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 |
|---|---|
| Weather MCP Server andresilvase/weather-mcp-server Retrieves weather alerts and forecasts from the National Weather Service API. | |
| RAG LangGraph MCP Server andresjmnz92-jpg/rag-langgraph Exposes a RAG agent built with LangGraph, enabling retrieval-augmented question answering over a PostgreSQL/pgvector corpus via the MCP protocol. | |
| LinkedIn MCP Server andresminakata/linkedin-mcp-server Enables AI assistants to browse profiles and companies, manage messages and inboxes, and search jobs, posts, and people through a locally logged-in browser session. All actions run on the user's own machine. | |
| mem0-mcp andresmorales07/mem0-mcp A server that wraps a self-hosted mem0 REST API as MCP tools for Claude Desktop and Claude Code, enabling memory operations such as adding, searching, and managing memories via natural language. | |
| tldraw MCP Server andresmuelas2004/tldraw-mcp-server A full-featured MCP server that lets AI assistants create and edit tldraw diagrams programmatically with 30 tools across all 14 shape types. | |
| Hello World MCP Server andresninou/test_mcp A simple demonstration MCP server that provides basic greeting functionality and server information. Enables users to generate hello messages and retrieve server details through tools and resources. | |
| ribbo-mcp andrespadeto/ribbo-mcp Enables AI assistants to operate the Ribbo recurring billing API, allowing them to manage subscriptions, check entitlements, refund payments, charge immediately, and generate payment or renewal links. | |
| zotero-mcp-server andresrocha99/zotero-mcp-server-v2 An MCP server for the Zotero Web API v3 that lets you search, read, and write items, collections, tags, and notes in a Zotero library, supporting literature-review workflows. | |
| mcp-worker-starter andressalame/mcp-worker-starter Enables running a minimal, dependency-free Model Context Protocol server on Cloudflare Workers that exposes custom tools to MCP clients over plain POST, with optional token auth and rate limiting. | |
| Command-Line MCP Server andresthor/cmd-line-mcp Allows AI assistants to safely execute common Unix/macOS terminal commands through a controlled interface with comprehensive security features. | |
| Excalidraw MCP Server andreswebs-public-images/excalidraw-mcp Enables creation, management, and export of Excalidraw drawings through natural language. Supports CRUD operations on drawings and export to SVG, PNG, and JSON formats with file-based storage. | |
| elastic-security-mcp andreucrespo/elastic-security-mcp A Python MCP server that provides AI agents with a controlled, read-first interface to Elasticsearch, Kibana Security, Fleet, and Elastic Defend. | |
| MCP Command Server andrew-beniash/mcp-command-server A secure server that allows LLM applications like Claude to execute whitelisted system commands with user confirmation and comprehensive security features. | |
| Code Graph Context andrew-hernandez-paragon/code-graph-context Builds rich code graphs from TypeScript/NestJS codebases using AST analysis and Neo4j, enabling semantic search, natural language querying, and intelligent graph traversal to provide deep contextual understanding of code relationships and d | |
| todo-mcp-server andrew-klear/todo-mcp-server An MCP server that serves the same todo domain via hand-written tools or a tRPC router, to compare the two approaches. It enables todo operations through MCP with optional bearer-token auth and scopes. | |
| fedramp-docs-mcp andrew-nolan-owl/fedramp-docs-mcp An unofficial MCP server that exposes public FedRAMP 20x documentation as deterministic, citable lookup tools for AI assistants, with every response citing the exact upstream source. | |
| workday-studio-mcp andrew-price-huron/workday-studio-mcp A local MCP server that gives Claude direct access to Workday Studio workspace. Enables reading, writing, planning, and validating integration assemblies without network calls or tenant credentials. | |
| ZipExplore MCP Server andrew-sondgeroth/zipexplore-mcp Enables location intelligence for US ZIP codes, allowing users to search, profile, and compare ZIP codes across various domains like crime, income, schools, and more. | |
| Kali MCP Pentest Server andrew-stclair/kali-mcp-server Enables users to perform security testing and penetration testing tasks through a Docker-based API that provides access to popular security tools like nmap, nikto, sqlmap, wpscan, dirb, and searchsploit. Designed for educational purposes wi | |
| Dotfiles MCP Server andrew-wu-12/dotfile-mcp-server Enables LLMs to access and execute custom automation scripts from a dotfiles repository, including tools for JIRA, GitHub, Jenkins, and code review. | |
| GameForge MCP andrew012410/gameforge-mcp Enables MCP-capable coding agents to act as a deterministic technical art director and multi-engine pipeline builder, locking AI-generated 2D/2.5D game assets to consistent camera angles, palettes, rigs, atlases, and exports across Blender, | |
| MCP Memory Keeper andrew0665/mcp-memory-keeper Enables AI coding assistants to save, search, checkpoint, and restore context across sessions so work history, decisions, and progress persist through conversation compaction or session resets. | |
| taskdeck andrew1431/taskdeck Lets AI agents discover and run a repo's commands defined in a single taskdeck.yaml contract, with typed parameters, schemas, and risk levels. Safe actions run directly while deploys, deletes, and other high-risk actions become proposals a | |
| MultiZen MCP Server andrew5251/multizen-browser Enables AI agents and human operators to drive isolated browser profiles with persistent cookies, fingerprints, and proxies, exposing navigation, clicking, typing, extraction, screenshots, JS evaluation, tabs, cookies, and waits to MCP clie | |
| line-cua-mcp andrew54068/line-cua-mcp A macOS MCP server for LINE that reads encrypted local database snapshots to fetch chat history and sends messages via LINE UI without cursor movement. | |
| docx-mcp andrew82106/llm_docx_agent_mcp Enables comprehensive management of Microsoft Word documents with 30+ tools for reading, writing, formatting, template merging, image extraction, equation extraction, and style application. | |
| FRED MCP Server andrewalekseev35/fred-mcp-server Enables browsing, searching, and retrieving any of the 800,000+ Federal Reserve Economic Data time series, with support for date ranges, frequency aggregation, and transformations such as percent change or natural log. | |
| CubeCobra MCP Server andrewanderson/cubecobra-mcp MCP server for CubeCobra that enables fetching cube lists, CSV, JSON, plaintext, and record data. It supports optional authentication for private endpoints and configurable base URL. | |
| promptspend andrewavery7/promptspend LLM pricing for coding agents: every price carries its source and the date it was last confirmed, and disputed prices are flagged. Looks up model rates, costs a described workload, and finds cheaper models that score at or above a given one | |
| Claude Works andrewaws26/claude-works An MCP server that exposes a perpetual, honest job-application pipeline as typed tools an LLM agent can call, with fit scoring, verified resume building, and a submission planner enforced by code, not prompts. | |
| Matryoshka andrewb6868/matryoshka Enables token-efficient analysis of documents far larger than an LLM's context window by executing validated symbolic commands against server-side handle and memo stores, with recursive query support via MCP sampling. | |
| NOESIS andrewbalda01/noesis-mcp A cognitive optimization engine exposed as an MCP server that amplifies LLM reasoning through self-consistency sampling, MCTS, Dung argumentation, symbolic verification, and measured confidence. | |
| Apple Calendar MCP Server andrewbergsma/apple-calendar-mcp A comprehensive MCP server that provides AI assistants with natural language access to Apple Calendar, enabling reading, searching, creating, and managing calendar events. | |
| ygo-format andrewboe/ygo-format Enables an AI assistant to search real card data, check legality and points, validate or save decks, pull rulings, and review tournament meta for TCG Advanced and Genesys. It exposes tools for card search, archetype lookup, deck validation, | |
| Claude Sidekick andrewbrereton/claude-sidekick A Model Context Protocol (MCP) server that connects Claude to local Ollama models, enabling offloading of simpler tasks to save Claude tokens. | |
| Detection Workbench andrewbrooks/detection-workbench Enables an MCP client to write, validate, run, explain, and tune Snort 3 detections against packet captures on disk offline, with every change verified by real engine runs and recorded in exportable case reports. | |
| @upon-ai/mcp-server andrewcallsandy/uponai-developer-tools Enables workspace discovery, access to 18 curated read operations, and separately enabled call-changing operations for interacting with UponAI services through MCP. | |
| power-automate-mcp andrewcharlwood/power-automate-mcp Enables interaction with Microsoft Power Automate cloud flows via Azure CLI, allowing management of flows, triggers, runs, and connections. | |
| senja-mcp andrewconnell/senja-mcp An MCP server that enables AI assistants to list, retrieve, and create testimonials through the Senja API. | |
| Zoho Projects MCP Server andrewcraigmorgan/zoho-projects-mcp An enhanced MCP server for Zoho Projects API integration, enabling AI assistants to manage projects, tasks, issues, milestones, comments, attachments, and more with automatic OAuth token refresh. | |
| velocity andrewctf/velocity Live aircraft and ship positions for an agent, by circle or polygon, with the feeds that reported each contact and how old each fix is. Runs against your own self-hosted Velocity instance, no API keys. | |
| YouTube Transcript Fetcher (YTT) andrewctf/ytt An MCP server that enables searching YouTube and retrieving high-accuracy video transcripts using local Whisper AI transcription without requiring an API key. It supports single or batch processing and provides transcripts in multiple forma | |
| MCP Agent Coordinator andrewdavidrivers/multi-agent-coordination-mcp A Model Context Protocol server for coordinating multiple parallel agents working on the same project within an IDE, managing projects, tasks, todo items, and file locking to enable safe concurrent development. | |
| WooCommerce MCP Server andrewdejager65/woocommerce-mcp-server Enables interaction with WooCommerce stores through the WordPress REST API, providing tools for managing products, orders, customers, shipping, taxes, coupons, payment gateways, reports, and store settings. Also supports WordPress content o | |
| architecture-map MCP server andrewdpg/waycairn Enables MCP-compatible AI agents to read and write architecture-map projects and diagrams with per-project access controls via OAuth 2.1/PKCE. | |
| Octopus Deploy Official MCP Server andrewengstrom47191/mcp-server Enables AI assistants to connect to an Octopus instance to inspect, query, and diagnose deployment problems, with toolsets covering projects, releases, deployments, runbooks, tenants, Kubernetes, machines, and accounts. Supports read-only m | |
| Bright Data MCP Server andrewestopinan/browser-mcp Enables AI agents to browse and extract data from any public website via Bright Data's cloud infrastructure, handling proxy rotation, CAPTCHA solving, and JavaScript rendering. | |
| ropey andrewesweet/ropey Enables coding agents to perform safe, project-wide Python refactoring (rename, move, extract, inline, change signature, organize imports, etc.) with a dry-run safety contract and LSP-coordinate addressing. | |
| FineRx MCP server andrewfinerx/finerx-mcp Gives AI assistants live access to US prescription drug prices by pharmacy with observation dates, the free discount card, and vetted US equivalents of foreign-brand medicines, all through the Model Context Protocol. | |
| vaultrecall-mcp andrewg0r/vaultrecall-mcp A local MCP server that turns an Obsidian vault into a searchable second brain for Claude with meaning-based search, note read/write, and insight reports like contradictions and stale TODOs. |
28,751–28,800 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.