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 |
|---|---|
| MCP Standards airmcp-com/mcp-standards A self-learning AI standards system that automatically detects patterns from user corrections and updates AI configuration files. Learns from repeated corrections (like 'use uv not pip') and automatically generates CLAUDE.md and other AI as | |
| air airmcp-dev/air SDK-free MCP server framework with self-implemented protocol engine (MCP 2026-07-28 + legacy), 19 built-in plugins, OWASP MCP Top 10 security, and zero external dependencies. | |
| insight-mcp airohh/insight-mcp Enables hybrid document search (BM25 and dense) over a configurable corpus via MCP tools, returning passages and sources for AI agents to cite in answers. | |
| sora-mcp airsulg/sora-mcp MCP server for generating videos using OpenAI Sora model via api.tu-zi.com, enabling AI assistants to create videos from text prompts with customizable orientation and model quality. | |
| GEDCOM MCP Server airy10/gedcommcp Enables AI agents to create, edit, and query genealogical data from GEDCOM files. Supports complex genealogy searches, automatic data enrichment from web sources, relationship analysis, and biography generation for individuals and families. | |
| Agent Foyer aisa-team/agent-foyer An MCP server that lets agents act as the person who added them, giving them identity, shared context (data, documents, goals, calendar, skills), and a place to publish apps and pages behind sign-in. It also brokers access to models, data A | |
| SecOps MCP aisacadmin/secops-mcp2.0 Provides access to 13+ penetration testing and security audit tools through a unified MCP interface. Enables security professionals to perform vulnerability scanning, web fuzzing, network reconnaissance, and other security assessments throu | |
| yt-subtitle-mcp aisahpa/yt-subtitle-mcp Turns a YouTube link into a readable, timestamped Markdown transcript by preferring existing subtitles and falling back to local Whisper transcription, with optional Traditional-to-Simplified Chinese conversion and Obsidian-friendly output. | |
| google-ads-mcp aisandler/google-ads-mcp MCP server for Google Ads campaign reporting and management via Claude, enabling GAQL queries, performance metrics, and campaign modifications. | |
| Frame.io MCP aiscalestudio/frameio-mcp Connects Claude to Frame.io to pull transcripts, post frame-accurate comments, list comments, and upload attachments. | |
| HexStrike AI MCP Server aisecurityservices/hexstrike-ai Enables AI agents to autonomously run over 150 cybersecurity tools for penetration testing, vulnerability discovery, bug bounty automation, and security research through MCP. | |
| MCP Kali Server aisecurityservices/mcp-kali-server Exposes an API that lets MCP clients such as Claude Desktop or 5ire execute terminal commands on a Kali Linux machine, including offensive security tools like Nmap, sqlmap, Nikto, gobuster, Metasploit, Hydra, and John the Ripper. This enabl | |
| Knowledge Base MCP Server aisho-alex/knowledge_base_mcp Manages projects, requirements, and knowledge entries with full-text search via SQLite FTS5. Provides 19 MCP tools for AI assistants to create, update, search, and delete project data. | |
| Gmail MCP Server (Multi-User) aishu2508/mcp Multi-user Gmail MCP server that enables sending/receiving emails, managing accounts, and searching mail via SMTP/IMAP with per-user isolation and encrypted app passwords. | |
| safe-db-mcp aishwaryadv/safe-db-mcp Lets an MCP client query SQLite databases through validated, forced read-only, row-capped, time-limited and logged operations, so AI agents can explore data without risking writes or runaway queries. It also ships an eval harness that measu | |
| invoice-intake aishwaryamurali-bi/claude-invoice-intake Enables accounts-payable teams to turn emailed or uploaded invoice PDFs into structured, source-cited fields via Claude, run deterministic arithmetic, date, PO and duplicate checks, and route each invoice to a named human for approval or re | |
| summon-mcp aiskillhub/summon-mcp Self-evolving knowledge graph for AI agents — persistent memory that gets smarter with every interaction. | |
| thinqee aiskreme/thinqee An honest, cite-or-abstain persona engine that answers questions about a specific person based on a signed knowledge base, declining anything not in the notes. | |
| agent-memory-hub aisofialuz/agent-memory-hub Enables AI agents to store, search, and retrieve long-term memories with BM25 full-text search, auto-tagging, and importance scoring. | |
| ClickUp MCP Server aisprint/clickup-mcp-dist A self-hosted MCP server that enables AI agents to directly interact with your ClickUp workspace, including tasks, lists, folders, comments, time tracking, and more via 51 tools over SSE. | |
| srefix-diagnosis aisrefix-commits/srefix-diagnosis A toolkit of 256 MCP servers for SRE incident diagnosis with Claude. One agent per tech (Postgres, Kafka, Istio, Kubernetes, Prometheus, MongoDB, Redis, Cassandra,
...) with failure modes, key metrics, and runbooks baked in. Plus telemetry | |
| mcp_gmail_autosend aissam-salman/mcp_gmail_autosend Enables sending emails via Gmail API, checking thread replies, and listing sent emails, all logged locally in SQLite. | |
| hub-mcp aistartacademy/hub-mcp Enables an AI assistant to operate an academy hub through its authenticated internal API, covering cohorts and sessions, instructors, courses and media, CRM leads, drip email, memberships, and venue events. All writes are two-step: a dry ru | |
| lietuvos-viesieji-pirkimai-mcp aistasmendeika-max/lietuvos-viesieji-pirkimai-mcp Enables MCP clients to retrieve, search, and filter Lithuanian public procurement data from the official CVP IS API, returning original JSON for analysis and links to procurement searches. | |
| Poster MCP aistudy11/poster-mcp Enables AI assistants to obtain exact credit quotes, create posters after explicit approval, and retrieve owned results through Poster.sh. | |
| Muse Relay aisupplyguy/muse-relay Enables a Meta Muse agent and a Grok Bot to exchange questions, answers, and file attachments in both directions through stateless streamable HTTP MCP tools for sending messages, long-polling for incoming ones, fetching threads and attachme | |
| Digital Twin MCP Server aisystant/digital-twin-mcp MCP server for Digital Twin learner data, providing tools for AI Guide to explore metamodel and manage twin data with access control. | |
| pypddlengine ait-complex-dynamical-systems/pypddlengine Enables AI agents to interactively explore PDDL planning problems by exposing a PDDL engine as MCP tools for initialization, action execution, state inspection, and goal checking. | |
| canvas-scholar-mcp ait0u5hi/canvas-scholar-mcp Enables students to ask an AI assistant about their Canvas LMS data, including assignments, grades, missing submissions, discussions, and upcoming items, while keeping access read-only and private. | |
| RAGFlow MCP Server aitech-team/ragflow-mcp-server-continue Enables interaction with the RAGFlow API to manage knowledge base datasets and conduct AI-driven chat sessions. Users can list datasets, create chat assistants, and retrieve or query information from specialized knowledge bases. | |
| MCP Evolution API aiteks-ltda/mcp-evolution-whatsapp-api A Model Context Protocol server that enables Claude to interact with WhatsApp through the Evolution API, allowing for message sending, contact management, group operations, and WhatsApp instance administration. | |
| FreeRTOS Embedded Development MCP aitersmam888/freertos_mcp Enables automated generation of FreeRTOS embedded projects for chips like BK7252, STM32F4, and ESP32. Provides intelligent project structure creation, peripheral driver code generation, and complete embedded development workflows through na | |
| Awesome Linux MCP Server aitesthaj/awesome_linux_mcp Enables AI models to securely control remote Linux servers via SSH for command execution, file operations, and system monitoring, plus browser automation capabilities for web navigation, form interaction, and screenshot capture. | |
| awrelay aitherium/awrelay Enables agents to send and receive structured messages through an AitherRelay-shaped chat server, providing relay_send, relay_history, and relay_channels tools for inter-agent coordination. | |
| ForgePilot MCP aitherium/forgepilot A lightweight local MCP server that gives MCP hosts read-only tools for health checks, grounded web research, chat over trusted sources, and generation of portable client config snippets. It also exposes the aw* bootstrap plan and backend-s | |
| lemgen-ai-design-mcp aithink001/lemgen-ai-design-mcp Turns AI coding agents into visual creative assistants by providing a curated prompt gallery, prompt enhancement, and image/video generation via LemGen, with free inspiration tools and optional token-based generation. | |
| LocalPulse MCP aithx/localpulse-mcp MCP server for value-first cold outreach to local service businesses, enabling personalized cold email generation and lead scoring. | |
| Cinema4D MCP aitidi/cinema4d-agent Enables prompt-assisted 3D manipulation in Cinema 4D, including scene editing, object creation, animation, lighting, and material management, through MCP clients like ChatGPT, Claude, and Codex. | |
| Weather MCP Server aitiwari/weather Provides real-time US weather alerts and forecasts by integrating with the National Weather Service API. It enables AI assistants to fetch state-specific alerts and detailed local forecasts using geographic coordinates. | |
| poptarts-mcp aito-do/poptarts-mcp Provides a random Pop-Tarts flavor via an MCP tool or HTTP endpoint, with alternating 30-second delays to simulate long-lived requests. | |
| AKIMCP aito87/aki-mcp-sv Enables web-based AI chat clients and local IDEs to securely operate a user's own machine through one OAuth-gated MCP endpoint, exposing 38 governed tools for file read/write/edit, whitelisted shell commands, content search, Git, SQLite, br | |
| Pangle Coordinator aitools420/pangle-coordinator An MCP server for coordinating a permissionless swarm of AI agents to discover, investigate, and synthesize on-chain anomalies across EVM chains. Agents authenticate via off-chain ECDSA and earn reputation through useful contributions. | |
| twist-ai aitorcontrerasn/twist-ai-modificado-phi Enables AI agents to access and interact with a Twist workspace, including inbox, threads, conversations, search, replies, reactions, and completion actions. | |
| Wingate SEO MCP aitradesniper-blip/wingate-seo-mcp-public Enables natural-language, read-only analysis of your own Google Search Console and Google Analytics 4 data, including search performance, engagement, sitemap health, ranking opportunities, and deterministic SEO audits through MCP clients li | |
| scaffold-hbar-metered-mcp aitrailblazer/scaffold-hbar-metered-mcp Enables MCP clients to call free and paid tools, including account balance lookups, topic message reads, and echoes, on Hedera testnet. Each paid call settles in HBAR and writes a tamper-evident usage receipt to an HCS topic. | |
| moa365-mcp-proxy aitrendmaster/moa365-mcp-proxy MCP proxy server for Moa365 AI budgeting app, enabling expense recording, monthly summaries, and recent expense listing through natural language. | |
| AITuber MCP Server aituberapp/ai-video-mcp Create AI-powered videos from any MCP-compatible client. Generate videos with AI narration, visuals, and synced captions for short-form and long-form content. | |
| AgentKits Memory aitytech/agentkits-memory A local, persistent memory system for AI coding assistants that stores decisions, patterns, and session context via MCP tools. It enables cross-session memory management using SQLite and optional vector search without external dependencies | |
| mcp-hub aiua-dev/mcp-hub A lightweight control plane and local stdio agent that enables multiple MCP clients to connect to one local agent while configuration is managed from a remote control plane, supporting tool naming, exposure control, and multiple upstream so | |
| Knowledge Graph MCP Server aiuluna/knowledge-graph-mcp Enables creating, managing, analyzing, and visualizing knowledge graphs with support for multiple graph types (topology, timelines, changelogs, requirements, knowledge bases, ontologies) including node/edge management and resource associati |
25,251–25,300 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.