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 |
|---|---|
| ActSeal MCP arults/actseal-mcp Enables agents to issue and publicly verify Ed25519-signed receipts for their actions via the ActSeal API, supporting action input/output hashes plus optional policy and idempotency metadata. | |
| Contoso Insurance MCP Server arulvelk/insurance-mcp-api Enables voice and AI agents to service insurance policies and claims through natural language, including customer lookup and identity verification, coverage checks, billing summaries, and claim filing, status, notes, and callback requests. | |
| procurement-codes arulvelk/procurement-code-agent Enables MCP clients to classify free-text purchase descriptions into United States federal procurement codes and submit authorized, idempotent reviews through typed tool contracts. | |
| Docker MCP Server arumallarevanthreddy/custom-docker-mcp-server Provides Docker management tools for Claude Code, enabling container, image, network, and volume operations. | |
| AgentRelay arumwu/agentrelay A local coordination layer that enables multiple AI coding agents to share context, task leases, file ownership, and decisions via MCP tools, preventing repeated work and allowing seamless handoffs. | |
| Local Workspace MCP arumwu/local-workspace-mcp Enables ChatGPT Desktop to read, search, edit and move files on your own computer, produce Word, Excel, PowerPoint, PDF and chart outputs, launch and manage terminal programs and processes, and run work on other machines you own by name ove | |
| MCP Server for Gemini CLI arun-esh/mcp-server Extends Gemini CLI agent with tools for YouTube transcript retrieval and web search formatting into structured notes. | |
| oradb-explorer-mcp arun-siv/oradb-explorer-mcp Enables read-only exploration of Oracle databases through natural language, providing schema inspection and safe bounded SQL query execution. | |
| Greeting MCP Server arunachalam-b/toy-dns-mcp A simple MCP server built with Next.js that provides a greet_user tool to return friendly greetings, either general or personalized. | |
| linewatch-mcp arunanksharan/linewatch Enables agents to run internet speed and latency tests, and retrieve historical network quality summaries from a local JSONL store, all via simple MCP tools. | |
| cairn arunash/cairn A local-first MCP server that connects Claude Code to your Robinhood account, enabling read-only portfolio insights, tax analysis, and natural language queries, with optional human-in-the-loop trading actions. | |
| jev-mcp arunav25/jev-mcp Enables MCP clients to call TypeSafe's JEV classifier and receive structured, typed judgments with probabilities for binary, choice, and scoring questions. | |
| Agent Context MCP Server arunavo-projectidea/agent-context-mcp-server Tracks working context and code structure in a portable local SQLite database, enabling seamless context and task continuity across different AI coding tools. | |
| nexla-mcp-doc-qa arundhaticat/nex-mcp An MCP server that exposes grounded, source-attributed question-answering over a collection of PDF documents. | |
| BIG-IP MCP Server arunhotra/mcp-bigip Enables management of F5 BIG-IP load balancers through secure authentication and configuration queries. Supports multiple devices with token caching, allowing users to list virtual servers and device configurations through natural language. | |
| Finance MCP Server arunkonapala/finance-mcp-server Exposes personal-finance tools like accounts, transactions, spending analysis, budgets, bills, reminders, portfolio, and goals via MCP, enabling any MCP client to query financial data. | |
| Microsoft Entra MCP Server arunksingh16/azure-entra-mcp A FastMCP server that provides AI assistants with access to Microsoft Entra (Azure AD) directory services. It enables LLMs to search for users, groups, and check memberships using the Microsoft Graph API. | |
| mem0-agent-memory arunkumars-mf/mem0-agent-memory An MCP server that provides persistent memory capabilities for AI agents using Mem0, enabling storage, search, and management of contextual information across conversations with support for multiple backends and LLM providers. | |
| z/OS FTP MCP Server arunkumars-mf/zos-ftp-mcp Enables interaction with z/OS mainframe systems via FTP, including dataset listing/download/upload, JCL job submission and monitoring, with advanced text processing and pagination support. | |
| Moodle MCP Server arunl/moodle-mcp-server Enables AI assistants to interact with Moodle LMS via browser automation, using a server and browser extension to keep credentials local and route commands securely. | |
| Shopify MCP Server arunlakshmikabilan1982/mcp-server Enables management of Shopify orders through the Admin REST API, allowing users to create new orders and retrieve order status details. It supports both local and remote access via SSE and STDIO transports for integration with MCP clients l | |
| Weather MCP Server arunm8489/mcp Provides real-time weather alerts from the National Weather Service API via the Model Context Protocol. It allows LLMs to fetch active alerts for specific US states using both STDIO and SSE transport protocols. | |
| kg-memory-mcp arunmenon/kg-memory-mcp An in-memory knowledge graph MCP server that gives coding agents structural and semantic recall over codebases by indexing Python source, ADR documents, and project configuration, exposing 7 tools for search, traversal, context retrieval, a | |
| SDK MCP Server arunmenon/sdk-mcp-server A configurable MCP server providing searchable access to AI/ML SDK source code and documentation, supporting frameworks like OpenAI Agents and Google ADK. It enables AI assistants to browse files, extract class definitions, and compare impl | |
| Google Maps MCP Server for Cloud Run arunrajece/google-maps-mcp-cloudrun Provides Google Maps functionality through Cloud Run, enabling route calculation, traffic analysis, route comparison, and trip cost estimation with rate-limited public access. | |
| Google Maps MCP Server arunrajece/google-maps-mcp-server Integrates Google Maps routing and traffic capabilities with Claude AI for advanced route planning, real-time traffic analysis, route comparison, and trip cost estimation including fuel and tolls. | |
| AWS Sage arunsanna/aws-sage-mcp A unified MCP server for AWS that enables natural language infrastructure management, cross-service resource discovery, and dependency mapping. It features 30 intelligent tools for cost optimization, incident investigation, and multi-accoun | |
| gemini-diagram-mcp arunsanna/gemini-diagram-mcp MCP server for generating diagrams, charts, and visualizations using Gemini image generation on Vertex AI. Supports auto-detection of diagram types, multiple style modes, and iterative refinement. | |
| reins MCP Server aruntemme/reins Provides tools for AI coding agents to read and write shared team context, including status, pending items, and handoffs. Enables agents to query current project status and claim pending work. | |
| code-intel-mcp arunveersingh/code-intel-mcp MCP server that gives AI agents deep code understanding across multiple git repositories, combining git lifecycle management, Zoekt-based trigram code search, and cross-repo dependency analysis. | |
| mcp-calculator arunyaiitm/mcp-calculator Enables users to perform mathematical calculations through natural language by integrating an AI model with calculator tools via the Model Context Protocol. | |
| servicenow arunz3/mcp-server-servicenow Connects Claude Desktop directly to a ServiceNow instance for incident management, service catalog, workflow tools, and AI-powered smart incidents and KB generation using Gemini. | |
| taru-mcp arupa-inc/taru-mcp Connects AI assistants like Claude Code and Codex to a team's shared knowledge graph for searching, storing, and managing documents. | |
| douyin-ide-control arusheng/douyin-ide-control Enables MCP hosts to safely control Douyin developer tools for tasks such as opening projects, previewing, building, capturing screenshots, reading console errors, uploading, and auditing mini programs and mini games. | |
| brd-enhancer-mcp arushsingh17/mcp Enhances developer tasks by retrieving relevant context from project documentation via a backend API. It enables users to generate enriched task descriptions and prompts by automatically integrating specific technical details from their pro | |
| maxion-gateway aruuhii2yo/maxion-gateway Enterprise MCP gateway providing unified tools for hardware telemetry/performance benchmarking, zero-trust security auditing, AES-256-GCM encrypted storage, HMAC payload verification, and Amazon Bedrock media generation. | |
| chesscom-mcp arvahedi/chesscom-mcp A stateless, read-only MCP gateway for the public Chess.com API, enabling agents to fetch player profiles, stats, games, and club data without storing credentials. | |
| Doctolib MCP arvernesmotion/doctolib-mcp Enables querying Doctolib's public data to find practitioners, retrieve all available appointment slots in a geographic area, access practice details, and receive alerts when new slots open. | |
| Nabu arvicco/nabu Self-hosted read-only MCP server over a local library of ancient-text corpora — 2.47M documents and 118M passages from 258 sources (cuneiform, Classical, biblical, medieval and more), with the license class tracked on every passage. 14 rese | |
| Chess MCP arvid-berndtsson/chess-mcp A powerful chess engine and game server built with the Model Context Protocol (MCP). Play chess against AI, analyze positions, and integrate chess functionality into your AI applications. | |
| YouTube Transcript MCP Server arvind29/youtube-transcript-mcp-server Retrieves YouTube video title, duration, and transcript. Supports language preferences for Hindi, Marathi, and English. | |
| veriloop arvindcr4/veriloop Exposes a verified tool registry (calculator, sandboxed file read, web fetch) over MCP stdio, enabling any MCP-capable client to reuse the same tools from the inspectable ReAct loop. | |
| DuckDuckGo Search MCP Server arvindg4u/ddg-search-mcp Brings DuckDuckGo search (web, news, images, videos) to any MCP-compatible AI client without requiring an API key. | |
| grp-docx-mcp arvindh95censof/docx-mcp-custom Enables AI agents to create, read, and edit Word documents with tracked changes, comments, and template manipulation, including bulk text replacement and paragraph-level operations. | |
| grp-kb arvindh95censof/grp-kb Semantic search MCP server for an Acumatica knowledge base, indexing markdown notes with multilingual embeddings to enable search across English and Bahasa Malaysia content. | |
| kb-mcp arvindh95censof/kb-mcp Semantic search MCP server for Acumatica KB Obsidian vault, enabling querying and reading knowledge base files via natural language. | |
| mcp-twikit arvinmoj/mcp-twikit MCP server for interacting with Twitter, enabling search tweets and fetching timeline via natural language. | |
| TwitGhost arvinmoj/twitghost-mcp Enables interacting with Twitter/X through natural language, including searching tweets, posting, sending DMs, and managing timelines via any MCP client. | |
| Screenbook arvoreeducacao/screenbook Enables an AI agent to read and write a product's design screens on a shared, versioned canvas: creating and editing HTML screens and shared parts, taking screenshots, linking flows, posting comments and annotations, and opening or approvin | |
| container-mcp arxndev/linux-mcp-server- MCP server for Apple container to manage, build, inspect, and diagnose Linux containers on macOS directly from AI agents. |
30,851–30,900 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.