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 |
|---|---|
| @kanbio/mcp aritzbl/kanbio-mcp Enables AI clients to read, search, comment on, create, update, assign, and move tickets and sprints in a mini-Jira platform via a personal access token. It runs locally over stdio and respects token permissions and project scope. | |
| NSAF MCP Server ariunbolor/nsaf-mcp-server A Model Context Protocol server that allows AI assistants to interact with the Neuro-Symbolic Autonomy Framework, enabling capabilities like running NSAF evolution with customizable parameters and comparing different agent architectures. | |
| multi-cloud-llm-platform ariz-ahmad/multi-cloud-llm Exposes multiple LLM providers (AWS Bedrock, OpenAI, Google Gemini, local Ollama) as MCP tools with automatic routing by task type and Prometheus metrics, enabling any MCP-compatible client to generate text, route prompts, and list provider | |
| weather-mcp-server ariz-ahmad/weather-mcp-server A no-API-key-required MCP server that wraps Open-Meteo APIs to provide geocoding and weather forecast data, enabling city lookups and multi-day forecasts through tools, resources, and prompts. | |
| vidlizer arizawan/vidlizer vidlizer pulls frames out of any video, image, or PDF using ffmpeg, sends them to a vision LLM, and returns a flow array — one entry per scene. Each entry tells you what happened, who was on screen, what text was visible, and what changed. | |
| @arizeai/phoenix-mcp arize-ai/phoenix Phoenix MCP Server is an implementation of the Model Context Protocol for the Arize Phoenix platform. It provides a unified interface to Phoenix's capabilites.
You can use Phoenix MCP Server for:
Prompts Management: Create, list, update, | |
| deepseek-mcp arizen-dev/deepseek-mcp Enables using DeepSeek models as a small, cheap supervised worker from any MCP-compatible client, providing fast flash and deep reasoning tools for bounded tasks. | |
| discord-mcp arizona-dev/discord-mcp An MCP server for managing Discord servers with 73 tools including channels, roles, messages, moderation, voice, events, forums, emojis, invites, and permissions. | |
| teambrrr arizqi/teambrrr Recruits specialized AI agents into your existing chat sessions, letting you audition, hire, and @mention named teammates with persistent personas and memory across Claude Code, Codex, hermes-agent, and Slack. | |
| Data Commons MCP Server arj999/data-commons-mcp-server Enables AI agents to query and retrieve public statistical data from Data Commons through search and observation tools. Provides access to demographic, economic, and other statistical indicators for analysis and research. | |
| Repository Intelligence Engine arjade25/repo-intelligence-engine Enables querying a TypeScript repository's structure (symbols, imports/exports, references) through direct queries, avoiding repetitive grep operations. | |
| Polymarket MCP Server arjein/polymarket-mcp Enables LLM agents to interact with Polymarket prediction markets, including market discovery, real-time pricing, analytics, account management, and trading with built-in safety guards. | |
| OpenPapers arjhinety/openpapers Enables provenance-first scholarly retrieval, paper ingestion, and reproducible research workflows by searching academic and developer sources, extracting source-located facts and claims, and preserving evidence and provider uncertainty for | |
| sark arjia-labs/sark Enables Slack-driven coding agents in isolated cloud sandboxes per thread, with thread-scoped MCP tokens and fail-closed allowlists. | |
| Expense Tracker MCP arjit005/mcp_server Enables AI assistants to manage local expense and income records, including adding, listing, editing, deleting expenses, tracking credits, categorizing spending, and calculating balances via SQLite-backed MCP tools. | |
| universal-email-mcp arjoma/universal-email-mcp Enables AI assistants to search, retrieve, and send email across multiple ordinary IMAP, POP3, and SMTP mailboxes, with per-account permissions and safe sending checks. | |
| BlazeSQL MCP Server arjshiv/blaze-sql-mcp-server A Model Context Protocol server that enables AI clients to interact with BlazeSQL's Natural Language Query API, allowing natural language queries against SQL databases. | |
| Local Utilities MCP Server arjshiv/localutils-mcp-server Provides quick access to local system utilities including time/date, hostname, public IP, directory listings, Node.js version, and port usage through an MCP server interface compatible with Cursor and other MCP clients. | |
| GitHub MCP Server arjun-palani-sada/mcp-auth-poc Enables authenticated GitHub operations and exposes MCP tools for agent interaction. | |
| AgenTest arjun-vegeta/agentest AI-driven mobile app testing via MCP, enabling AI coding agents to test Android apps without test frameworks or testIDs. | |
| belong-mcp arjun1194/belong-mcp Exposes Belong Resident Application APIs as MCP tools for AI assistants to manage visitors, vehicles, maintenance, amenity bookings, and finances. | |
| IMAP MCP Server arjun2551/imap-mcp-server Enables AI assistants to search, read, send, reply to, forward, organize, and bulk-delete email across multiple mailboxes via IMAP and SMTP, with connection pooling and AES-256-encrypted credential storage. Supports 15+ pre-configured provi | |
| Cinema4D MCP Server arjun30743/cinema4d-mcp Connects Claude Desktop to a Cinema 4D socket plugin so users can build and edit 3D scenes through natural-language prompts. Enables creating and modifying primitives, cameras, lights, materials, MoGraph cloners, fields and dynamics, plus r | |
| zotero-mcp arjun3391/zotero-mcp Enables AI assistants to search a Zotero library, retrieve item metadata, and access full text from PDFs via the local or Web API. | |
| Kingdee MCP Server arjun99100/kingdeemcp Enables AI assistants such as Claude, Cursor, and Windsurf to query and operate Kingdee Cloud Star ERP entirely through natural language, exposing 97 tools spanning procurement, sales, inventory, production, costing, fixed assets, workflow | |
| Storyblok MCP Server arjuncodess/storyblok-mcp Connects AI tools to Storyblok CMS, allowing users to manage content through natural language commands for tasks like story management, asset handling, and AI-powered content operations. | |
| ibkr-mcp-server arjundivecha/ibkr-mcp-server MCP server for Interactive Brokers API integration, enabling account management, trading, market data, and short selling analysis through Claude. | |
| hermes-cowork-bridge arjungoel10/hermes-cowork-bridge Bridges Claude Cowork/Desktop to a local Hermes Agent, exposing hermes_delegate, hermes_check_run, and hermes_health tools for task delegation, status polling, and health checks. | |
| Read-Only vSphere MCP Server arjungowdal4601/vcenter_mcp Connects MCP-compatible coding agents to VMware vCenter to query information about virtual machines, hosts, clusters, datastores, datacenters, and networks. | |
| Basic MCP Server arjunkmrm/agentmail-smithery-mcp A minimal Model Context Protocol server template built with Smithery SDK that demonstrates basic tools, resources, and prompts functionality for getting started with MCP development. | |
| Attio MCP Server arjunkmrm/attio-mcp-server Enables AI assistants to interact with Attio CRM through natural language, providing complete access to companies, people, deals, tasks, lists, notes, and records with advanced search, batch operations, and relationship management. | |
| Hello Widget Example arjunkmrm/cafe-explorer A minimal ChatGPT app demonstrating interactive greeting widgets with confetti animations and theme support, built as an MCP server example using Smithery CLI. | |
| GitHub Tools MCP Server arjunkmrm/demo-github-mcp Model Context Protocol server that enables interaction with GitHub repositories, issues, pull requests, and search functionality through natural language. | |
| mcp-minecraft arjunkmrm/mcp-minecraft Allows AI models to observe and interact with the Minecraft world through a bot. | |
| Singapore LTA MCP Server arjunkmrm/mcp-sg-lta Facilitates real-time access to Singapore's Land Transport Authority (LTA) transportation data, offering insights into bus arrivals, train services, traffic conditions, and more through integration with the LTA DataMall API. | |
| Mem0 MCP Server arjunkmrm/mem0-mcp Enables AI applications to add, search, update, and delete long-term memories using the Mem0 Memory API, allowing agents to persistently remember user preferences, conversation history, and contextual information across sessions. | |
| Perplexity Deep Research MCP arjunkmrm/perplexity-deep-research A server that allows AI assistants to perform web searches using Perplexity's sonar-deep-research model with citation support. | |
| Basic MCP Server arjunkmrm/pnpm-test A minimal Model Context Protocol server template demonstrating tools, resources, and prompts implementation. Built with Smithery SDK for quick MCP server development and deployment. | |
| Hello Widget Example arjunkmrm/tic-tac-toe A minimal ChatGPT app demonstrating interactive greeting widgets with confetti animations and theme support, built as a template for creating MCP servers with custom UI components. | |
| Weather MCP Server arjunkmrm/weather-test Retrieves current weather information for any location using the OpenWeatherMap API with configurable temperature units (Celsius or Fahrenheit). | |
| multi-llm-mcp arjunkr303/multi-llm-mcp Enables IDE agents to delegate coding tasks to any LLM provider — cloud APIs like NVIDIA NIM, OpenRouter, Groq, DeepSeek or local Ollama models — through a unified MCP interface. | |
| Math MCP Server arjunkrish7356/mathagent Enables mathematical calculations through basic arithmetic operations including addition, subtraction, multiplication, division, exponentiation, and logarithms. Provides a simple interface for AI agents to perform mathematical computations. | |
| Expense Tracker MCP Server arjunnavadiya8/expense-tracker-mcp Enables AI assistants to track, query, summarize, and delete personal expenses stored in a local SQLite database via natural language. | |
| Online Boutique AI Assistant MCP Server arjunprabhulal/ai-boutique-assit-mcp MCP server for Online Boutique AI Assistant that exposes 18 e-commerce microservice functions via the Model Context Protocol, enabling any MCP client to manage products, carts, checkout, payments, and shipping. | |
| mcp-youtube-search arjunprabhulal/mcp-youtube-search Enables searching YouTube videos via SerpAPI, returning video details such as title, link, channel, views, duration, and publish date. | |
| Workday Studio MCP arjunsena-eze/workday-studio-mcp A local MCP server that gives Claude direct access to a Workday Studio workspace, enabling reading, writing, planning, and validating integration assemblies without copy-pasting XML. | |
| FinanceOS MCP arjunsena-git/financeos-mcp Real-time financial superpowers for Claude. Live crypto prices, US and Indian NSE stock quotes, full portfolio P\&L, Bittensor/TAO network stats, Fear & Greed index with 7-day history, top movers and global market overview. 8 tools. Zero AP | |
| IB MCP Server arjunsmith84244/ib_mcp Enables MCP clients to interact with Interactive Brokers' official Web API for brokerage account management, reporting, and related IBKR operations, with authentication and session handling through the Client Portal Gateway. | |
| MCP Hub arjunswalia/dynamic-mcp-hub Dynamically converts uploaded OpenAPI specs into MCP servers, allowing multi-spec exposure and control plane management via REST API. | |
| Google Calendar Meeting Setup arjuntheprogrammer/google_calendar_meeting_setup Enables creating Google Calendar meeting invites with automated authentication via OAuth. Supports scheduling meetings with customizable title, duration, notes, and attendees through a simple command-line or MCP tool interface. |
30,401–30,450 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.