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 |
|---|---|
| memex chalermchaimulder529/memex Enables AI coding agents to persistently store, recall, link, and sync atomic markdown knowledge cards across sessions and supported clients without a vector database. | |
| swissdevjobs chalermchait448/swissdevjobs-cli Enables AI agents to search, filter by salary, and apply to salary-transparent tech jobs across nine job boards in eight countries, returning JSON-first results and remembering which postings have already been applied to so duplicates are s | |
| MCP-Discord chalermchaiweiss/mcp-discord Enables AI assistants to interact with the Discord platform through a bot token, covering server and member inspection, channel and category management, message reading/searching/editing, reactions, forum posts and tags, role assignment, an | |
| chalkieboard-icloud-mcp chalkieboard/chalkieboard-icloud-mcp Local MCP server enabling management of Chalkieboard lesson data in iCloud Drive, with tools to list subjects and lessons, read files, add materials, and create subjects—all offline. | |
| Aframe MCP Connector chalkworld/aframe-mcp-connector Enables Claude to create and manage transactions in Aframe via the Aframe Open API, supporting transaction creation and note addition. | |
| MCP-Pay challalokesh08/mcp-pay Enables AI agents to discover and pay for MCP tools on a sub-cent, pay-per-call basis using x402 and Algorand USDC settlements. | |
| ChillClock MCP Server challaramyasree777-maker/chillclock Enables clients to estimate food-cooling deadlines from temperature readings and retrieve deterministic, rule-based cooling guidance through MCP tools. | |
| KakaoCloud OpenAPI MCP Server chals-go/kakaocloud-openapi-mcp Enables AI assistants to discover and invoke KakaoCloud OpenAPI endpoints for managing cloud resources like VMs, VPCs, load balancers, and databases. | |
| mcp-infra chalshik/mcp-infra Enables AI assistants to identify processes listening on specific network ports by returning process names and PIDs. It provides infrastructure introspection capabilities through the Linux ss command to help users monitor and debug local se | |
| CatMCP chambtai-sys/catmcp A lightweight MCP server that serves a curated collection of cat jokes to LLM clients, supporting tools for random jokes by category, search, and resource access. | |
| Dev Guru chameleonbr/dev-guru An AI-powered code consultation server that routes programming queries to specific AI models based on requested expertise levels. It enables users to receive structured feedback on debugging, architectural decisions, and code reviews from G | |
| Skills MCP Server chameleonbr/skills_mcp_server Centralized, sandboxed MCP server to manage, execute, and expose advanced Agent Skills to any MCP-capable framework or low-code platform. | |
| User Intent MCP chameleonscool/feedback-mcp A multi-modal user intent collection MCP server that allows AI agents to ask users questions and receive text/image replies. | |
| Athlete MCP chamilqs/athlete-mcp An open-source, Strava-first remote MCP server that enables users to authorize with Strava and ask AI about their training data. | |
| ChampCity GPT MCP Launcher champcitychris/champcity_gpt_mcp ChatGPT-compatible MCP server and Electron launcher for controlled local project-file access, providing read-only and approval-gated write tools over STDIO or HTTP with optional OAuth and HTTPS tunneling. | |
| touchgrass champdev-me/touchgrass.win Enables AI agents to participate in a persistent survival world, allowing them to join a game, observe the environment, and move to survive and fight while humans watch. | |
| rc-mcp champi-ai/rc-mcp Enables controlling your own Linux desktop machines from any MCP-capable LLM client, with opt-in agent capabilities for shell, filesystem, processes, screenshots, system info, and input injection. | |
| Image Analysis MCP Server champierre/image-mcp-server A server that accepts image URLs and analyzes their content using GPT-4-turbo, enabling Claude AI assistants to understand and describe images through natural language. | |
| DevAssist MCP Server champion-2006/devassist-mcp-server A production-ready MCP server for GitHub and competitive programming (Codeforces) that enables AI assistants to fetch user profiles, repository stats, contest history, and personalized problem recommendations. | |
| shopfloor-mcp champion-buzz/shopfloor-mcp Enables AI assistants to read and safely schedule manufacturing work orders, including checking resource availability, finding free slots, booking without overlaps, and reporting utilization or late risks. | |
| modforge champmk/modforge Provides deterministic, audit-chain-backed Minecraft symbol migration and version-truth queries over MCP for AI assistants, enabling grounded rename resolution and API diffs without hallucination. | |
| ArXivLens MCP chan4kum/arxivlens-mcp Enables real-time arXiv paper discovery, structured research briefs, and automated mapping to GitHub code implementations through MCP tools, resources, and prompts. | |
| ebbingflow-mcp chanada440824/ebbingflow-mcp Enables MCP clients like OpenCode or Claude to use EbbingFlow long-term memory across sessions through stdio tools for writing, retrieving, and chatting with remembered context. | |
| nessus_mcp_server chanakayaa/nessus_mcp_server Enables AI assistants to manage Nessus vulnerability scans, analyze results, and generate reports through the MCP protocol. | |
| WeatherForcast-MCP-using-playwright chanar-git/weatherforcast-mcp-using-playwright Enables fetching weather forecasts for the USA via NWS API and for Israel via browser automation using Playwright. | |
| charles-mcp chancecreate/charles-mcp Native, read-only MCP bridge exposing live Charles Proxy traffic to MCP clients like Claude Code, Codex and Cursor | |
| godot-mcp chanceflow/godot-mcp Enables AI assistants to interact with the Godot game engine, including launching the editor, running projects, capturing debug output, and managing scenes. | |
| creator-analysis-mcp chanchilun2004/creator-analysis-mcp Remote MCP server that provides Creator Recommendation API tools (creator_research, creator_tagged_media, etc.) with secure authentication, rate limiting, and OAuth support for Claude clients. | |
| Polymarket US MCP server chand1012/polymarket-us-mcp Enables MCP clients to explore markets, events, prices, order books, sports, tags, accounts, portfolios, orders, combos, RFQs, and incentives, and to preview, place, modify, cancel, and batch-manage live trades through Polymarket's US retai | |
| Azure Impact Reporting MCP Server chand45/mcp-server-azure-impact-reporting Enables large language models to automatically report customer-facing issues with Azure resources by parsing natural language requests and submitting impact reports through the Azure Management API. | |
| DoctorVerify chandanbcsm012/verify_indian_doctor_mcp Enables verification of Indian doctors by querying the National Medical Commission's Indian Medical Register for registration, profiles, and blacklist status, with fallback guidance for manual lookup. | |
| mcp-tool-gateway chandancoding/mcp-tool-gateway A secure tool-execution plane for agentic AI that enforces JWT authentication, rate limiting, prompt-injection inspection, and audit logging, while ingesting downstream OpenAPI endpoints as MCP tools. | |
| MCP Server Basic Example chandanduttaind-sys/mcp A foundational Model Context Protocol server demonstrating core functionality through basic arithmetic tools and personalized greeting resources. It serves as a template for developers learning to build and deploy MCP-enabled AI application | |
| Review Analysis MCP Server chandanrocky/mcp A local, privacy-friendly pipeline for analyzing customer reviews using Ollama for sentiment analysis and issue clustering. | |
| Kite MCP Server chandantherefore/kite-mcp Enables trading and portfolio management on Zerodha Kite Connect through natural language. Supports placing orders, viewing positions/holdings, accessing real-time market data, and managing GTT orders. | |
| jmeter-mcp-server chandanvars/jmeter-mcp-server A powerful MCP server for automated JMeter test generation and execution with Docker integration and comprehensive performance analysis. | |
| agy-bridge chandara-code/a2a-panel Enables Claude Code to delegate coding work to a team of Google Antigravity specialists, dispatching tasks to particular roles, listing available agents, checking or cancelling task status, and validating delivered work against acceptance c | |
| Gmail SMTP MCP Server chandhinii1510-coder/mcp-multiuser Enables sending emails via Gmail using SMTP and app passwords without OAuth. It provides a custom authorization flow and encrypted credential storage for multi-user access. | |
| archival-imagery-mcp chandhoke/archival-imagery-mcp An MCP server for browsing and downloading open-licensed imagery from major museum and archive APIs including Wellcome, Met, Library of Congress, Smithsonian, and Europeana. | |
| AIChat MCP Server chandler-rj/aichat-mcp 将AIChat服务封装为MCP服务器，供Claude、Cursor等AI客户端调用，支持创建AI角色、管理会话、自动对话和搜索历史论战。 | |
| University Course Catalog MCP Server chandrabhanu18/model-context-protocol-mcp-server-for-a-university-course-catalog-mandatory Provides intelligent access to a university course catalog with full-text search, prerequisite tracking, instructor lookups, and course comparison prompts. | |
| RAG Information Retriever chandrahaasj/rag_mcp An MCP server that implements Retrieval-Augmented Generation to efficiently retrieve and process important information from various sources, providing accurate and contextually relevant responses. | |
| PsMCP - MCP Server for Photoshop chandrahas455/psmcp-mcp-server-for-photoshop A server that allows AI tools like Claude and Cursor to automate and control Photoshop through natural language commands, enabling tasks like editing PSDs, toggling layers, and generating marketing creatives. | |
| Marketing Events MCP Server chandrahasm/marketing-events-extension This MCP Server enables users to interact with HubSpot's marketing events API, allowing management of marketing event data through natural language commands. | |
| mcpdockery chandrakant1988/https-github.com-theo-gkisis-mcpdockery MCP server for natural-language control of local Docker, covering containers, images, volumes, networks, and Compose stacks, plus security scanning and diagnostics. | |
| csw-mcp chandrapati/csw-mcp A read-only MCP server that lets MCP clients such as Cursor and Claude Desktop query a Cisco Secure Workload (Tetration) cluster in plain English. It exposes tools for scopes, sensors, flows, workspaces, policies, and CVE/package vulnerabil | |
| mailpouch chandshy/mailpouch An MCP server that gives AI agents permission-gated, audit-logged access to private email providers (Proton Mail via Bridge and plain IMAP), running locally with OAuth-based authentication and human-controlled escalation for destructive ope | |
| Camoufox Playwright MCP chandu-cpz/camoufox-playwright-mcp An MCP server that provides a stealth-enhanced Playwright browser automation engine with anti-detection features, enabling AI agents to navigate websites, interact with elements, and bypass anti-bot systems. | |
| system-mcp chandukasireddy/system_mcp Exposes system telemetry tools to retrieve CPU, memory, disk, battery, network, process, and GPU metrics from a local machine. | |
| easytiny-mcp chaneasy/easytiny-mcp Enables visually lossless batch compression of JPEG, PNG, WebP, AVIF, GIF, and SVG files, writing results to a temporary preview directory with size, encoder, and quality-score details. Originals are only replaced atomically after the user |
37,851–37,900 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.