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 Hello World Server 9kubczas4/mcp-app-angular-boilerplate A minimal MCP server that exposes a 'say_hello' tool and serves an Angular UI as an MCP App resource, demonstrating the MCP App architecture. | |
| MCP Notes 9ninety/mcpnotes A simple note-taking MCP server for recording and managing notes with AI models. | |
| MCP Server Pentest 9olidity/mcp-server-pentest A security testing tool that enables automated vulnerability detection including XSS and SQL injection, along with comprehensive browser interaction capabilities for web application penetration testing. | |
| Weather MCP Server 9renbufu/mcp_server Provides real-time weather information for global locations and 12 major Chinese cities using the wttr.in API. It enables users to query temperature, humidity, and atmospheric conditions through the HelloAgents framework. | |
| Daemon-MCP 9thlevelsoftware/daem0n-mcp Daem0n-MCP provides AI agents with persistent, semantically indexed memory to track decisions, rules, and outcomes across sessions. It actively prevents repetitive mistakes by enforcing context checks and prioritizing information about past | |
| tesseract-26-eyeshot-mcp a-001-byte/tesseract-26-eyeshot-mcp Enables AI-driven CAD operations through natural language, integrating LLM and Eyeshot SDK for model manipulation. | |
| Canvas MCP a-ariff/canvas-mcp A local MCP server for Canvas LMS that enables querying courses, assignments, grades, modules, and more from any MCP-compatible AI client. | |
| MCP Chat a-bdullah-khan/cli-based-mcp-server-chatbot Enables interactive AI chat through the Anthropic API, with document retrieval, slash commands, and extensible MCP tool integrations. | |
| Claude MCP x Google Docs a-bonus/google-docs-mcp A Model Context Protocol server that enables AI assistants like Claude to read from, append to, and format text in Google Documents programmatically. | |
| MCP Task Server a-cdeveloper/mcp-task-server---example Enables task management through MCP tools, resources, and prompts, backed by a PostgreSQL database. | |
| Joern MCP Server a-chernobrov/joern-mcp Enables executing arbitrary Joern/CPGQL queries against a loaded Code Property Graph, loading source code in multiple languages (PHP, Java, JavaScript, Python, C/C++) to build new CPGs, and inspecting loaded projects and the active workspac | |
| Example MCP Server with FastMCP a-ddollar-cs/mcp An educational example demonstrating how to build MCP servers in Python using FastMCP, showing how to expose tools, resources, and prompts to AI clients. | |
| LightRAG MCP Server a-earthperson/lightrag-mcp MCP server for integrating LightRAG with AI tools. Provides a unified interface for interacting with LightRAG API through the MCP protocol. | |
| mcp-client-discord a-g-e-n-t-s/mcp-client-discord Listens for Discord @mentions via Gateway and queues them for processing by an agent, exposing a tool to retrieve pending mentions for automated responses. | |
| mcp-client-slack a-g-e-n-t-s/mcp-client-slack Listens for Slack @mentions and publishes them as real-time events to the KĀDI event bus, enabling event-driven architectures with low latency. | |
| MCP_Discord_Server a-g-e-n-t-s/mcp-server-discord Discord Message Sending Service for Claude Desktop and KADI Agents that enables sending messages and replies to Discord channels via the Discord REST API. | |
| Git MCP Server a-g-e-n-t-s/mcp-server-git A secure and scalable Git MCP server giving AI agents powerful version control for local and (soon) serverless environments. | |
| mcp-server-github a-g-e-n-t-s/mcp-server-github An MCP server that enables GitHub API operations such as managing repositories, issues, and pull requests through natural language. | |
| mcp-server-quest a-g-e-n-t-s/mcp-server-quest Comprehensive quest orchestration system with KĀDI broker integration, multi-channel approval workflow, and Git-backed data storage. | |
| Slack Message Sender a-g-e-n-t-s/mcp-server-slack MCP server for sending messages to Slack channels and replying in threads, with automatic channel name resolution and support for Claude Desktop and KADI agents. | |
| kismet-wireless-mcp a-g-u-p-t-a/kismet-wireless-mcp A read-only MCP server for querying Kismet Wireless systems, enabling AI agents to retrieve network status, datasources, devices, and alerts via REST API. | |
| jaxa-earth-mcp a-hikata/jaxa-earth-mcp Enables interactive access to JAXA's satellite observation data (precipitation, land surface temperature, NDVI, elevation, soil moisture) via Claude, providing tools for point time series, dataset information, and area image generation. | |
| Blender MCP a-homelab/blender-mcp Enables AI assistants to control a Blender instance through MCP tools, supporting scene creation, editing, and asset exchange via HTTP and background CLI processes. | |
| CSV Insight & Cleaner MCP a-i-m-a-n/mcp Minimalistic MCP server that lets AI assistants inspect, quality-check, and clean CSV datasets through tools, resources, and prompts, without needing local file access. | |
| ms-365-mcp-server a-impact-pavel/ms365-mcp Enables AI assistants to interact with Microsoft 365 and Office services through the Microsoft Graph API, providing tools for email, calendar, files, Teams, SharePoint, and more with configurable permissions and output formats. | |
| Todoist MCP Server a-j-c/todoist-mcp-server Provides 44 tools to interact with the Todoist API v1, enabling task, project, and label management, with read, write, and destructive operations. | |
| Developer Roadmaps MCP Server a-kaibu/developer-roadmaps-mcp Provides access to developer roadmap content from roadmap.sh, allowing users to list available roadmaps and fetch detailed Markdown content for specific career paths. | |
| Planning Center MCP Server a-kamari/planning-center-mcp Provides read-only access to the Planning Center People API, enabling natural language queries for people, households, background checks, and lists. | |
| Nextcloud MCP Server a-lagutov/nextcloud-mcp Connects any MCP client to a Nextcloud instance through official WebDAV and OCS APIs, enabling browsing, searching, uploading, downloading, copying, moving, and deleting files and folders, plus managing favorites, public links and user/grou | |
| @agent-mcp/react a-launch/agent-mcp-react Enables agents to drive a running React application through typed MCP tools, using the same actions as the UI instead of browser automation. | |
| aspark-graph a-lottes/aspark-graph A lean, local knowledge graph that joins a repo's code to its aSPARK delivery artifacts, enabling agents to trace user stories to code and assess impact of changes, served over MCP. | |
| Enhanced API Gateway a-m-o-r-f-a-t-i/easyeda-enhanced-api-gateway Enables MCP/AI clients to read project state and execute protected PCB operations in EasyEDA Pro via a local Bridge and official extension APIs. | |
| Boneyard Integration Starter a-mart/boneyard-integration-starter Enables Boneyard to call authenticated, stateless Streamable HTTP tools for searching tickets and adding ticket comments, with caller context, attribution, and bounded results. | |
| ComfyUI MCP Server a-misen/mcp-comfyui An MCP server for generating images and checking generation status through ComfyUI's API. It allows interaction with local ComfyUI instances by providing workflow-based image generation and status checking tools. | |
| DashMCP PBI a-negi1/dash_mcp Enables generating Power BI .pbit dashboards from CSV files or live SQL databases using plain-English prompts and optional reference-image layouts, with local-only processing and MCP tools for Claude Desktop. | |
| MCP Filesystem Server a-niranjan/mcp-filesystem Provides secure filesystem access for AI models through the Model Context Protocol with strict path validation, file operations, directory management, and system command execution within predefined directories. | |
| FirstPromoter MCP Server a-petukhov/firstpromoter-mcp An MCP server that provides AI assistants with access to the FirstPromoter affiliate management platform for managing referrals, promoters, campaigns, and commissions. It is designed for remote multi-user deployment and supports operations | |
| Yes or No MCP a-polishchuk/mcp-example-stdio A simple MCP server implementation in TypeScript that communicates over stdio, allowing users to ask questions that end with 'yes or no' to trigger the MCP tool in Cursor. | |
| AI Workspace MCP Server a-proof/coding-mcp Provides a secure workspace for AI-driven file management and Python script execution designed to run on Vercel. It enables tools for full file operations and code execution within a sandboxed environment. | |
| WhkerDB MCP Server a-quark2005/whkerdb-mcp Enables interaction with the WhkerDB shared PDF editor to manage collaborative rooms, file structures, and real-time annotations. It allows users to upload PDFs and images, manage note trees, and sync data across platforms through natural l | |
| Estonian Transport MCP a-rank/estonian-transport-mcp Provides Estonian public transport timetables, trip planning, stop search, and real-time vehicle tracking. | |
| bource a-saeedia/bource-mcp Read-only MCP server for Tehran Stock Exchange (TSETMC) live market data and authenticated TSE portal pages, enabling quotes, order books, market watch, and session-safe page reads via natural language. | |
| creative-lemon a-saeedia/creative-lemon Enables AI agents to design and critique websites using 2026 trend reports, motion code recipes, design principles, palettes, type systems, section skeletons, references, and DESIGN.md tokens, with performance and reduced-motion handling bu | |
| codemode-node a-saeedia/node-code-mode Enables agents to accomplish multi-step work by writing a single sandboxed JavaScript program that drives shell, filesystem, HTTP, and every tool of any configured MCP server, returning only a small summary instead of raw JSON. This collaps | |
| Woodpresser a-saeedia/woodpresser-mcp Gives AI coding agents typed, mode-gated access to a real WordPress site — content, media, users and settings via core REST, plus PHP execution, SQL queries, filesystem operations and Elementor page read/build/patch/snapshot via a companion | |
| bitrix24-mcp-server a-shipilo/bitrix24-mcp-server Enables AI assistants to manage Bitrix24 CRM entities, tasks, project kanban boards, and Scrum sprints through an incoming webhook, requiring explicit user confirmation for all write operations. | |
| telegram-mcp-server a-shipilo/telegram-mcp-server Enables Claude to send Telegram messages through your own bot for notifications, such as routine summaries, long-running task completions, and issue alerts. | |
| YouTube MCP Server a-shipilo/youtube-mcp-server Lets an MCP client read comment threads on your own YouTube channel, prepare replies, moderate or hide comments, and query YouTube Analytics reports. Every publishing or moderation action is held for explicit user confirmation before it tak | |
| truenas-mcp a-simple-test-organization/truenas-mcp Read-only MCP server for TrueNAS Scale debugging, providing k3s tools for kubectl operations and whitelisted midclt calls for system info, apps, and pools. | |
| selectel-mcp a-slvn/selectel-mcp An MCP server that gives an AI agent controlled access to a Selectel cloud account: OpenStack cloud servers, S3 object storage, and account billing. |
22,451–22,500 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.