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 |
|---|---|
| mailru-mcp diesel-v/mailru-mcp Enables users to interact with Mail.ru mail and calendar through IMAP/SMTP and CalDAV, including searching messages, managing flags and folders, creating drafts, sending when enabled, and viewing, creating, updating, deleting, and respondin | |
| TradesPro dieselpro1111/trades-mcp-server TradesPro is an open source MCP server that gives AI assistants structured knowledge of the skilled trades: electrical (NEC 2023), plumbing (UPC 2024), and HVAC (IRC Mechanical). | |
| Bitbucket MCP dieter1485/bitbucket-mcp Enables AI assistants to interact with Bitbucket Cloud and Server APIs to list and retrieve repositories, manage pull requests, and access related resources via the Model Context Protocol. | |
| applemusic-mcp dieter288/applemusic-mcp Enables MCP clients like Claude, Cursor, Cline, and Windsurf to search and browse the Apple Music catalog and library, manage playlists and favorites, control playback, and drive the Up Next queue on macOS, Windows, and Linux. It works with | |
| onedrive dieter84214/onedrive-cli Enables MCP clients to browse and read a user's cloud drive read-only, including folder listing, full-text search, file finding, album listing, file reading, metadata retrieval, and storage quota reporting. | |
| read-website-fast dietererdogan61/mcp-read-website-fast Fetches webpages and converts them into clean, token-efficient Markdown, optionally crawling multiple linked pages while respecting robots.txt and caching results for AI agents and LLM pipelines. | |
| Semantic Scholar MCP Server dieterherrera6757/semantic-scholar-fastmcp-mcp-server Enables searching and retrieving academic papers, author profiles, citations, references, and recommendations through the Semantic Scholar Academic Graph API, without writing API code. Supports relevance, bulk, and title search, batch looku | |
| FirstData MCP dieterkim/firstdata Enables AI agents to turn natural-language questions into authoritative primary data sources, ranked by authority level and returned with API details, coverage metadata, and traceable evidence chains. It also supplies step-by-step website n | |
| Android Source Explorer MCP Server dieters73120/android-source-explorer-mcp Enables precise, on-demand access to AOSP framework and Jetpack/AndroidX source code so AI tools can inspect classes, methods, inheritance hierarchies, and cross-file references. | |
| MCP Python Interpreter dietersheikh625/mcp-python-interpreter Enables LLMs to manage Python environments, execute code and scripts, install packages, and read/write files within an isolated working directory. It also provides prompts for common tasks such as function creation, refactoring, and debuggi | |
| Firestore Advanced MCP diez7lm/firestore-advanced-mcp A Model Context Protocol server that enables large language models like Claude to perform comprehensive interactions with Firebase Firestore databases, supporting full CRUD operations, complex queries, and advanced features like transaction | |
| Amazon SageMaker Catalog MCP Server difeorte/amazon-sagemaker-catalog-mcp-server Auto-generates MCP tools for all Amazon DataZone API operations, enabling natural language management of SageMaker Catalog resources. | |
| Diffblue Cover MCP Server diffblue/cover-mcp Enables AI development environments to call the Diffblue Cover CLI tool to automatically generate unit tests for Java code. | |
| diffbot-mcp diffbot/diffbot-mcp A Diffbot MCP server that provides tools for extracting structured web content, searching the web with accuracy-focused ranking, and enhancing entity data from the Diffbot Knowledge Graph. | |
| Deep Graph MCP Server diffbot/mcp-code-graph Enables seamless interaction with public or private code graphs from DeepGraph and CodeGPT to perform semantic searches and dependency analysis. It allows developers to explore architectural relationships, retrieve source code, and analyze | |
| Mac Sandbox Control MCP Server different-ai/mac-sandbox-control Enables agents to manage and operate macOS VM workspaces through authenticated MCP tools, including lifecycle control, command execution, job monitoring, and access to desktop connection and guest login details. | |
| Session Think MCP differentstuff/session-think-mcp A session-based thinking workspace for Claude that preserves and structures reasoning text. Supports structured session names, search, and persistent storage for complex problem-solving. | |
| agent-orchestration diffmeyend/agent-orchestration A multi-agent runtime that coordinates six specialized agents through a typed artifact pipeline with 41 RPC methods. It features dynamic autonomy levels and context sufficiency scoring that adjust agent behavior based on the operator's stat | |
| dwd-mcp difu/dwd-mcp Enables access to German weather data from the Deutscher Wetterdienst, including station observations, forecasts, and warnings, through standardized MCP tools. | |
| roblox-mcp-difz difz25x/roblox-mcp-difz MCP server for controlling and reverse engineering Roblox games, providing 132 tools across 8 categories for instance exploration, property inspection, input simulation, and more. | |
| Expense Tracker MCP Server digam-hue/expense-tracker-mcp-server Enables AI assistants to add, list, and summarize personal expenses backed by a persistent Turso database. | |
| Local File Organizer diganto-deb/local_file_organizer A file organization MCP server that safely categorizes and manages files in allowed directories by type, with search and analysis capabilities. | |
| CoursePack Local MCP Server digaocoite/canvasmcplocal Read-only MCP server that provides Claude Desktop with access to converted Canvas course exports, including Markdown files, reports, and search tools for local course content. | |
| h4kfi-mcp digenaldo/h4kfi Enables AI agents to drive wireless penetration testing end-to-end through MCP, including monitor mode, network scanning, handshake and PMKID capture, WPS attacks, deauthentication, and password cracking. It exposes all h4kfi tools to MCP-c | |
| Heart Rate MCP digi-the-robot/heart-rate-mcp Enables AI clients to access live heart rate readings, recent history, and events from sources such as Pulsoid, HypeRate, Bluetooth, OSC, HTTP pushes, or text files, while optionally pushing updates to Discord and JSON webhooks. | |
| FMP MCP Server digibugcat/cassandra-fmp Provides financial data from Financial Modeling Prep for AI-assisted investment research, including company profiles, financial statements, and analyst ratings. It features high-level workflow tools for market analysis and atomic tools for | |
| Gemini Interactions MCP digibugcat/gemini-interactions-mcp A FastMCP server for stateful Gemini conversations with automatic Google Search grounding. | |
| Logpush MCP digibugcat/logpush-mcp Enables reading and analyzing Cloudflare Workers logpush data stored in R2 buckets. Supports searching logs with filters, viewing statistics, accessing errors, and browsing logs by date and environment. | |
| @digidai/mcp-website2markdown digidai/website2markdown Converts any web page to clean Markdown, handling JS-heavy SPAs, paywalled content, and Chinese platforms through a 5-layer fallback pipeline and 14 site adapters. | |
| dml-bps-mcp digimetalab/dml-bps-mcp MCP server for accessing Indonesian BPS statistics data via natural language queries. | |
| agent-scrape digimiami/agent-scrape MCP server that lets AI agents scrape web pages as clean markdown for a micro-payment in USDC, using the x402 protocol on Base network. No API keys or signup required. | |
| digisensus-recorder digisensus/digisensus-recorder Lets AI agents search, read and export call recordings, transcripts and AI meeting notes from Digisensus Recorder, a free open-source call recorder for macOS, and start or stop recording. Runs locally on the Mac and talks to the app over a | |
| Ops HubSpot CRM MCP Server digishop92/mcp-serveur-ops-hubspot-crm Custom MCP server for HubSpot CRM providing ICP segmentation, scoring, duplicate detection, Data Quality Score, and lifecycle stage automation. Exposes 39 tools to enhance HubSpot's native capabilities. | |
| fts-gate-mcp digitable-lol/fts-gate MCP server for fts-gate. It enables verification of FTS executable specifications through proof-carrying checks, exposing tools to run gate checks (fts_gate_check) and list available morphisms (fts_morphisms_list), with rejection of invalid | |
| digit-tools digitable-lol/tools-core MCP stdio server that exposes 95 headless it-tools utilities (crypto, encoding, converters, generators, text, math, and more) through three routing tools (categories, list, execute), with flat JSON schemas, worked examples, and deterministi | |
| Dell SC Series MCP Server digitainit/dell-sc-series-mcp A read-only MCP server that lets AI assistants diagnose Dell SC Series storage arrays through the array's own REST API. | |
| marketing-mcp digital-021/marketing-mcp Enables marketing optimization tasks such as copywriting, campaign analysis, social media planning, audience segmentation, and KPI tracking through natural language. | |
| Max MCP Server digital-crew-technologies/max-mcp-server Enables to fetch and update workspace profile settings for the Digital Crew Max AI sales agent via MCP tools. | |
| MCP Process Server digital-defiance/mcp-process Enables AI agents to launch and manage system processes with strict security controls through executable allowlists, resource monitoring, and output capture capabilities. | |
| mcp-aws digital-dimentia/mcp-aws Enables read-only querying of AWS accounts, regions, and resources through a small fixed set of MCP tools backed by a YAML catalog of views. | |
| Ghost in the Box MCP Server digital-disconnections-ltd/ghost-in-the-box Connects MCP clients to a local social engine that reads bounded posts, comments, replies, and feeds into local inboxes, turns source material into drafts and briefs, and publishes exact frozen jobs with recorded provider IDs and receipts a | |
| Model Context Protocol Demo digital-duck/mcp_demo A demonstration server for the Model Context Protocol (MCP) that exposes calculator and Yahoo Finance tools, allowing LLMs to interpret natural language requests and make tool calls via the MCP standard. | |
| jgrants-mcp-server digital-go-jp/jgrants-mcp-server MCP server for Japan's Jグランツ grant application system, enabling LLMs to search and retrieve subsidy information via natural language. | |
| komodo-mcp digital-grease/komodo-mcp An MCP server that exposes the full API of the Komodo infrastructure management platform. It enables users to manage deployments, stacks, servers, and containers through tools for inspection, configuration, and operational control. | |
| LogNexus digital-lake-ai/lognexus Universal Git-powered persistent memory, context rules & native MCP server for AI coding agents. Prevents context amnesia with stateful workflows, Git Notes, and cross-model review gates across Claude, OpenAI, Gemini & DeepSeek in Cursor, C | |
| gtfs-pro-mcp digital-mountaineers/gtfs-one-mcp MCP server that provides tools for querying live transit data (stops, departures, routes, vehicles, alerts) from any WP GTFS Pro site, enabling AI assistants to answer rider questions. | |
| feishu-demand-mcp digital-sy/feishu-demand-mcp A self-hosted MCP server for managing a Feishu (Lark) demand pool and archiving daily reports. It exposes tools to list, get, create, update demands, and archive daily reports. | |
| dtJiraMCPServer digital-thought/dtjiramcpserver An MCP server that bridges LLM clients with Atlassian Jira Cloud and Jira Service Management Cloud REST APIs, enabling administrative and operational tasks via natural language. | |
| DVBase MCP Server digital-vereinfacht/dvbase-mcp-server Enables Claude to access Ninox database schema and data, supporting table inspection, data queries, and context retrieval. | |
| mcp-server digitaladapt/mcp-server Enables language models to run command-line tools and access calendars, Gitea repositories, notifications, and weather through typed HTTP endpoints. |
44,601–44,650 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.