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 |
|---|---|
| Blender Production MCP diegoarias32/blender-production-mcp Enables MCP-capable assistants to inspect, create, measure, and review Blender production workflows for characters, rigs, animation, game meshes, facial performance, secondary motion, and PBR materials with checkpoints and visual QA. | |
| aranet4-mcp-server diegobit/aranet4-mcp-server MCP server to manage your Aranet4 CO2 sensor, enabling scanning, data fetching, historical querying, and plotting. | |
| mcp-database diegobulhoes/mcp-database MCP server for multiple databases (PostgreSQL, MySQL, MariaDB, SQLite, MongoDB, Redis) with tools for schema inspection, querying, performance diagnostics, and safe write operations, featuring access modes, PII masking, and audit logging. | |
| claude-in-firefox diegochagas/claude-in-firefox Enables Claude Code to control Firefox through tools for tabs, navigation, clicks, typing, scrolling, screenshots, page reading, forms, JavaScript, and console/network logs. | |
| AISecretary diegodopazo/aisecretary A modular collection of MCP servers for automating virtual secretary tasks within Microsoft Outlook, including email management, calendar operations, contacts, tasks, and mailbox settings through Microsoft Graph API. | |
| Map Canvas MCP diegodox/map-canvas-mcp Enables interactive map display with up to 50 marked places and optional route lines, using a bundled Leaflet UI and OpenStreetMap tiles. | |
| Guess Number MCP Server diegoduas/mcp-remote Enables users to play a number guessing game through a remote MCP server deployed on Google Cloud Run. The server tracks game state per user and maintains conversation logs for an interactive guessing experience. | |
| local-kms-mcp-server diegoescalonaro/local-kms-mcp-server Local-first MCP server for per-agent key management, generating and using signing keys without external KMS. | |
| BlenderMCP diegofornalha/blender-mcp-claude BlenderMCP enables Claude AI to directly interact with and control Blender for prompt-assisted 3D modeling, scene creation, and manipulation. It supports object and material control, scene inspection, and execution of Python code through na | |
| Docker MCP diegofornalha/docker-mcp-py Enables Docker container management directly through Claude using the Model Context Protocol. Provides 14 tools for managing containers, images, volumes, and Docker Compose deployments through natural language commands. | |
| MCP-Server-TESS diegofornalha/mcp-server-tess A Model Context Protocol server that enables integration with the TESS API, allowing users to list and manage agents, execute agents with custom messages, and manage files through natural language interfaces. | |
| MCP Server Trello diegofornalha/mcp-server-trello Enables seamless integration with Trello boards, allowing users to manage cards, lists, and activities while automatically handling rate limiting and providing type safety. | |
| MCP Shell Server diegofornalha/mcp-shell-server A secure server that implements the Model Context Protocol (MCP) to enable controlled execution of authorized shell commands with stdin support. | |
| mcp-turso-cloud diegofornalha/mcp-turso-cloud An MCP server that integrates Turso databases with LLMs, supporting organization and database-level operations with two-level authentication. | |
| MCP Sentry para Cursor diegofornalha/sentry-mcp-cursor Um servidor MCP completo para integração com Sentry no Cursor, oferecendo 27 ferramentas para monitoramento de erros, performance e saúde de aplicações. | |
| InventarioDB diegogfhjk/mcp A small MCP server that manages a product inventory using SQLite, providing CRUD operations through exposed MCP tools. | |
| playpub diegohorvatti/playpub Enables publishing Android apps to the Google Play Console from monorepos by exposing commands as MCP tools that handle AAB uploads, store listings, testers, and setup via the Google Play Developer API, returning structured JSON results. | |
| tachy diegokoes/tachy A self-hosted knowledge engine that enables Claude Code to fetch, analyze, and store structured lessons learned from support tickets/issues via MCP tools, leveraging hybrid search for relevant prior cases. | |
| legit-prv-mcp diegolegitsec/mcp-internal MCP server for Legit Security that answers questions about security issues, Actions, inventory, posture, and platform usage across one or multiple tenants. | |
| Academic Paper Search MCP Server diegoli08/academic-search-mcp-server Enables Claude and other MCP-compatible clients to query Semantic Scholar and Crossref for scholarly works, retrieving metadata, abstracts, TL;DR summaries, and full-text links when available. | |
| Social Broadcast MCP diegolm2012-creator/social-broadcast-mcp Enables publishing to Facebook, Instagram, and YouTube through official APIs using your own OAuth credentials, with support for images, videos, Reels/Stories, and scheduled posts. | |
| pmi-mcp-server diegoluppi1993/pmi-mcp-server MCP server that exposes a single tool to execute SQL queries directly against Microsoft SQL Server via pyodbc, returning result sets as JSON. It forwards queries without parsing or filtering, relying on database permissions for security. | |
| Gmail & Calendar Multi-Account MCP Server diegomaldonadorosas/gmail-mcp A local MCP server that connects multiple Gmail and Google Calendar accounts to Claude Desktop, enabling email and calendar management across accounts. | |
| Email MCP Server diegomartin733/email-mcp Enables AI assistants to read, search, send, reply, forward, schedule, organize, and analyze email across multiple IMAP/SMTP accounts, with real-time IMAP IDLE triage, verification-code catching, calendar extraction, and analytics. It offer | |
| WhatsApp Channel diegomichel19/whatsapp-claude-plugin Enables driving a Claude Code (or other MCP client) session directly from WhatsApp chats, with bidirectional messaging, media and locally transcribed voice notes, polls, per-group personalities, cron tasks, and emoji-reaction approval of to | |
| opengsc diegomm27/easygsc Enables MCP clients such as Claude to read Google Search Console data, including search analytics, sitemaps, and URL inspection, so users can answer SEO questions with real numbers while remaining read-only. | |
| MCP Context Hub diegonogueiradev/mcp-context-hub A local MCP server for RAG memory, semantic search, and context optimization using Ollama and SQLite. It serves as a central hub that manages document embeddings, text compression, and proxies calls to other sub-MCP servers. | |
| repopack MCP server diegonogueiradev/repopack Serves local and remote repositories over MCP, enabling AI models to search and retrieve code snippets, file contents, and repository structures on demand. | |
| Mellos Mapping diegoomar925/mellos-mapping Enables Claude Code, Codex, and other MCP clients to declare a layered, bottom-up dependency design as ghost nodes and then light each node up as it is built and verified, mirroring the whole structure in a live terminal pane beside the con | |
| Codexless diegoozdemir/codexless Enables ChatGPT to inspect projects, edit files, run bounded commands, use Chrome/Edge and live Excel controls through a supported MCP connection, and explicitly invoke Codex only when model-backed work is actually needed. | |
| mcp-google-ads diegorenatob/mcp-google-ads Enables keyword research and read-only Google Ads reporting through Google Ads Explorer API access combined with Google Autocomplete, including keyword suggestions, location lookup, GAQL queries, and search-term reports. Runs as a remote Do | |
| MCP-PostgreSQL-Ops diegororato5559/mcp-postgresql-ops Enables AI assistants to monitor and administer PostgreSQL 12-18 databases through natural language, covering performance and slow-query analysis, table bloat detection, connection and lock monitoring, autovacuum and maintenance recommendat | |
| job-search-copilot diegoruv20/job-search-copilot Enables an MCP-capable coding agent to run a local-first job search: recording verified opportunities in a private SQLite tracker, tracking follow-ups and outcomes, and preparing evidence-based resumes, application answers, and outreach dra | |
| Another bloated Obsidian MCP Server diegorv/another-bloated-obsidian-mcp-server A Model Context Protocol (MCP) server that provides AI assistants with secure access to Obsidian vaults. Enables reading, writing, searching, and managing notes without requiring Obsidian to be running. | |
| Vectorize MCP Server diegosullivan1045/vectorize-mcp-server Enables users to perform vector searches, retrieve documents, extract and chunk files into Markdown, and generate private deep research reports from configured pipelines. | |
| swarmix-mcp diegotorreslopez81/swarmix-mcp AI client acquisition autopilot. 15 MCP tools for LinkedIn, Email, X, Instagram & Blog outreach from Claude. | |
| mef_subnational_efficiency_mcp diegoturpo/mef_subnational_efficiency_mcp Provides 10 tools over the CKAN API to audit and analyze Peruvian public spending, including budget execution data for 2025 and digitized historical records from 1964. | |
| MCP Local Server diegoval-dev/mcp-server A minimal Model Context Protocol server that provides basic utility tools including mathematical operations, text processing, hashing, and JSON validation. Implements JSON-RPC stdio transport for local testing and development. | |
| Vectorize MCP Server diegovandenberg/vectorize-mcp-server Enables vector search and document retrieval, text extraction and chunking into Markdown, and private deep research through a Vectorize pipeline. | |
| mcp-maker diegovergacas/mcp Enables users to learn what MCP is and generate new MCP servers from an idea, including tool design and configuration files. | |
| agent-checkpoint-mcp diegoware/agent-checkpoint-mcp A local MCP server that saves work-in-progress checkpoints to SQLite, enabling AI agents to resume interrupted sessions without redoing work. | |
| MCP Cobranza diegoxai-shape/mcp_model Provides read-only tools for analyzing a collections portfolio, including summaries, aging, account details, cashflow, and collector performance, with on-demand HTML reporting via natural language. | |
| nostr-mcp diegoyegros/nostr-mcp A read-only MCP server for safely exploring Nostr, enabling agents to resolve identifiers, fetch profiles and events, query notes, and inspect relay metadata. It does not accept private keys or publish events. | |
| jev-agent-quality diegozhou114-cloud/jev-agent-quality Enables code agents to run risk-based Jev quality reviews on focused diffs through a read-only MCP tool, returning structured scores and weakness hints without modifying code. | |
| privacy-informativa-mcp diegts/privacy-informativa-mcp Helps individuals analyze privacy policies and verify if a website's technical behavior matches its stated privacy practices. | |
| ru-finance diekinari/ru-finance-mcp MCP server providing financial data from Moscow Exchange and Bank of Russia, including quotes, bond metrics, interest rates, and portfolio analysis. Enables AI agents to analyze Russian financial markets through natural language. | |
| ga4-mcp-server dienhokhanh/ga4-mcp-server Enables AI assistants to query Google Analytics 4 properties for standard, pivot, realtime, and batched reports, discover accounts, properties, and metadata, and optionally manage custom dimensions, metrics, and key events. | |
| Google Search Console MCP dienhokhanh/google-search-console-mcp Enables MCP clients to query Search Analytics metrics, list and inspect properties and sitemaps, and inspect indexed URLs with secure authentication and optional allowlisted write controls. | |
| gtm-mcp-server dienhokhanh/gtm-mcp-server Enables creating and managing Google Tag Manager tags, triggers, and variables directly from any MCP client, operating at the workspace draft level without auto-publishing. | |
| mcp-openai-ads dienhokhanh/mcp-openai-ads Enables AI assistants to read a ChatGPT Ads account — account summaries, performance insights, campaigns, ad groups, ads, product feeds and conversion setup — and, when writes are explicitly enabled, create or update campaigns, budgets and |
44,551–44,600 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.