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 |
|---|---|
| Kanysh Basic almukhanomr/kanysh Enables users to connect their chat client to calculation tools for subsurface geological models, perform model checks and scenarios on exported Petrel/RMS data, and inspect reports and 3D scenes through a local viewer. | |
| TaskBridge almusalhaz1-ship-it/taskbridge Enables natural language task management via Claude, allowing users to add, list, and complete tasks stored in a local JSON file. | |
| claim alnaik/claim Returns a picture of the source page with a quoted passage highlighted—green for a full match, amber for partial, red if absent—so any AI-supplied citation can be checked at a glance. Works across PDFs, text and markdown files, CSV/TSV/XLSX | |
| mcPER alnasl-micro/mcper Enables AI assistants to look up Fiat, Lancia, Alfa Romeo, and Abarth ePER v84 parts data by VIN, resolve part-number supersessions, and view drawings with relevant parts highlighted. | |
| Maple alnosarus/copymaple A unified MCP server providing observability, safety control, and behavior evolution for high-agency AI agents through tracing, replaying, and auditing. It features real-time firewall guardrails and ML-driven anomaly detection to monitor, b | |
| PGEK-moodle-mcp alnyx-dev/pgek-moodle-mcp Enables AI assistants to access the Polotsk State Economic College Moodle platform, including course catalogs, course contents, modules, files, assignments, forums, and tests, using session or token authentication. | |
| IMAP MCP Server alobarquest/imap-mcp-server Enables Claude to read, search, send, and manage emails across multiple IMAP/SMTP accounts via a single deployment. | |
| InfraOps MCP Server alobarquest/infraops-mcp-server Enables infrastructure operations through Claude Code by exposing 195 tools across 7 providers including Coolify, VPS, Hetzner, Namecheap, Cloudflare, Supabase, and GitHub for server management, DNS, cloud resources, and more. | |
| Todoist MCP Server alobarquest/todoist-mcp MCP server that connects Claude to Todoist, enabling full CRUD operations on tasks, projects, sections, comments, and labels. | |
| Xploit47 aloc999/xploit47 AI-powered penetration testing reasoning engine (MCP server) for attack path planning, step scoring, and tool recommendations using Beam Search and Monte Carlo Tree Search. | |
| Top News MCP Server aloewright/top-news-mcp Enables fetching top headlines, searching news articles across 150,000+ sources, and listing available news sources via NewsAPI. | |
| openai-tool2mcp alohays/openai-tool2mcp A lightweight bridge that wraps OpenAI's built-in tools (like web search and code interpreter) as Model Context Protocol servers, enabling their use with Claude and other MCP-compatible models. | |
| Puch AI WhatsApp Integration MCP Server alok-ahirrao/puch-ai-whatsapp-integration-mcp-server Enables AI assistants to fetch web content, search for products on Google Shopping, and integrate with WhatsApp messaging. Serves as a bridge between Puch AI and external services through authenticated API endpoints. | |
| wpxmcp alokemajumder/wpxmcp Enables managing self-hosted WordPress sites from any MCP client, covering content, themes, plugins, menus, users, and SQL with credentials in Cloudflare Worker Secrets or local stdio. It provides 117 tools and adds guardrails like drafts, | |
| Expense Tracker MCP Server alokmishra1807/expense-tracker-mcp-server MCP server for tracking expenses with SQLite storage, enabling users to add, list, and summarize expenses by category. | |
| Statelessor MCP Server aloksinghgit/statelessor-mcp Analyzes .NET and Java projects to detect stateful code patterns and provides remediation guidance for migrating to stateless architectures. | |
| mcp alokverma18/mcp Provides MCP servers for GitHub API operations and SQL database queries, enabling users to interact with GitHub repositories and databases through natural language. | |
| MCP Python Learning Server aloladze88-afk/mcp-intro Provides tools to search and retrieve details of programming topics, and exposes a catalog resource for topic listings. | |
| Overboard Studio alona-iaig/overboard-claude-plugin Create visual whiteboards, diagrams, flowcharts, and project plans from AI conversations. 17 MCP tools for board management, element creation, and real-time collaboration. | |
| Overboard Studio MCP Server alona-iaig/overboard-mcp-server Enables AI agents to create and manage collaborative whiteboards with sticky notes, shapes, charts, and more, directly in Overboard Studio. | |
| robot-runtime alonbbar6/robot-runtime Enables agents to safely drive a simulated Franka Panda pick-and-place cell through MCP tools, with gated motion, emergency stop, structured errors, and audit logging. | |
| internet-radio alondrilich/72fm-radio-plugin Enables Claude to search the Radio Browser directory for live internet radio stations and return working stream URLs, supporting queries by country, genre, popularity, or specific station. | |
| opencli-mcp aloneatwar/opencli-mcp MCP server wrapping OpenCLI to let agents control a real Windows Chrome browser, reusing existing login sessions and extensions, with DOM/AX snapshot, action, and network capabilities. | |
| 1C Templates MCP Server alonehobo/1c_templates_mcp Provides storage, searching, and retrieval of 1C (BSL) code templates with a built-in web interface for easy template management. It enables AI assistants to fetch specific boilerplate code directly into editors using natural language searc | |
| Remote Coding Runtime aloneio/runmesh Enables MCP clients to safely access user-local filesystems, apply validated patches, inspect git state, and run persistent jobs on outbound-connected local runners through a stateless Cloudflare control plane. | |
| deepseek-harness-codex-bridge aloneswork/deepseek-harness-codex-bridge This MCP server enables Codex to delegate bounded subtasks to DeepSeek Harness through MCP, with persistent JSON mailbox messaging and proactive task initiation via Codex app-server. It provides tools for delegation, message exchange, and t | |
| Linux Diagnostics MCP Server alonf/mcppythondemo This MCP server provides read-only Linux system diagnostics tools for inspecting system information, processes, and log snapshots. It enables AI models to analyze Linux system health, troubleshoot issues, and review security through workflo | |
| RETRO MCP KALI alongbarbasumatary/retro-mcp-kali Enables AI assistants to run any Kali Linux tool or command over Streamable HTTP, supporting penetration testing, CTF challenges, and offensive security automation with full root access and async job handling. | |
| structured-extract-mcp alonsoalviraa/structured-extract-mcp Enables MCP clients to extract validated typed records from unstructured text using named schemas, with schema listing and extraction tools. It returns validated JSON or tool errors, optionally using an offline parser or an OpenAI-compatibl | |
| mx-postal-codes alonsomaciasm/codigos-postales-api Enables AI agents to query Mexican postal codes, validate addresses, and search settlements using natural language from the official SEPOMEX catalog. | |
| model-advisor-mcp alonsosg0/model-advisor-mcp Helps LLMs choose the best AI model for each coding agent by fetching real-time data from OpenCode subscriptions and matching with benchmarks and reasoning capabilities from OpenRouter. | |
| CountdownMCP alontsur1601/countdownmcp A local, read-only MCP server that gives Codex a plan-aware view of its remaining usage and helps choose work that fits the current usage window. | |
| TodoMCP alontsur1601/todomcp A local Model Context Protocol server that helps Codex turn requests into atomic tasks, manage plans, and rigorously verify completions without using any model API. | |
| Codex Memory MCP Server alooswr/codex_engineering-memory-mcp Local stdio MCP server for long-term engineering memory, enabling Codex to store, search, and manage project facts, progress, interfaces, and troubleshooting cases. | |
| Firmware MCP Server alooswr/firmware-mcp-server A local stdio MCP server for embedded firmware automation that exposes tools to build, flash, reset devices, and capture serial logs through a device configuration file. | |
| snipara-mcp alopez3006/snipara-mcp Snipara is the Project Brain for AI coding agents: a shared Project Intelligence layer for persistent context, reviewed memory, code impact, verification evidence, and handoffs through MCP. | |
| Outlook MCP Server alopezch21/outlook-mcp-server-temp MCP server that uses Microsoft Entra OAuth 2.0 On-Behalf-Of flow to access Microsoft Graph for Outlook data, enabling email, calendar, and contacts interactions via MCP tools. | |
| GitLab MCP Server alosies/gitlab-mcp-server A TypeScript MCP server that provides integration with GitLab's REST API, allowing users to interact with GitLab projects, issues, merge requests, pipelines, and more through natural language. | |
| wordpress-mcp aloudname/wordpress-mcp Enables Claude Code and Codex to manage WordPress posts and pages, query categories and tags, upload media, and convert Markdown to HTML or HTML to Markdown through a secure stdio MCP interface. | |
| tradingview-mcp aloysiusjs/tradingview-mcp Enables MCP clients to access market data from TradingView with automatic fallback to licensed providers, including symbol search, quotes, OHLCV history, technical indicators, and health checks. | |
| readeck-mcp alozur/readeck-mcp Enables AI agents to push generated HTML into a Readeck library with automatic LLM-based auto-labeling and to retrieve and read documents back, turning the library into a read/write knowledge base. | |
| five9-mcp alp-dev1710/five9-mcp Connects AI assistants to the Five9 cloud contact center, enabling them to manage campaigns, agents, IVR flows, and monitor call statistics through a secure, zero-dependency MCP server. | |
| Supabase MCP Server alpa-const/supabase-mcp Connects AI assistants to Supabase projects to manage databases, execute SQL queries, and handle project configurations. It enables tasks like table management, edge function deployment, and log retrieval through the Model Context Protocol. | |
| Dex MCP Server alpabon73/dex-mcp-server Provides AI agents with comprehensive contact relationship management (CRM) capabilities through the Dex API, enabling management of contacts, notes, and reminders. | |
| After Effects MCP Server alpacahq/after-effects-mcp Enables AI agents to control Adobe After Effects for project inspection, composition creation, and layer manipulation via a hardened bridge panel. | |
| alpaca-mcp-server alpacahq/alpaca-mcp-server Alpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs | |
| Alpacon MCP Server alpacax/alpacon-mcp Enables AI assistants to securely access and manage servers via Alpacon's zero-trust platform, allowing natural language command execution, file transfer, and monitoring without SSH keys or VPNs. | |
| ActiveDirectoryMCP alpadalar/activedirectorymcp A comprehensive MCP server for managing Active Directory environments through LDAP, enabling user, group, computer, and OU management, as well as security auditing and policy compliance checks. | |
| FortiGate MCP Server alpadalar/fortigate-mcp-server A production-ready MCP server for managing FortiGate firewalls, enabling AI assistants to manage firewall policies, network objects, routing, and device configurations. | |
| cpu3d alparn/cpu3d Enables AI agents to build and edit 3D scenes as safe JSON shape recipes over MCP, then render PNG views of their own work on a pure-JavaScript CPU rasterizer with no GPU or browser. Agents can add, update, and remove objects, place them vi |
26,801–26,850 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.