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 |
|---|---|
| soapbox-faith alansafahi/soapbox-faith Faith tools for AI agents: cited public-domain (KJV) Scripture verification, ORA Bible Q&A, sermon search, a church directory, and consent-gated prayer requests and giving. Free read tools need no key. | |
| ClickUp Multi-Workspace MCP Server alanse-inc/clickup-multi-mcp-server Enables AI agents to interact with tasks, spaces, lists, and folders across multiple ClickUp workspaces via the Model Context Protocol. | |
| MCP Server - Google Workspace alanse-inc/mcp-server-google-workspace Provides comprehensive programmatic control over Google Workspace applications including Sheets, Docs, Drive, Gmail, Calendar, and Slides with 141 tools for automation and management. | |
| Pocket Casts MCP Server alansmodic/pocketcasts-mcp Connects AI assistants to Pocket Casts accounts for browsing subscriptions, reading episode details, and retrieving transcripts with automatic transcription via AssemblyAI when no native transcript exists. | |
| fl-studio-mcp alansork/fl-studio-mcp An MCP server that connects Claude to FL Studio, enabling natural language control of transport, mixer, channel rack, and piano roll operations. | |
| Tarantella Slack MCP Server alantaranti/tarantella-mcps Enables AI assistants to search Slack messages and channels using the Slack Web API, with filtering options by user, date, channel, and content type. | |
| wafer-map-mcp alantseng1018/llm-agent-yield-analysis-tools Exposes semiconductor wafer analysis tools including wafer maps, P-charts, and statistical plots, enabling AI assistants to visualize and analyze wafer test data. | |
| ffmpeg-mcp-server alanveloper-epam/ffmpeg-mcp-server Enables AI coding agents to safely inspect, trim, reframe, extract audio from, and burn dynamic subtitles into media files through structured, sandboxed FFmpeg/ffprobe tools with validation and dry-run previews. | |
| tarefy-mcp alanvncs/tarefy-mcp Enables AI agents to access Tarefy tasks, internal team conversations, and public client conversations via MCP tools like get-task and login. | |
| HoldDesk alanwen168/holddesk Enables voice assistants and MCP clients to check office availability, place appointment holds, answer FAQs, provide illustrative insurance quote ranges, and escalate requests. It keeps final approval with a signed-in human desk, so no hold | |
| blackboard-mcp alanwtom/blackboard-mcp Enables AI assistants to read a student's own Blackboard (Ultra) data—courses, assignments, grades, announcements, and attachments—through their existing logged-in browser session, read-only and locally. | |
| fwrd-sms-mcp alanwtom/fwrd-sms-mcp Enables an AI agent to wait for and retrieve SMS verification codes forwarded from your iPhone, returning each code once, and to list recent texts for login links or non-numeric messages. It runs in your own Cloudflare account and deletes s | |
| MCP Poker alanyangrice/mcp-poker An MCP server that provides poker play recommendations by combining real-time Monte Carlo equity calculations with historical player tracking and exploit-based advice. It enables users to import PokerNow hand histories to analyze player ten | |
| mcp-alapi-cn alapi-sdk/mcp-alapi-cn 这是一个基于 ALAPI 的 MCP (Model Control Protocol) 服务器实现，可以通过MCP协议直接调用ALAPI的接口 | |
| claude-docs-mcp alara7/mcp-server-ccar-f A local MCP server providing read-only search and retrieval over the Claude documentation corpus via SQLite FTS5, with tools for searching, fetching documents, outlines, and listing sources without network I/O. | |
| flow-mcp alarconcesar/flow-mcp MCP server for generating images via Google Flow's API without daily quota limits, supporting text-to-image and image-to-image generation. | |
| gemini-tts-mcp alarconcesar/gemini-tts-mcp Multi-key Gemini TTS MCP server with automatic API key rotation, model fallback, and 30 multilingual voices. Enables text-to-speech generation through MCP tools. | |
| Bridge Suite MCP Server alarinel/bridge-suite-mcp Gives AI agents full access to IntelliJ IDE by running terminal commands, triggering builds, pushing notifications, and querying project context through a single MCP server with specialized plugins. | |
| x-agent-mcp alarok/x-agent-sdk Enables AI agents to interact with X (Twitter) through its private GraphQL API using session cookies, supporting tweets, replies, likes, retweets, searches, direct messages, and more. Provides 24 MCP tools for full account automation. | |
| clinicaltrialsgov-mcp-server alarsson575/clinicaltrialsgov-mcp-server Enables searching ClinicalTrials.gov studies, retrieving full protocol records and posted results, discovering valid API fields and values, and matching patient demographics to candidate recruiting trials. It supports full-text and field-sp | |
| DCS-ME-gateway alasek/dcs-me-gateway Enables AI mission designers to author and validate DCS World missions through the Mission Editor via a versioned protocol, providing tools for planning, payloads, map inspection, and live editor integration. | |
| myUplink MCP Server alastair-pandelus/myuplink-mcp-server Connects MCP clients such as Claude to a NIBE myUplink heat-pump account, letting users list systems and devices, read sensor values and common parameters, check alarms, view smart-home zones, and write settings where scopes allow. Handles | |
| MCP Imposto de Renda alastecnology/mcp-imposto-de-renda Enables an AI assistant to build and update an IRPF 2026 tax return entirely on your machine, reading and writing the official program's .DBK backup file, adding income and expenses, computing tax under both the simplified and complete mode | |
| EarSay MCP alastormordrek/earsay-mcp Provides voice transcription control and polling for MCP-compatible agents, enabling start/stop/pause/resume and retrieval of new text via tools. | |
| DefterIki alatifkose/defteriki Enables local document-based personal finance management with SQLite storage, accessible via the Model Context Protocol. | |
| MCP Trino Server alaturqua/mcp-trino-python A Model Context Protocol server that provides seamless integration with Trino and Iceberg, enabling data exploration, querying, and table maintenance through a standard interface. | |
| Juror Cloud alaurent746/juror Enables an MCP client to sign in and inspect workspace-scoped review findings and hosted runs, and to prepare, then start or rerun after explicit confirmation, an existing hosted code review for a pull request. It exposes only concise summa | |
| cpanel-mail-mcp alaverde/email-mcp Enables agents to read, search, organize, draft, and optionally send email from a cPanel mail account over IMAP and SMTP, with configurable safeguards for sending and permanent deletion. | |
| WikiCleanHTML alavna/wikicleanhtml Fetches Wikipedia articles and returns cleaned, readable HTML stripped of citations, infoboxes, navboxes, and other clutter. Enables fetching specific articles or random ones with options to keep images, tables, or links. | |
| stellar-mcp-server alawusa-naira/stellar-mcp-server An MCP server that provides Stellar blockchain tools for account queries, Soroban contract simulation, and boilerplate generation within compatible AI IDEs. | |
| File Context MCP Server alayonyo/mcp-resume Enables AI assistants to read, search, and analyze local file systems with tools for reading file contents, listing directories, searching by patterns, and analyzing folder structures for context-aware queries. | |
| MCP Server for Frappe alazabdev/mcp-server Enables secure, permission-controlled exposure of Frappe/ERPNext DocTypes and CRUD, search, metadata, and deletion operations to MCP clients such as AI agents, with field-level allowlisting and audit logging. | |
| abap-mcpb albanleong/abap-mcpb Enables SAP ABAP development by connecting Claude Desktop to SAP systems via the ADT API for reading, writing, and deploying code. It offers 25 tools covering object management, transports, quality assurance, and SQL data access. | |
| Grant Tool albanlongchamp/grant-tool-public Enables a connected frontier-model assistant to develop research grant proposals with traceable evidence, claim review, and versioned drafts. It preserves source passages, judgments, proposal versions, and editable exports in a local resear | |
| Currency-Weather MCP Server albats/mcp-currency-weather-project Enables currency conversion, exchange rates, geocoding, and weather queries through MCP tools, integrated with OpenAI Responses API. | |
| mcp-systemd albe83/mcp-systemd Provides an experimental semantic interface for discovering and reading mock systemd unit resources for service and timer units, with tools for listing supported unit types and units. | |
| claude-usage albeedev/claude-usage Provides Claude plan usage data (session and weekly percentages) as an MCP tool by reading through a logged-in browser, enabling Claude to check its own remaining usage. | |
| mockoon-mcp albenzoo/mockoon-mcp Lets AI assistants create and manage Mockoon mock APIs through natural language. | |
| financial-agent albeorla/personal-finance-agent Enables AI agents to manage personal finances with deterministic, grounded tools for cash-flow projection, drift detection, reconciliation, and Todoist integration. All figures trace back to a local SQLite database. | |
| sas-local-mcp albert-huan/sas-local-mcp A read-only MCP server that lets LLMs explore and query local SAS datasets (.sas7bdat / .xpt) without Viya, network, or SAS licensing. It exposes tools for listing, metadata inspection, summarization, frequency tables, value-label decoding, | |
| QuickBooks Online MCP Server albert-lacroix/quickbooks-online-mcp-server Provides comprehensive CRUD operations for 29 QuickBooks Online entity types and 11 financial reports, enabling full accounting management through natural language. | |
| MCP G Suite Integration albert-launcher/mcp-gsuite Integration server that enables interaction with Google services including Gmail and Calendar, allowing users to manage emails, draft responses, and schedule events across multiple Google accounts. | |
| GenLayer MCP Server albert-mr/genlayer-mcp-server A comprehensive MCP server for generating sophisticated GenLayer Intelligent Contracts with AI-native blockchain capabilities. | |
| gpt-image-2-combined albert850904/gpt-image-2-skill Enables generating images from text prompts using OpenAI's GPT-Image-2 model within Claude Code and Codex conversations. | |
| nl2sql albertd01/nl2sql Enables natural-language questions over any SQLAlchemy database by inspecting the schema, looking up stored values, and running read-only SQL queries to answer or explain when data is unavailable. | |
| mcp-wb albertharbez/mcp-wb Enables access to Wildberries marketplace feedback and questions, allowing listing accounts, filtering feedbacks, viewing statistics and ratings, and posting answers, with secure token management and throttling. | |
| Lunar Calendar MCP Server alberthuangksfo/lunar_mcp_server A Model Context Protocol (MCP) server for Chinese traditional calendar functions, including BaZi calculation, calendar conversion, Huangli query, daily fortune, solar terms, and Wu Xing analysis. | |
| MCP Control Plane albertik322-sudo/mcp-control-plane Open-source, Windows-first control plane for operating local and homelab services through typed MCP servers, featuring 13 servers and 290 tools with infrastructure adapters for Windows, Ubuntu, Docker, and more. | |
| ghidraMCP albertlab0/ghidramcp An Model Context Protocol server that enables LLMs to autonomously reverse engineer applications by exposing Ghidra's decompilation and analysis tools. It allows AI agents to list code structures, rename methods, and analyze binaries direct | |
| e-worker-mcp albertm88/e-worker-mcp A local-first MCP server that handles daily work tasks through your AI assistant: converts meeting notes into todos, manages todo lifecycle, tracks work hours, generates daily/weekly reports, organizes files via move-only operations, and di |
25,801–25,850 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.