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 |
|---|---|
| Open Design Desktop ai-for-anyone/loop-now-plugin-open-design Enables agents to commission and refine web pages, product prototypes, landing pages, decks, images, and motion through the desktop app, and to read design files, copy artifacts, and access design systems. | |
| RedAlert MCP Server ai-for-anyone/redalert An intelligent game assistant for Red Alert, based on LangGraph and MCP, providing asynchronous architecture and multimodal AI control for game strategy, production, and combat management. | |
| MCP Kandinsky ai-forever/mcp_kandinsky MCP server that generates images from text prompts using the Kandinsky AI via official API. | |
| Hetzner MCP Connection ai-foundry-col/hetzner-mcp-connection Enables AI agents like Mistral Work to manage Hetzner Cloud VPS services in natural Spanish, including creating, modifying, and deleting servers, networks, firewalls, and storage, as well as automating complex tasks. | |
| Poco MCP Service ai-fsxgt/poco-service-mcp Independent MCP service module for Poco, providing analytics and management tools such as daily usage analysis and service introspection. | |
| Universal Google Ads Manager ai-godfather/google-mcp-universal Enables users to manage any Google Ads account through Claude Code or Claude Desktop, automating campaign creation, ad copy generation, asset and image handling, bid optimization, and performance reporting. It covers Search, Shopping, Perfo | |
| Straight Connect ai-guru/mmxxvi_straight_connect An MCP server for communication service connectors that currently provides multi-account Telegram integration with granular tool access and security controls. It allows AI models to manage messages, chats, and media across various accounts | |
| Finance Agent MCP Server ai-hub-admin/finance-agent-mcp-server Provides real-time stock price data from global markets, including the US, China, India, and Europe, without requiring API keys. It enables AI systems to retrieve financial information from trusted public sources such as NASDAQ, HKEX, and M | |
| Omni File Converter MCP ai-hub-admin/omni-file-converter-mcp Converts various document formats to desired output formats, currently supporting PDF to image conversion. No access keys required for basic file format conversion operations. | |
| GitHub MCP Server ai-info-x/github-mcp Enables MCP-compatible AI clients to manage GitHub repositories and issues and trigger repository dispatch events via tools and a REST API. | |
| GitHub MCP Server ai-info-x/github-mcp-server Enables triggering GitHub repository dispatch events, creating issues, and retrieving repository information. | |
| code-execution-mcp ai-integr8tor/agent0ai-code-execution-mcp An MCP server that enables AI agents to execute terminal commands and Python code on the host system, leveraging Agent Zero's battle-tested implementation with session management and smart output handling. | |
| Browserbase MCP Server ai-integr8tor/mcp-server-browserbase Enables LLMs to perform cloud browser automation tasks including navigation, actions, observation, and data extraction using Browserbase and Stagehand. | |
| Cloudflare MCP Server ai-integr8tor/mcp-server-cloudflare Enables natural language interaction with Cloudflare services including Workers, observability, documentation, and Radar for managing configurations, analytics, and internet insights. | |
| mcp-server-qdrant ai-integr8tor/mcp-server-qdrant An MCP server for storing and retrieving memories using Qdrant vector search, acting as a semantic memory layer. | |
| Tavily MCP Server ai-integr8tor/tavily-mcp Provides web search, extraction, mapping, and crawling tools through Tavily API, enabling real-time web data retrieval. | |
| Minion Comms ai-janitor/minion-comms Multi-agent coordination MCP server using RPG raid mechanics for task assignment, context management, and knowledge persistence. | |
| mcp-server ai-maker-space/mcp-session-code Web search MCP server using Tavily API, enabling natural language queries to search the web. | |
| Weather and Tasks MCP Server ai-makes-sense/ep01 Enables AI to read live weather data and manage a persistent to-do list through MCP tools, demonstrating both read and write capabilities without API keys. | |
| Agent Construct ai-mcp-garage/agent_construct An MCP server implementation that standardizes how AI applications access tools and context, providing a central hub that manages tool discovery, execution, and context management with a simplified configuration system. | |
| JEFit MCP Server ai-mcp-garage/jefit-mcp Enables analysis and retrieval of JEFit workout data through natural language. Provides access to workout dates, detailed exercise information, and batch workout analysis for fitness tracking and progress monitoring. | |
| DateTime MCP Server ai-mcp-garage/mcp-datetime Provides timezone-aware date and time information with configurable time formats and timezone support. Enables users to get current date and time in their preferred timezone and format through simple MCP tools. | |
| Apple Find My MCP Server ai-mcp-garage/mcp-findmy Enables interaction with Apple's Find My network to track devices, check battery status, and manage device information. Provides secure authentication and caching for efficient access to your Apple devices' location and status data. | |
| IntelliDiff MCP Server ai-mcp-garage/mcp-intellidiff Enables intelligent file and folder comparison with advanced text normalization, duplicate detection, and line-level diff analysis. Provides secure workspace-constrained file operations with CRC32-based exact matching and smart text compari | |
| MyFitnessPal MCP Server ai-mcp-garage/mcp-myfitnesspal Enables retrieval and analysis of MyFitnessPal nutrition data including daily summaries, meal breakdowns, exercise tracking, and macro/micronutrient analysis. Uses browser cookie authentication to access your personal MyFitnessPal account d | |
| MCP Screenshot Server ai-mcp-garage/mcp-screenshot Enables LLMs to capture and analyze screenshots of your screen, windows, or regions with smart detection capabilities. Features natural language queries, automatic window targeting, and text enhancement for UI debugging and visual inspectio | |
| System Information MCP Server ai-mcp-garage/mcp-sysinfo Provides comprehensive system diagnostics and hardware analysis through 10 specialized tools for troubleshooting and environment monitoring. Offers targeted information gathering for CPU, memory, network, storage, processes, and security an | |
| User Info MCP Server ai-mcp-garage/mcp-userinfo Enables AI assistants to access and manage user profile information including name, company, location, role, interests, and skills. Supports both static configuration files and dynamic session-based storage with automatic date context. | |
| Hello World MCP Server ai-mcpx/mcp-hello A simple MCP server that generates multi-language greetings and provides server information using the FastMCP framework. | |
| arena-bridge ai-modelsapi/arena-bridge Enables MCP clients like arena.ai Agent Mode or Claude Desktop to securely control real machines (VPS, Mac/Linux, Android) through a single URL and token, with a password gate protecting unauthorized directories. | |
| AI Naming Standard MCP Server ai-naming-standard/mcp Enables automatic generation and validation of standardized file names using AI-driven conventions for microservices architecture. Supports multi-language naming with structured components like microservice, layer, domain, and action identi | |
| Oura MCP ai-niki/oura-mcp Provides LLMs with access to Oura Ring health data including sleep metrics, activity tracking, heart rate, readiness scores, and other wellness insights through the Oura API v2. | |
| Fast Mermaid Validator MCP ai-of-mine/fast-mermaid-validator-mcp Validates Mermaid diagrams with comprehensive grammar parsing supporting 28+ diagram types. Processes markdown files, ZIP archives, and direct input with detailed error reporting and enterprise-grade performance capabilities. | |
| Lore ai-pipes/lore Enables AI agents to search and ask questions across versioned service documentation, retrieve documents and diffs, and find related docs with cited answers over Streamable HTTP, SSE, or stdio. | |
| mcp-registry ai-pipes/mcp-registry Provides a single MCP endpoint that lets AI agents discover and call tools across many upstream MCP servers using per-user credentials and group-based access. | |
| Skills Registry ai-pipes/skills-registry Enables Claude Code and other agents to search versioned skills, fetch skill contents, and browse folders through MCP, backed by hybrid full-text and semantic search. | |
| store-ops-mcp ai-product-allen-yu/duvo-store-ops-mcp Enables store operations including inventory and sales queries and automated replenishment ordering through natural language. | |
| Korral StoreLink MCP Server ai-product-allen-yu/korral-storelink-mcp Enables AI agents to interact with Korral's StoreLink system to check store inventory and sales data, and create replenishment orders to manage stock-outs. | |
| ViralSpin MCP ai-product-allen-yu/viralspin-mcp Enables AI agents to edit video assemblies from A-roll and B-roll, add captions, and publish to social media platforms. | |
| Superstore MCP Server ai-protocols/superstore-mcp Enables interaction with Real Canadian Superstore to extract order history, browse products, and export purchase data. Supports authentication via bearer token and provides comprehensive order management and product discovery capabilities. | |
| Claim Check for Jira ai-q-labs/claim-check-for-jira Enables AI agents and users to verify claims about Jira issues and issue counts against live Jira, retrieve verifiable facts for drafting updates, and re-check previously posted claims. It provides read-only tools and an issue panel so stat | |
| Sealed Case for Alexa+ ai-q-labs/sealed-case-mcp Enables a player to investigate and solve a voice-only murder mystery through an MCP client by searching locations, examining evidence, questioning suspects, reviewing notes, and making a confirmed accusation. The AI assistant never receive | |
| mcp-devcontainers ai-ql/mcp-devcontainers MCP server for generating and configuring development containers from devcontainer.json files, enabling management of devcontainer environments through tools like devcontainer_up, devcontainer_exec, and cleanup. | |
| Scraper.is MCP Server ai-quill/scraperis-mcp Enables extracting data from websites using natural language prompts, allowing users to specify exactly what content they want in plain English and returning structured JSON data. | |
| isthereanydeal-mcp ai-repo-save/isthereanydeal-mcp Enables querying game deals, prices, and managing collections using the IsThereAnyDeal API with 53 specialized tools. | |
| kansallisarkisto-mcp ai-riksarkivet/kansallisarkisto-mcp Enables full-text search and retrieval of Kansallisarkisto's machine-transcribed archival corpora, including medieval charters from Diplomatarium Fennicum, with filters and stemming support. | |
| Riksarkivet MCP Server ai-riksarkivet/ra-mcp Enables users to search and access digital collections from the Swedish National Archives (Riksarkivet) through multiple APIs. Supports searching records by keywords, exploring collections, and downloading historical images and documents. | |
| appstoreconnect-codex-mcp ai-scarlett/appstoreconnect-codex-mcp Enables read-only interaction with App Store Connect via MCP tools, including listing apps, versions, builds, and review submissions, with compliance boundaries and no write operations by default. | |
| AI Shopping Feeds MCP Server ai-shopping-feeds/ai-shopping-feeds-mcp Enables AI agents to import and refresh product feeds, edit products, write rules, run optimization and audits, connect ad channels, set performance labels, and create product ad creatives. | |
| mcp_argo_pipeline ai-skill-mcp/mcp_argo_pipeline MCP server to dispatch Argo WorkflowTemplates according to pipeline configurations, supporting multiple pipelines, authentication, and remote access. |
24,901–24,950 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.