, analysis, and treatment logging, enabling natural language interaction with CGM data. | |
| adalm2000-mcp b83c/adalm2000-mcp MCP server for ADALM2000 (M2k) — AWG, scope, and PSU control via FastMCP 3.4. | |
| before-you-pr b84330808/before-you-pr Enables an agent to check a repository's contribution rules (AI policy, CLA/DCO, assignment and claim windows) and an issue's status (linked open, merged and closed PRs, active claims, merge friendliness) before writing any code. It returns | |
| mcp-server-jma b84330808/mcp-server-jma Enables access to Japan Meteorological Agency data through MCP, covering weather forecasts, warnings, earthquakes with seismic intensity, tsunami bulletins, and volcano alerts, with place-name lookup in kanji, kana, or romaji and no API key | |
| Stock Valuation MCP Server b9b4ymin/mymcpserver Provides professional-grade financial analysis tools for Thai stock markets, including PE Band Analysis, DDM, DCF valuation models, real-time SET Watch API data, complete financial statements, and historical ratio analysis with investment r | |
| mcp-proxy ba0f3/mcp-proxy Enables AI agents to make bounded public HTTP/HTTPS requests through a single curl MCP tool, with strict security filtering, redirect validation, and size/time limits instead of granting general network access. | |
| searxng-mcp baadir/searxng-mcp An MCP server that wraps a local SearXNG instance to provide private, customizable web search capabilities. It enables AI assistants to perform queries with support for specific parameters like results limits, language, and time ranges. | |
| oauth-auth0-mcp-prototype baadr-ia/oauth-auth0-mcp-prototype This MCP server demonstrates end-to-end Auth0 authentication, validating JWT tokens and mapping org_id to cabinet_id via a whoami tool. | |
| FHIR MCP Server baala-saravanan/fhir-mcp-server Enables AI applications to query and retrieve healthcare data (patients, conditions, observations, medications) from a public FHIR R4 server via MCP tools. |
32,401–32,450 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.