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 |
|---|---|
| chuk-mcp-lazarus chrishayuk/chuk-mcp-lazarus Mechanistic interpretability MCP server wrapping chuk-lazarus, enabling model loading, activation extraction, probe training, steering, and ablation via MCP tools. | |
| CHUK Music MCP Server chrishayuk/chuk-mcp-music Enables AI-assisted music composition through copyable pattern templates, style constraints, and arrangement tools that compile to MIDI files. Provides 30+ tools for managing musical structures, layers, patterns, and styles with determinist | |
| chuk-mcp-s3-bucket-manager chrishayuk/chuk-mcp-s3-bucket-manager The CHUK MCP S3 Bucket Manager is a Python-based tool for managing Amazon S3 buckets using the MCP runtime. This utility provides a simple interface for listing, creating, and deleting S3 buckets. | |
| MCP Reference Server chrishayuk/chuk-mcp-server-reference A comprehensive reference implementation demonstrating all features of the Model Context Protocol (MCP) specification, serving as documentation, learning resource, and testing tool for MCP implementations. | |
| chuk-mcp-stage chrishayuk/chuk-mcp-stage Orchestrates 3D scene creation, camera paths, and physics-driven animations, bridging physics simulations with video rendering by defining scene graphs, binding objects to physics bodies, and exporting to React Three Fiber or Remotion. | |
| MCP Time Server chrishayuk/chuk-mcp-time-server A Python microservice that provides utilities for retrieving current times and converting between different global timezones with robust validation. | |
| MCP Code Sandbox Server chrishayuk/mcp-code-sandbox An extensible Message Communication Protocol server that provides secure code execution capabilities in isolated sandbox environments, compatible with Claude for Desktop and other MCP clients. | |
| mcp-local-llama chrishorne74/mcp-local-llama MCP server that delegates mechanical tasks like summarization, classification, extraction, and drafting to a local Llama.cpp LLM, serving as a cost-optimization layer while Claude handles reasoning and quality control. | |
| mcp-jev chrishow2/mcp-jev Enables MCP clients to get machine-readable yes/no, choice, and score decisions from TypeSafe Jev, bridging fast classification to Cursor and other clients. | |
| Endole MCP chrisjohnleah/endole-mcp Provides MCP clients with tools to search UK companies and retrieve Endole company data, including profiles, appointments, financials, group structure, CCJs, shareholders, credit scores, VAT numbers, and documents. | |
| suse-mcp chrisjohntapp/suse-mcp MCP server that bridges AI assistants with the SUSE Linux ecosystem, enabling safe access to openSUSE Wiki, OBS, and repositories for system management. | |
| TickTick MCP Server chrisjvanek/ticktick-mcp-ratv An MCP server that lets your AI assistant manage TickTick tasks, projects, habits, and more through natural language, supporting both TickTick and Dida365. | |
| Envoi MCP chriskoturathbun/envoi-mcp Provides AI agents with a real email address to send, receive, and manage emails via the Envoi.work platform. It enables seamless email communication, including inbox management and threaded replies, directly within MCP-compatible clients. | |
| PodHome MCP Server chrislas/podhome-mcp An MCP server that integrates with the Podhome API to manage multiple podcast shows. It enables users to create and schedule episodes, generate clips, and manage webhooks through natural language commands. | |
| driftless chrislee121/driftless-registry Enables querying and retrieving public design styles from the Driftless registry, including listing, searching styles, and fetching design markdown and tokens. | |
| MCP Server Boilerplate chrisleekr/mcp-server-playground A comprehensive Model Context Protocol server template that implements HTTP-based transport with OAuth proxy for third-party authorization servers like Auth0, enabling AI tools to securely connect while supporting Dynamic Application Regist | |
| expense-tracker chrislfmd/expense-tracker-mcp-claude Enables tracking business trip expenses and calculating settlements using Google Sheets, with natural language parsing of expenses. | |
| claude-subagent-mcp chrisliebaer/claude-subagent-mcp Provides structured access to Claude Code agent log files, allowing agents to query assistant lines and tool calls without reading raw JSONL data. | |
| Trello MCP Server chrislochhead/trello-mcp-server Enables Claude to manage Trello boards, lists, cards, labels, and checklists via the Trello REST API, allowing natural language task management. | |
| sonic-net-debugger chrisma113/sonic-net-debugger An MCP (Model Context Protocol) server for debugging and interacting with SONiC (Software for Open Networking in the Cloud) network devices (DUTs). | |
| PubMed MCP Server chrismannina/pubmed-mcp A comprehensive Model Context Protocol server that enables advanced PubMed literature search, citation formatting, and research analysis through natural language interactions. | |
| claude-journal chrismbryant/claude-journal-mcp A lightweight journal/memory system for Claude Code with no ML dependencies, using SQLite for fast local storage. | |
| prlt chrismcdermut/proletariat Enables AI agents to orchestrate development tasks by creating tickets, spawning isolated worker agents, and managing multi-agent workflows through the Proletariat platform. | |
| CaseClerk chrismeyersfsu/caseclerk MCP server that indexes and searches law firm case documents and drafts Outlook-ready emails, scoped to one client and case at a time. | |
| SuperDB MCP Server chrismo/superdb-mcp Enables AI assistants to execute SuperSQL queries on data files and SuperDB databases without shell escaping issues. Supports querying, schema inspection, database pool management, and provides LSP features for code completion and documenta | |
| atlas-social-mcp chrismole310/atlas-social-mcp AI-powered social media posting across 14 platforms. Post to Twitter, Instagram, TikTok, Facebook, LinkedIn, YouTube and more with one command. AI adapts content per platform, schedules posts, and generates 30-day content calendars. | |
| SolidWorks MCP chrisncm17/solidworks-mcp Enables AI agents on Windows to build parts from JSON recipes, create and verify whole assemblies in a single call, check mass, center of mass, mates and interference, produce drawings with BOM, balloons and sections, work with sheet metal, | |
| google-cli-mcp chrisnoronha/google-cli-mcp An MCP server that exposes 17 Google Workspace APIs (e.g., Gmail, Drive, Calendar) as auto-generated tools for AI assistants, enabling natural language control of Google services. | |
| Zenith Bridge chrisp671/zenithbridge An Obsidian plugin that provides embedded AI agent terminals and an MCP server for connecting Claude Code and other clients to your vault. | |
| warriorgpt-mcp chrispelzer/claude-warriorgpt-mcp Exposes a single ask_warriorgpt tool that lets Claude Code delegate self-contained code generation prompts to Wayne State's hosted model API, passing files to and from disk so the content never counts against the Claude plan. It validates m | |
| fifa-public-api-mcp chrispickford/fifa-public-api-mcp Enables querying FIFA competitions, fixtures, results, and live match data through the FIFA Public API without authentication. | |
| Standup MCP Server chrisprobably/standup-mcp Connects AI coding agents to the Standup kanban app so they can list boards, read and create cards, move cards between columns, manage assignees, and post comments through natural conversation. | |
| ui-gen-mcp chrisregis100/ui-gen Enables coding agents to initialize a project and generate, add, or list React + TypeScript + Tailwind components directly within the project. | |
| simple-memory-mcp chrisribe/simple-memory-mcp Provides AI assistants with persistent memory across sessions using local SQLite and keyword search, allowing storage and retrieval of user preferences, project context, and decisions. | |
| TextWeb chrisrobison/textweb Renders web pages as structured text grids for AI agents to browse and interact with, preserving spatial layout without screenshots. | |
| ArchHub MCP chrisryugj/archhub-mcp Enables natural language access to 11 Korean building data tools including building registers, permits, comprehensive profiles with zoning, floor composition, district statistics, old building analysis, price history, demolitions, and permi | |
| Korean DART MCP chrisryugj/korean-dart-mcp Provides 15 tools covering OpenDART 83 APIs for disclosures, financials, equity, XBRL, plus insider signals, accounting risk scores, and Buffett-style quality checklists, and converts HWP/PDF attachments to markdown for AI assistants. | |
| Korean Patent MCP (KIPRIS) chrisryugj/korean-patent-mcp MCP server that enables searching Korean patents, trademarks, and designs via KIPRIS Plus open APIs. Supports keyword, advanced, applicant, and rightholder searches with detailed bibliographic lookup. | |
| Swizzler MCP chrisscott/swizzler-mcp Provides read-only access to a personal cocktail library stored in a synced on-device snapshot, letting AI assistants search recipes by name, ingredient, spirit, or collection, retrieve full drink specs, list collections, determine which dr | |
| Guitar Tone Assistant chrissdks/tone3000mcp Enables searching TONE3000 captures and cabinet IRs, designing AmpliTube 5 MAX rigs, and getting tone recommendations and troubleshooting through natural language. | |
| agent-ready chrissgon/agent-ready-kit Serves a site's validated public profile, product list and newest-first posts to AI agents through three read-only tools (get_profile, list_products, list_posts) over stdio or any Web Request/Response runtime. | |
| perfectui-mcp chrissgon/perfectui-mcp Enables coding agents to retrieve Perfect UI 1.0.0's real classes, markup, and install instructions, search documentation, and validate generated HTML for unknown or legacy pui-* classes. | |
| extrapify christ0pper/extrapify-mcp Structured web context infrastructure for AI agents. Extract reliable schema-guided JSON from websites using Claude-powered parsing, Browserless fallback rendering, and MCP-native workflows. | |
| illustrator-mcp christancho-co/illustrator-mcp Enables AI assistants to control Adobe Illustrator on Windows, including creating, opening, saving, and exporting documents, drawing shapes, adding text, and running arbitrary ExtendScript. | |
| solidworks-mcp christancho-co/solidworks-mcp Enables building and modifying parametric solid models in a local SOLIDWORKS installation via the COM API. | |
| unreal-mcp christancho-co/unreal-mcp Enables Claude to control a running Unreal Engine editor via Epic's Python Remote Execution protocol, supporting asset import, actor manipulation, viewport screenshots, and arbitrary Python execution. | |
| brand-asset-mcp christansey007/brand-asset-mcp A shareable, lightweight MCP server for managing corporate brand assets, logos, color design tokens, social media templates, and image watermarking across multiple locations and platforms. | |
| axsquiggle christaylor98/axsquiggle Lets AI clients draft, inspect, edit and review wireframe/storyboard boards over MCP, sharing one live board with the app the user has open. It also supports loading boards back, resolving review notes, and exporting realistic previews so s | |
| OHADA MCP christchad-mv/ohada-mcp-server A public MCP server for OHADA legal research, enabling search of relevant provisions, retrieval of full articles with hierarchical context, and citation verification. | |
| five9-mcp christenbergarw/five9-mcp Connects AI assistants to Five9 cloud contact center, enabling management of campaigns, agents, call logs, and more through natural language commands. |
38,651–38,700 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.