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 |
|---|---|
| Trello MCP dannbleeker/trello-mcp A personal remote MCP server that lets Claude read and update Trello boards, with safety guards and access control. | |
| tiktok-live-studio-mcp dannguyen9x/tiktok-live-studio-mcp A local MCP server for Windows that lets stdio MCP clients control TikTok LIVE Studio via its Socket.IO protocol, providing tools for scenes, sources, audio, recording, and LIVE actions. | |
| planner-mcp danniejwright/planner-mcp MCP server that turns planning documents into structured SQLite data and exposes plan metadata to AI agents, with tools to list and delete saved plans. | |
| DSH MCP Bridge dannndouglas/dsh-antigravity-acp Lets Google Antigravity's agent request tools that DeepSeek Harness validates, authorizes, and executes, covering files, commands, and installed extension tools, with the real result returned over the same ACP prompt. | |
| Multi-Memory MCP Server dannsk/multi-memory-mcp A knowledge graph memory server using SQLite to provide persistent, isolated contexts for organizing information into searchable categories like work and personal projects. It features unique ID-based operations and a token-efficient serial | |
| aws-security-mcp danntking/aws-ops-sec-mcp-seqtest A Model Context Protocol (MCP) server that enables AI assistants to perform comprehensive AWS security analysis through natural language queries, bridging AI with AWS security services. | |
| MCP Knowledge Base Server dannwaneri/mcp-knowledge-base-server Provides semantic search and data retrieval capabilities over a knowledge base with multiple tools including keyword search, category filtering, and ID-based lookup with in-memory caching. | |
| Vectorize MCP Server dannwaneri/vectorize-mcp-server Provides semantic search capabilities by connecting Claude Desktop to a Cloudflare Workers backend powered by Vectorize. It enables natural language querying of knowledge bases using vector similarity and edge-based embedding generation. | |
| Simple Streamable HTTP MCP Server danny-avila/example-mcp-server A reference implementation demonstrating proper MCP server patterns with HTTP transport, featuring session management, progress notifications, and example tools for testing server functionality. Serves as a clean template for building MCP s | |
| muse-code-bridge danny-hines/muse-code-bridge Enables Codex, ChatGPT desktop, Hermes, and OpenCode to invoke Muse Code as a collaborator through a local bridge, supporting subscription or pay-as-you-go API-key authentication for reviews, comparisons, and delegated implementation. | |
| mcp-cha-cha danny-sbr/mcp-cha-cha Enables managing a tea shop's menu and orders, including browsing drinks, placing and updating orders, and getting personalized drink recommendations. | |
| PayPal AI Billing MCP Gateway danny121583/paypal-ai-billing-kit Enables AI assistants to create and manage invoices, process sandbox payments and refunds, generate PDF receipts, and inspect transactions, subscriptions, disputes, and merchant insights through a unified tool gateway backed by PayPal Sandb | |
| Media Context MCP danny2708/media-context-mcp Enables text-only coding models to read images, PDFs, presentations, spreadsheets, and other non-text files through a single analyze_media tool, combining local document extraction, OCR, and optional vision models with clear evidence labeli | |
| MonadicSharp MCP Server danny4897/monadic-sharp-mcp Provides Claude with expert knowledge on MonadicSharp's Railway-Oriented Programming patterns and a tool to generate idiomatic code snippets. | |
| ISyMCP dannybaanks/chatgpt-http-mcp Turns a logged-in ChatGPT Web conversation into an OpenAI-compatible HTTP endpoint, letting any compatible client send chat completions and responses without an API key. Native tool calls tunnel back to the local MCP server and execute unde | |
| cognism dannybarr/cognism Enables AI agents to search, retrieve, and list 153 curated negotiation, persuasion, and leadership principles, each with its source, deployment steps, examples, and cautions. Grounds agent advice in a small vetted library of citable playbo | |
| groundstation dannybauman/groundstation Enables AI agents to query Earth observation data, satellite imagery, active fires, and weather via natural language, returning interactive maps and briefs. | |
| AI Context Manager dannybombastic/mcp-standard-ai Manages .ai/ workspace folder, syncs assets with a cloud service, and generates environment-specific bootstrap files for AI context management. | |
| technocore-mcp dannybyarun/technocore-mcp Enables AI assistants to interact with technocore.chat by reading and sending messages, listing rooms, managing key-value notes, searching messages, and checking server health. | |
| SalesDrive MCP Server dannychirkov/salesdrive-api Enables AI assistants to interact with SalesDrive CRM, allowing order management, product queries, and more through natural language. | |
| jira-mcp dannychou7911/jira-mcp Wraps Jira Data Center operations as MCP tools, enabling AI assistants to interact with Jira for project management and issue tracking. | |
| pokefinder-webmcp dannydev784/pokefinder-webmcp Enables deploying a JSON-RPC 2.0 MCP server on Cloudflare Workers and registering its tools in WebMCP-aware browsers via navigator.modelContext. It provides reusable server-side handlers and a browser-side client for tool discovery and invo | |
| MCP Arbitrage Suite dannyduo26/stock_arbitrage_notify_mcp An MCP server for QDII/LOF premium arbitrage, WeChat notifications, and A-share/futures market data, with Docker deployment support. | |
| Frappe MCP dannyfiallo030503/mcp-frappe Enables AI agents to explore and operate Frappe Framework, ERPNext, and HRMS sites at runtime by discovering installed apps, permission-visible DocTypes, schemas, records, child tables, reports, workflows, workspaces, print formats, files, | |
| Odoo MCP Server dannyg-sys/odoo-mcp-server Enables AI assistants to manage Odoo development environments by providing tools for server control, module management, database operations, and project navigation. | |
| Windows Semantic Bridge dannygi82/windows-semantic-bridge Enables MCP clients to observe Windows accessibility trees and deltas, generate fail-closed semantic action plans for external authorized executors, and control isolated, agent-owned Chrome tabs without accessing personal tabs. | |
| Agent Mission Control MCP Server dannyhawkins/agent-mission-control Enables Claude Code sessions to escalate decisions to a local mission-control hub through its request_decision tool, returning the operator's selected choice or typed answer straight back to the waiting tool call. | |
| Simple MCP Server dannyhertz/mcp-server A Python-based MCP server demonstrating tools for math calculations, time retrieval, and echo messages, along with resources and prompt templates. | |
| MCP Test Server dannyhertz/mcp-test-server A simple server for testing Model Context Protocol (MCP) that serves CSV and image resources, allowing developers to test MCP implementations with sample data via SSE transport. | |
| nameplate dannyheskett/py-nameplate Parses unstructured US contact strings into structured name and address components. Supports automatic detection of input type (name, address, or contact) and optional enhancement using a US street database. | |
| MVR dannyhoang249-hub/self-host-mcp-server-for-ai-video-reference-library A self-hosted MCP server for building a reusable AI-video reference library. It stores named Elements as structured reference images and provides them to MCP-compatible agents via @tags. | |
| qobuz-mcp dannyisyog/qobuz-mcp Connects your Qobuz account to Claude for music search, playlist management, favorites browsing, and streaming URL retrieval through natural conversation. | |
| sonarr-radarr-mcp dannyj/sonarr-radarr-mcp Enables AI assistants to manage TV shows and movies via Sonarr and Radarr, including searching, adding, and monitoring downloads. | |
| Afternote MCP Server dannykim32/afternote Enables Codex and Claude Code to save decisions, deadlines, and context into an encrypted local vault on macOS, then recall them later with citation to the exact note revision used. Grants are scoped, device-bound, and owner-approved via To | |
| EasyPanel MCP Server dannymaaz/easypanel-mcp Enables AI agents to manage infrastructure and deploy Docker services through EasyPanel using natural language commands. It supports full lifecycle management of services, deployments, and networks while facilitating automated scaling and a | |
| Edge DevTools MCP dannymaaz/edge-devtools-mcp Enables LLM agents to launch or attach to a Microsoft Edge session and drive it through a four-tiered tool set spanning navigation, clicking, typing, and token-efficient accessibility-tree inspection. Also exposes raw Chrome DevTools Protoc | |
| Memory MCP dannymaaz/memory-mcp Persistent project memory for AI models and coding agents. Memory MCP stores architecture, decisions, tasks, warnings, preferences, and session state in Supabase so OpenCode, Claude Code CLI, Qwen Code, Codex, or any MCP-compatible client c | |
| Topaz Video AI MCP Server dannymaaz/topaz-video-ai-mcp Connects AI assistants and agents to the Topaz Video AI engine so they can inspect frames, detect faces, pick optimal upscale models, preview and run headless background renders, and track job progress with anti-plastic photorealism presets | |
| MCP Think Tool dannymac180/mcp-think-tool An MCP server that implements the 'think' tool, providing Claude with a dedicated space for structured thinking during complex problem-solving tasks to improve reasoning capabilities. | |
| Gmail MCP Server dannymoons/mcp-gmail A Gmail integration for Cursor IDE that enables email management, collaborative drafting, and AI-powered email composition. | |
| Captivate MCP dannyoosterveer/captivate-mcp Enables MCP clients to read podcast shows, episodes, and listening analytics from Captivate.fm, including download trends, geographic and app breakdowns, and episode comparisons. It is read-only and does not modify or publish account conten | |
| gsheets-mcp dannyozh/gsheets-mcp Enables CRUD operations on your own Google Sheets, Docs, and Drive files through any MCP client, with a token-lean design using TSV output, server-side filtering, and config-driven sheet layouts. | |
| Pocketsmith MCP Server dannyshaw/pocketsmith-mcp Enables AI assistants to interact with the Pocketsmith personal finance API to manage accounts, budgets, and transactions through natural language. It supports comprehensive financial tasks including spending analysis, category management, | |
| MCP Multiagent Bridge dannystocker/mcp-multiagent-bridge Enables secure coordination between multiple LLM agents through authenticated messaging, status updates, and conversation management. Features automatic secret redaction, rate limiting, and audit trails for safe multi-agent collaboration in | |
| YouTube MCP Server dannysubsense/youtube-mcp-server A Model Context Protocol server that enables AI assistants to access YouTube data in real-time, with capabilities for searching videos, analyzing channels, retrieving video details, and extracting transcripts. | |
| second-opinion dannytrillion/second-opinion Evaluates proposed crypto trades against historical base rates and live order-book costs before Binance execution, returning APPROVE, CAUTION, or VETO decisions to guard against hallucinated trading rationales. | |
| @dannyvan/zentao-mcp dannyvan/zentao-mcp Enables reading, listing, searching, commenting on, and updating status of ZenTao bugs via its REST API, with write operations defaulting to dry-run. | |
| LaTeX Resume MCP dannywillowliu-uchi/resume_mcp Enables creating, editing, and compiling LaTeX resumes directly from Claude using built-in templates, with support for managing multiple resume files and automatic PDF generation. | |
| late-interest dannywolfoftech/late-interest Enables MCP clients such as Claude Desktop and Cursor to calculate UK statutory late payment interest and fixed compensation on business-to-business invoices, including unpaid ones, and to look up the applicable Bank of England Bank Rate on | |
| Real-time Stock MCP Service dannywongisavailable/real-time-stock-mcp-service Provides real-time stock market data and analysis from Chinese markets through 34 MCP tools, including K-line charts, technical indicators, fundamental analysis, financial metrics, and market insights without requiring authentication or API |
42,201–42,250 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.