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 |
|---|---|
| remote-mcp-server-authless emaintelligenz-sudo/remote-mcp-server-authless Enables deploying a stateless remote MCP server on Cloudflare Workers without authentication, allowing users to register custom tools and connect remote MCP clients like Cloudflare AI Playground or Claude Desktop via mcp-remote. | |
| DevDocs MCP Server emaland/devdocs-mcp Enables AI assistants like Claude to search and retrieve technical documentation from a local DevDocs instance for hundreds of programming languages and frameworks. | |
| pbi-mcp-remote emamuel03/pbi-mcp-remote Remote and centralized MCP server that enables AI models to interact with Microsoft Fabric (workspaces and items) via the Fabric Core REST API, using delegated OAuth 2.1 authentication with Microsoft Entra ID so each user's permissions and | |
| vault-semantic-mcp eman-hc/vault-semantic-mcp A local semantic search MCP server for Markdown vaults that indexes and retrieves notes using hybrid keyword and embedding search. | |
| Pallas MCP Server emanirfan-creator/figma-pallas-mcp Connects an AI agent to Figma and Panda CSS for two-way design system sync, component creation, and variable binding. | |
| Python Weather MCP Server emanmanco/mcppythonweather Enables AI agents to fetch real-time weather data for any location using the OpenWeatherMap API. Demonstrates how to build a simple MCP server that exposes weather information as a tool for LLMs. | |
| Vivado MCP Server emanuel-clearfield/vivado_mcp_windows Lets LLM clients control a persistent AMD/Xilinx Vivado TCL session on Windows, avoiding repeated startup cost with native process handling. | |
| mcp-server emanuel8almeidas/mcp A starter MCP server built with the official TypeScript SDK, providing example tools for echoing messages and getting current time. | |
| CamoFox MCP emanuele721/camofox-mcp Enables MCP-compatible AI agents to navigate, interact with, and automate web pages through an anti-detection browser toolset, including multi-tab workflows, search, extraction, downloads, and session reuse. | |
| Basecamp MCP Server emanueleh589/basecamp-mcp-server Enables MCP-capable clients to read and manage Basecamp 3 projects, todos, messages, card tables, documents, uploads, comments, events, and search through OAuth-authenticated API calls. | |
| BigQuery MCP server emanuelejaworski70712/mcp-server-bigquery Enables LLMs to inspect database schemas and execute SQL queries against BigQuery, including listing and describing tables. | |
| MCP Memory Keeper emanuelele5502/mcp-memory-keeper Enables AI coding assistants to persistently save, search, checkpoint, and restore project context across sessions, including decisions, progress, and file state. It supports shared channels, git-aware organization, and batch operations for | |
| Vantage Code Mode MCP Server emanuelelecchi/vantage-mcp-server Enables LLM clients to work with Vantage to inspect and modify scene state, open/save files, probe object properties, and run VScript payloads. | |
| Korean DART MCP emanuelet52195/korean-dart-mcp Enables AI assistants to search Korean OpenDART disclosures, analyze financial, equity, and XBRL data, score insider signals and accounting anomalies, run Buffett-style quality checks, and convert HWP/PDF attachments into Markdown. | |
| web3-mcp-server emanueljr/web3-mcp-server Enable to request information from EVM chains | |
| MCP Parse Server emanuelmartin/mcp-parse-server Enables interaction with Parse Server through the Model Context Protocol, providing CRUD operations, schema management, role-based security, and cloud function execution. | |
| Local File Manager emanuelmoraes/my-first-mcp-server Enables AI clients to manage and manipulate text files in a secured local directory through tools like list, read, write, delete, create directory, and move. | |
| eventin-mcp-server emarathossain/eventin-mcp-server MCP server for interacting with the Eventin booking system, enabling natural language management of bookings, events, and venues. | |
| setlistify emarkou/setlistify An MCP server that fetches real setlists from setlist.fm and creates Spotify playlists from them, supporting fuzzy matching and various modes like latest show or best-of from recent shows. | |
| apple-docs emasoft/emasoft-apple-documentation-plugin Enables Claude Code users to search and read Apple Developer Documentation — frameworks, APIs, SwiftUI/UIKit symbols, Human Interface Guidelines, design resources, sample code, and WWDC session transcripts — directly in their session. It al | |
| mem0-custom-mcp emasoudy/mem0-custom-mcp A custom MCP server that connects to self-hosted Mem0 API instances, enabling Claude Code to manage memories via custom endpoints. | |
| MCP OAuth Test emave/mcp-oauth-test Multi-tenant MCP server with OAuth 2.1 authorization, enabling tenant-scoped tool access and audit logging. | |
| whatsapp-mcp emawritz/whatsapp-mcp Connects WhatsApp to Claude Code, enabling message reading, audio transcription, image analysis, and message sending with full codebase context. | |
| open-artifacts emaxe/open-artifacts Enables AI agents to publish, retrieve, update, and delete hosted HTML, Markdown, Mermaid, and SVG artifacts and to create, list, or revoke shareable links through authenticated, scope-enforced tools. It exposes artifact hosting over Stream | |
| Ableton MCP Enhanced emaxees/ableton-mcp-enhanced Enables controlling Ableton Live from Cursor using natural language commands for session/transport, MIDI, arrangement, plugins, mixer, and batch operations. | |
| TickTick MCP emb99/ticktick-mcp A remote MCP server that enables Claude to create and manage TickTick to-dos using the TickTick Open API. It supports nine tools for projects, tasks, and sections, and works across all Claude platforms (web, mobile, desktop, Cowork). | |
| Ember MCP Server ember-tooling/ember-mcp A Model Context Protocol server that provides tooling support for Ember.js development, allowing developers to execute CLI commands, run codemods, access documentation, and discover community resources. | |
| taskmarket-mcp-server ember2819/taskmarket-mcp-server Integrates TaskMarket into MCP-compatible agents, enabling task discovery, details, and submission with secure API key handling. | |
| embercore embercore-labs/embercore Open-source AI marketing agent toolkit with plan-first workflow, human checkpoints, and BYOK support. | |
| FreeLLM-MCP emberfreellm/freellm-mcp Enables AI coding assistants and agent workflows to query live measured free-LLM performance and availability, including throughput, uptime, tool-calling success, and model diagnostics. | |
| KingBuilds MCP Server emberphoenix33/kingbuilds-mcp-server Provides sandboxed file operations, web scraping, data transformation, and authenticated HTTP requests with SSRF protection. | |
| seamcheck emberthreadhq/seamcheck Enables coding agents to scan their work mid-session for dead seams — files reachable only by tests — returning the same JSON as the CLI. | |
| Emblem AI emblemcompany/emblemai-agentwallet Emblem Vault AI.
Get a multi chain wallet by using the server.
Do everything crypto. Swaps, NFTs, Cross-chain bridges, Bitcoin assets, Defi... | |
| hy3-local-gateway embracecactus/hy3-local-gateway MCP server that reuses an existing CodeBuddy login to provide read-only model access as a sub-agent and an OpenAI-compatible proxy, without requiring API keys. | |
| GraphRAG MCP embracefailure/mcphub Enables enterprise document retrieval using graph-based reasoning and knowledge graphs. Allows agents to search and extract information from scattered documents through structured entity and relationship extraction. | |
| kb-agent-platform embracingthefuture/kb-agent-platform Enables MCP hosts like Cursor or Claude to query an enterprise knowledge base via stdio, providing RAG-based answers with cited sources. | |
| MercadoLibre MCP Server eme-ce/mcp-mercadolibre Connects Claude to your MercadoLibre seller account, enabling natural language management of listings, orders, and shipments. | |
| media-mcp emedinamaza/media-mcp-app Enables movie/series recommendations via TMDB API and personal tracking of watchlist, watched history, and episodes in local SQLite. | |
| RDF Explorer emekaokoye/mcp-rdf-explorer The Model Context Protocol (MCP) server provides a conversational interface for the exploration and analysis of RDF Turtle Knowledge Graph in Local File mode or SPARQL Endpoint. | |
| Hybris MCP Server emenowicz/hybris-mcp Enables AI assistants to interact with SAP Commerce Cloud (Hybris) instances for product management, order viewing, FlexibleSearch queries, Groovy script execution, ImpEx operations, and system administration tasks. | |
| polish-legal-mcp emenowicz/polish-legal-mcp Enables MCP clients such as Claude to search and retrieve official Polish legislation from the Sejm ELI API and court decisions from SAOS, fetch exact provision wording, check amendments, and verify legal citations. Every result carries exp | |
| Emercoin swap emercoin/swap Keyless MCP exchanger for AI agents — pay an exact amount to one deposit address, EMC delivered to any address. USDT(Tron) > EMC. Live at https://swap.emercoin.com/mcp | |
| ThunderSend MCP emercons/thundersend-mcp Lets an AI assistant save drafts and open compose windows for sending mail in Thunderbird or Betterbird, with optional account listing for sender selection. It deliberately exposes no ability to read, search, move, delete, forward or reply | |
| Hermes SearXNG MCP Server emericlaberge/hermes-searxng-mcp Enables privacy-preserving web search and content extraction through a self-hosted SearXNG instance, aggregating 70+ engines and converting pages to Markdown for LLM use. | |
| Emeritus MCP Server emeritus-china/emeritus-mcp MCP server for integrating AI models with Emeritus services, enabling user management, tag operations, order management, and leads import via a standardized interface. | |
| pacifico emersoftware/pacifico Enables local archiving and searchable recall of AI coding sessions from Claude Code, Codex, Pi, and OpenCode via MCP, allowing agents to access past conversations as context. | |
| cep-viacep emerson-rossi/cep-claude-plugin Enables Brazilian address lookup by CEP and reverse lookup from UF, city, and street via the public ViaCEP API. | |
| agente-mcp-streamlit-ecommerce emersonelio/agente-mcp-streamlit-ecommerce Enables natural-language querying of an e-commerce dataset by providing a LangChain agent that uses tools to execute parameterized SQL queries on a SQLite database, with short-term memory and Streamlit or Claude Desktop interfaces. | |
| Unity MCP emeryporter/unitymcp A Model Context Protocol server that integrates AI assistants like Claude and Cursor directly into the Unity Editor to automate game development workflows. It provides over 40 built-in tools for scene manipulation and project management, wh | |
| VirusTotal MCP Server emeryray2002/virustotal-mcp Provides comprehensive security analysis tools for querying the VirusTotal API, enabling detailed security reports on URLs, files, IP addresses, and domains with automatic relationship data fetching. |
47,851–47,900 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.