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-Orchestrator 4il228/orchestrator-mcp Manages AI agent workflows through a state machine and Git branches, enforcing isolated phases and audit trails via SPEC, PLAN, and AGENTS files. | |
| mcp-postgres 4l3x31s/mcp-postgresql Enables agents to inspect PostgreSQL schemas, run read-only queries and explain plans, and, when explicitly permitted, execute writes and DDL on a per-project database with layered safety controls. | |
| UniMCP 4lexxe/mcp_unju Connects AI agents to Argentine university systems so they can browse Moodle virtual classrooms, read course materials and forum discussions, search across courses, and consult SIU Guaraní academic records such as grades, enrollments, and e | |
| UniMCP 4lexxe/unju_mcp Enables agents to access Moodle virtual classrooms and SIU Guaraní for Argentine universities, including reading course materials, searching discussions, checking grades and academic status, and, with confirmation, posting to forums or subm | |
| Understand-Anything MCP Server 4nden/understand-anything-mcp This MCP Server bridges Egonex-AI/Understand-Anything with Claude Desktop and other MCP clients, giving LLMs native access to full-codebase structural graphs, architecture analysis, and CI/CD validation. | |
| iMessage MCP 4ndylg/imessage-mcp Read-only MCP server for local macOS Messages database, enabling querying of chats, messages, attachments, and metadata. | |
| vikunja-mcp 4nm1tsu/vikunja-mcp Enables AI assistants to interact with Vikunja task management instances, providing full task, project, label, and user management capabilities. | |
| spoooler 4nw3rprod/spoooler Enables local-first Instagram reel production entirely over MCP, turning raw footage, URLs, or topics into finished reels with script generation, stock media, voiceover, and captions. | |
| FastMCP ThreatIntel 4r9un/fastmcp-threatintel Enables AI-powered threat intelligence analysis of IPs, domains, URLs, and file hashes across multiple threat intelligence platforms (VirusTotal, AlienVault OTX, AbuseIPDB, IPinfo) with APT attribution and interactive reporting through natu | |
| MCP KQL Server 4r9un/mcp-kql-server Enables intelligent KQL query execution against Azure Data Explorer clusters with AI-powered schema caching and natural language to KQL conversion. Provides automated schema discovery and context-aware query assistance for enhanced data exp | |
| agent-rules-mcp 4regab/agent-rules-mcp MCP server that enables your agents to use coding rules from any or your GitHub repository. Instead of workspace rules files, you can now prompt agents to access the your coding rules from any repository. | |
| tasksync-mcp 4regab/tasksync-mcp MCP server to give new instructions to agent while its working. It uses the get_feedback tool to collect your input from the feedback.md file in the workspace, which is sent back to the agent when you save. | |
| DSpace MCP Server 4science/dspace-mcp Enables AI assistants to search, authenticate, and manage digital repository content through the REST API, including creating, updating, and deleting items, uploading file attachments, running workspace submissions, and browsing communities | |
| ytm-mcp 4shil/ytm-mcp A full-featured YouTube Music MCP server that lets AI assistants control playback, browse history, download songs, and manage playlists via natural language. | |
| MCP Google Contacts Server 4tal/mcp-google-contacts Provides comprehensive Google Contacts management including creating, searching, and updating contacts with 25+ fields, managing contact groups, and accessing Google Workspace directories. | |
| MJC MCP Server 4this/hackathon_mjc_mcp MCP server enabling AI assistants to query Myongji College data, including real-time library seat availability, campus notices, department lists, and course search (with user login). All tools are read-only and can be composed to answer com | |
| Lightroom Classic MCP 4xiomdev/lightroom-classic-mcp Enables AI agents to control Adobe Lightroom Classic on macOS for professional photo editing and catalog management. It allows users to inspect photos, apply develop settings, and automate workflows through a secure local bridge without dir | |
| MCP Time Server 501336north/oss-mcp-time A hosted MCP server providing current time, date, and timezone conversion tools specifically designed for Claude Code remote sessions. It enables users to fetch localized time data and convert times between IANA timezones through a centrali | |
| DocumentKit 504532934/documentkit Enables AI clients to render any URL or raw HTML into PDF files or PNG/JPEG/WebP screenshots over MCP stdio or Streamable HTTP. Output stays in memory with SSRF protection, bounded concurrency, and configurable size and timeout limits. | |
| dsh-document-editor 506058115-cmd/dsh-document-editor Enables creating, reading, editing, and verifying PDF, Word, Excel, and PowerPoint documents through MCP tools that return structured results. It preserves source files by default for edits and supports local stdio operation without network | |
| 心知天气 MCP Server 508364/xinzhi-weather-mcp Enables real-time weather queries for 400+ cities in China through the Seniverse Weather API. Provides secure weather data access with HMAC-SHA1 authentication and full MCP protocol compatibility. | |
| second-brain-worker 50r1paps/second-brain-worker Provides tools to retrieve, ingest, and reindex a serverless personal knowledge base built from Obsidian wiki and external files, with hybrid semantic + keyword search via the Model Context Protocol. | |
| kr-public-data-mcp 50seok/kr-public-data-mcp Enables Claude Code to query real-time Korean weather, air quality, and monitoring station information through natural language, using public data APIs with caching and error handling. | |
| User MCP Demo 511easy/my-mcp-user MCP server demonstrating Streamable HTTP with Tools, Resources, and Prompts for user registration, login, and profile management via a REST API. | |
| IoTaWatt MCP Server 519green/iotawattmcp Lets an MCP client read live power from a local IoTaWatt energy monitor over its HTTP API, query history logs for energy and interval data, inspect device configuration and channel definitions, and sample current waveforms to identify load | |
| frontier-mcp 51ck/frontier-mcp An MCP server that exposes the markdown issue tracker under .scratch/ as a queryable graph, letting agents see open, blocked, or takeable issues without re-parsing prose. | |
| codex-creo-mcp 520-ym/codex-creo-mcp Enables Codex to read and modify an active Creo Parametric session on Windows through a Node.js MCP service and Pro/TOOLKIT bridge, providing 60 tools for model inspection, parameters, dimensions, features, assemblies, sheet metal, STEP exp | |
| worktree-map 520wheat/worktree-map MCP server that visualizes git branch genealogy and worktree locations within a repository, marking the current session position. Supports creating branches/worktrees, safe deletion/cleanup, and session navigation with fallback guidance. | |
| AgentBridge 5258mf/agentbridge Expose your VS Code workspace's tools — files, terminal, LSP, diagnostics, and images — to remote MCP clients over a public HTTPS tunnel. | |
| Backpack Battles MCP 53721222-gif/mcpbpb Enables LLM clients to inspect live game state and perform deterministic shop, inventory, backpack layout, and combat actions in a running game through a local bridge. | |
| SEBI Compliance MCP System 53rao/sebi-research-analyst-compliance-mcp A deterministic regulatory compliance evaluation system for SEBI Research Analyst regulations, exposing MCP tools to check compliance, get applicable rules, and retrieve audit logs. | |
| Anki MCP Server 54334-bit/anki_mcp_server Enables AI assistants to interact with Anki through the Model Context Protocol, allowing natural language creation, editing, and review of flashcards, deck management, and media handling. | |
| cumcm-rag-mcp 54334-bit/cumcm-optimization-rag Provides read-only RAG retrieval, document access, source auditing, status, and health checks for CUMCM optimization and decision modeling contexts. | |
| mcp-china-ecosystem 543366565/mcp-china-ecosystem Bridges AI agents to Chinese internet services like Baidu, Bilibili, and Chinese web page extraction without requiring API keys. | |
| tavily-search 543366565/mcp-tavily-search Enables AI agents to perform real-time web searches and extract clean, LLM-readable content from URLs using the Tavily API. | |
| ctxray 54615616/ctxray Enables AI coding agents to compile repositories into high-signal, cache-pinned context and to query dependency centrality, blast radius, AST skeletons, circular dependencies, hotspots, and auto-generated agent rules through MCP tools. | |
| MCP-for-Stata 54cwh/mcp-for-stata-wine Enables AI agents to invoke a local Stata installation, including a Windows Stata build under Wine on Linux and macOS, for regression analysis, econometrics, paper replication, and empirical research with command guards, resource monitoring | |
| Kylin Offline MCP ECharts 54dabang/kylin-arm64-64kb-page-size-mcp An MCP server for generating offline charts using Apache ECharts SVG SSR and rsvg-convert, optimized for Kylin ARM64 with 64KB page size. | |
| Container-MCP 54rt1n/container-mcp A secure, container-based implementation of the Model Context Protocol (MCP) that provides sandboxed environments for AI systems to safely execute code, run commands, access files, and perform web operations. | |
| code-mcp 54yyyu/code-mcp Enables Claude AI to run terminal commands, perform file operations, and manage git in a project directory via the Model Context Protocol. | |
| Kaggle-MCP 54yyyu/kaggle-mcp Connects Claude AI to the Kaggle API through the Model Context Protocol, enabling competition, dataset, and kernel operations through the AI interface. | |
| PyApple MCP Tools 54yyyu/pyapple-mcp Provides seamless integration with macOS native applications including Messages, Notes, Contacts, Mail, Reminders, Calendar, and Maps, enabling natural language control and automation of Apple ecosystem apps. | |
| School MCP 54yyyu/school-mcp A Model Context Protocol server that helps students manage academic workflows by integrating with Canvas and Gradescope to fetch deadlines, download course materials, and sync with macOS Calendar or Reminders. | |
| naukri-mcp 556harishagarwal/naukri-mcp Enables automation of your own Naukri.com account for job search, job details, applications, saved jobs, profile viewing, and recruiter messaging through MCP-compatible clients. | |
| Cocos Creator MCP Server 557888-pixel/l1_n8n_cocos-mcp-server Enables AI assistants to interact with the Cocos Creator 3.8+ editor through standardized protocols for scene, node, component, prefab, asset, project, debugging, and server operations. | |
| Game Logs MCP Server 557888-pixel/l1_n8n_mcp-server-demo Retrieves game logs from the Lumigame platform, including recent logs and sign-in logs, with optional filtering by player ID. | |
| PD2 Lua MCP 55jrmds/pd2luamcp Provides LLMs with access to Payday 2 Lua documentation and source code via 7 MCP tools, enabling precise mod development queries. | |
| codefactor-mcp 5656565566/codefactor_mcp Enables reading and analyzing CodeFactor repository issue pages, providing normalized issue data, summaries, and prompts for code improvements. | |
| mcp-local-sandbox-cleaner 571242/mcp-local-sandbox-cleaner Enables AI coding agents to audit and sweep away transient scratch directories, bloated test caches, and forgotten probe scripts in a workspace, with dry-run previews to guarantee nothing tracked or production-related is touched. It also de | |
| Notion MCP Server 589411/notion_mcp_connection Enables interaction with Notion workspaces through the Notion API. Provides tools to search, read, create, and update Notion pages and databases with real-time synchronization. |
22,201–22,250 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.