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 |
|---|---|
| toolknit-mcp dawn-1029/toolknit-mcp Enables converting local files among Word, PDF, image, and HEIC formats via headless Microsoft Edge, with conversion performed client-side so files never leave the machine. Provides tools to list supported conversions and convert files, ret | |
| Fusion Native MCP dawn-of-justice/fusion-native-mcp Enables MCP-compatible assistants to control Autodesk Fusion for mechanical modeling, assembly editing, CAM workflows, inspection, and model export through Fusion's native MCP endpoint. | |
| AFFiNE MCP Server dawncr0w/affine-mcp-server Enables interaction with AFFiNE workspaces through GraphQL API to manage documents, search content, handle comments, and access version history. Supports comprehensive workspace operations including document publishing, comment management, | |
| ENSP-MCP AI dawnight0x/ensp-mcp Enables AI clients to manage Huawei eNSP simulated network devices, execute CLI commands, apply configurations, and perform network diagnostics through natural language, with topology upload and visualization via a web UI. | |
| DawnMCP dawnmcp/dawnmcp-1 A fully local, privacy-first MCP server that gives AI coding assistants deep repository intelligence with file-and-line-cited answers, persistent semantic memory, and agentic abilities like task planning and code review—all without any clou | |
| Eye of Sauron - Discord Bot MCP dawnreaverwows/thefinaldiscordmcp Enables AI assistants to control Discord servers with 93 tools for server management, moderation, voice TTS, AI chat via OpenRouter, and World of Warships stats lookup through the Model Context Protocol. | |
| Domo MCP Server dawoodali-showpass/domo-mcp-server Connects to Domo API to run SQL queries, search datasets, retrieve metadata and schema, and manage roles. | |
| pgnify dawsonbooth/pgnify Enables an AI assistant to convert PDF and EPUB chess books into faithful PGN by reading pages and diagrams, validating moves with python-chess, preserving variations and commentary, and reporting verifiable issues. | |
| xiaoliu-mcp-guardian daxiak001/rursor-mcp This MCP server intercepts and modifies Cursor AI behavior to enforce continuous execution, auto-confirm actions, log experiences, and prevent dangerous commands, aiming to automate development tasks and reduce interruptions. | |
| Cocos Creator MCP Server Plugin daxianlee/cocos-mcp-server A comprehensive plugin that enables AI assistants to interact with the Cocos Creator editor through the Model Context Protocol, providing 80 tools across 9 categories for nearly complete editor control. | |
| alignment-correction-mcp daxiongmao87/alignment-correction-mcp An MCP server that acts as an external conscience for AI agents, using Gemini or OpenAI APIs to validate plans, enforce behavioral rules, and maintain memory of past interactions to ensure alignment with user intent. | |
| Redmine MCP Server daxonet/redmine_mcp Exposes Redmine data to MCP clients through OAuth 2.1 authentication, enabling AI agents to manage projects, issues, and time entries. It supports a variety of operations including issue creation, full-text search, and time logging via a se | |
| superproductivity daxrpm/superproductivity-mcp-offline Enables AI assistants to read and write Super Productivity tasks through the Nextcloud sync file, preserving local-first data and safely handling concurrent edits from other devices. | |
| mcp-graph-me-tool day0ops/mcp-graph-me-tool Enables MCP clients to fetch the signed-in Microsoft Entra user's profile from Microsoft Graph via the GET /me endpoint using the provided bearer token. | |
| AMAP MCP Server day2586/travelplanner-agent Provides real-time weather, points of interest with coordinates, and nearby restaurant data from AMAP to support intelligent travel itinerary planning through natural language. | |
| InfiniteMCP day50-dev/mcp-search-and-run A meta-MCP server that acts as a universal gateway, allowing users to discover and execute tools from thousands of other MCP servers through semantic search. It dynamically loads servers on demand and provides standardized functions for sea | |
| Genesis MCP Server day7-engineering/genesis-mcp-server A template for deploying remote MCP servers on Cloudflare Workers without authentication. Provides a foundation for building custom MCP tools that can be accessed from Claude Desktop or the Cloudflare AI Playground. | |
| Mind Guide MCP dayainow/mind-guide-mcp Connects users to mental health counseling centers and welfare programs based on location and situation, prioritizing crisis resources. | |
| Salesforce MCP Server dayal-arnav05/salesforce-mcp-ts Enables natural language interactions with Salesforce, allowing users to query and modify data, manage custom objects and fields, execute Apex code, and perform SOQL/SOSL searches across Salesforce organizations. | |
| Claude–Codex Session Link dayc-l/claude-codex-session-link Enables Codex to list and read saved Claude Code conversations, retrieve incremental context updates before replies, and optionally ask Claude text-only follow-up questions within a selected session without disrupting the workflow. | |
| Task Orchestrator MCP Server daymanking990/task-orchectrator-mcp A sophisticated task orchestration system with role-based workflow management and Trello integration. | |
| renderping daymondhyper/renderping Enables AI agents to render website screenshots and PDFs, check page changes, and retrieve usage stats via REST calls. | |
| Post For Me MCP Server daymoondevelopment/post-for-me-typescript Enables AI assistants to interact with the Post For Me API, allowing them to explore endpoints, make test requests, and use documentation to help integrate this SDK into your application. | |
| MCP S3 File Uploader dayongd1/mcp-s3 Enables secure file uploads to Amazon S3 with progress tracking and presigned URL generation. Provides automatic UUID-based file naming and time-limited access URLs for uploaded files. | |
| MCP Veo 3 Video Generation Server dayongd1/mcp-veo3 Enables video generation from text prompts or images using Google's Veo 3 API. Supports multiple models, audio generation, and various aspect ratios for creating high-quality videos. | |
| OpenDART MCP Server dayoooun/dart-mcp Provides AI assistants with real-time access to Korean listed companies' disclosures, financial statements, and corporate information via the DART API. | |
| HWPX MCP Server dayoooun/hwpx-mcp Enables AI models to read, create, and edit Korean HWPX documents with advanced support for tables, paragraphs, styles, and images. It features enhanced stability through atomic file writing and smart layout recalculation to prevent documen | |
| Korea Stats MCP dayoooun/korea-stats-mcp Enables natural language querying of Korean statistical data from KOSIS, including population, employment, GDP, housing prices, and more, with support for regional and trend analysis. | |
| Atlassian Rovo MCP for Microsoft Copilot Cowork dayour/atlassian_cowork Provides Jira project-tracking skills and dynamic client registration to connect Atlassian services with Microsoft 365 Copilot Cowork. | |
| PowerPlatform MCP Server dayour/powerplatform-mcp Provides intelligent access to PowerPlatform/Dataverse entities and records, enabling entity metadata exploration, OData querying, relationship mapping, and AI-assisted query building through MCP. | |
| next-ai-drawio dayuanjiang/next-ai-draw-io Lets Claude Code, Cursor, VS Code and other AI agents draw and edit draw.io diagrams from your project's files, on a live browser canvas you can also edit by hand. Includes version history, undo, cloud shape libraries (AWS, Azure, GCP) and | |
| spectatty dayvidwang/spectatty Enables AI agents to spawn and interact with real terminal sessions, capturing screenshots of rendered TUI output and sharing live sessions for debugging. | |
| pluggy-mcp-br dayvison2b/pluggy-mcp-br Enables read-only access to Brazilian Open Finance banking data through Pluggy, allowing queries of accounts, balances, transactions, card bills, category spending, and connection status. | |
| cafes dayvough/opencode-mcp Enables querying saved BGC café records through a validated search tool that filters branches by Wi-Fi, customer power outlets, and required drinks, returning only supported matches with their sources and dates while keeping unknowns separa | |
| ispconfig-mcp dayzander/ispconfig-mcp MCP server for managing ISPConfig 3 hosting platform - enables DNS, mail, websites, databases, FTP, cron jobs, and client management through AI assistants. Supports server migration with export/import of configurations. | |
| @ztechlab/mcp-server-yubikey dazaffino/mcp-server-yubikey MCP server that exposes read-only YubiKey management tools (info, FIDO2, PIV, OpenPGP, OTP) to AI agents via the ykman CLI. | |
| transcribe-youtube-mcp dazamate/transcribe-youtube-mcp Enables Claude to fetch the spoken text of YouTube videos from any URL or video ID, listing available captions and languages and paging through long transcripts. It also handles proxy configuration to work around YouTube IP blocks. | |
| Copper MCP dazanza/copper-mcp An MCP server that provides an interface to the Copper CRM API for managing contacts, companies, activities, and opportunities. It enables users to search for people, log meetings or notes, and track sales deals directly through MCP-compati | |
| mailchimp-mcp dazanza/mailchimp-mcp An MCP server that interfaces with the Mailchimp Marketing API to manage audiences, email campaigns, and subscribers. It enables users to create and schedule campaigns, handle member lists, and send test or live emails through natural langu | |
| Cline Memory Bank dazeb/cline-mcp-memory-bank A Model Context Protocol server that provides persistent project context management for AI-assisted development, specifically designed for the Cline VSCode Extension. | |
| Enhanced Coolify MCP Server dazeb/coolify-mcp-enhanced A powerful Model Context Protocol server that enables AI assistants to manage Coolify infrastructure through natural language, supporting application deployment, database management, resource monitoring, and DevOps automation. | |
| Markdown Downloader dazeb/markdown-downloader An MCP server that enables users to download webpages as markdown files using r.jina.ai service, with features for configurable download directories and automatic date-stamped filenames. | |
| GitHub Mapper MCP Server dazeb/mcp-github-mapper Provides tools for mapping and analyzing GitHub repositories. It allows users to set a GitHub Personal Access Token and retrieve detailed information about a specified repository, including its structure and summary statistics. | |
| MCP Handoff Server dazeb/mcp-handoff-server Facilitates seamless collaboration between AI agents by providing tools for structured task handoffs, progress tracking, and documentation management. It allows agents to create, update, and archive handoff documents to ensure continuity ac | |
| Component Harvester MCP Server dazeb/mcp-react-component-harvester Harvests React components from Aceternity UI and Shadcn UI, fetching code and metadata to generate integration prompts for AI agents. | |
| wikipedia-mcp-image-crawler dazeb/wikipedia-mcp-image-crawler Enables searching and retrieving images from Wikipedia Commons with detailed metadata including licenses and authors. | |
| easy-codex-mcp dazebug/easy-codex-mcp Lets MCP-compatible AI assistants have read-only conversations with OpenAI Codex CLI for code analysis, review, and Q&A. | |
| Agent Router MCP dazhi666666/agent-router-mcp Lets any MCP-capable agent client join a shared local collaboration space with a common task board and mailbox, so agents can publish, claim, and track tasks with dependencies and message each other or the human. It supports an equal-peer m | |
| ChatGPT Escalation MCP Server dazlarus/chatgpt-escalation-mcp Enables autonomous coding agents to escalate complex technical questions to ChatGPT Desktop app via ToS-compliant UI automation, returning expert responses automatically without user intervention. | |
| Tifa dazyoung/tifa Enables AI assistants to query live London rail line status and the recorded history of disruptions, including filtered episodes, causes, period statistics and coverage gaps, through seven read-only tools. |
42,901–42,950 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.