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 |
|---|---|
| job-radar borissmaznov/job-radar Enables LLM agents to search jobs, retrieve individual job details, access statistics, and mark application statuses by querying a SQLite-backed job database. | |
| RS.ge Waybill MCP Server borissolomonia/mcpwaybill Enables natural language queries for Georgian tax system waybills through the RS.ge SOAP API. Supports waybill retrieval by date range, company TIN lookups, and access to tax system dictionaries. | |
| Spotify MCP Server boristopalov/spotify-mcp Connects Claude with Spotify, enabling playback control, search functionality, and queue management through Spotify's API. | |
| genomics-mcp borjanebbal/genomics-mcp Provides programmatic access to curated SNP data by trait, enabling LLM-powered applications to search, interpret, and discover genetic variants. | |
| twitter-username-changes-mcp borkst084-bot/https-github.com-kukapay-twitter-username-changes-mcp Tracks historical changes of Twitter usernames to detect frequent screen name changes, which can be a red flag for potential scam risks. | |
| oracle-kit born2be4/codex-oracle-kit Enables Codex to delegate tasks to ChatGPT through a browser-backed Oracle connection, with project memory and a verified-result cache. It supports preview, delegation, result polling, and explicit acceptance without an API fallback. | |
| marionette-mcp bornmw/firefox-mcp-marionette Enables AI agents to drive a user-launched Firefox instance via its native Marionette protocol, providing precise DOM actuation like clicking, typing, uploading files, taking screenshots, and evaluating JavaScript. | |
| MISP-MCP-SERVER bornpresident/misp-mcp-server A Model Context Protocol (MCP) server that integrates with the MISP (Malware Information Sharing Platform) to provide threat intelligence capabilities to Large Language Models. | |
| tmux-mcp-claude borod108/tmux-mcp-claude Gives Claude Code full control over tmux sessions, windows, and panes, with an optional Sonnet-based safety classifier for destructive commands. | |
| BuildWindow borovkov-d/buildwindow-mcp Enables scheduling of construction works against weather forecasts, using deterministic tools to check weather suitability, estimate curing times, and place dependent tasks into the earliest non-prohibited time windows. | |
| turing-test-game bortor/turing-test-game Enables interaction with the AnyAnyGame Turing test service via HTTP and WebSocket, exposing tools for auth, matching, messaging, and meme search. | |
| b4-after borwood/cb4 Enables coding agents to propose, review, promote, and verify architecture changes as recorded C4 model updates, with hypothetical diffs, evidence-based qualification, and component histories. | |
| gpt-image-2-mcp borys520/gpt-image-2-mcp Exposes OpenAI's gpt-image-2 (image generation and editing) as an MCP server for tools like generate_image, edit_image, and iterative edit sessions. | |
| todoapp borysbordunov-a11y/todoapp-mcp Lets users manage their personal todo items through MCP tools, with secure per-user authentication via stateless Streamable HTTP. | |
| homepl-email-mcp borystam/homepl-email-mcp Enables a local AI agent to read, search, compose, send, and organize mail in a home.pl mailbox over encrypted IMAP and SMTP, with credentials held in the OS credential store and a one-time private local setup form. Supports folder and hist | |
| mcp-visual-design-studio borystam/mcp-visual-design-studio Provides a local, collaborative visual document editor that works with MCP agents, enabling creation and editing of brochures, reports, and other designs with live synchronization, revision history, and portable exports. | |
| auth-vault borysttk/auth-vault-template MCP server for secure credential management, browser-based login automation, and TOTP/2FA auto-solving. Encrypts credentials with AES-256-GCM and automates login flows via Playwright. | |
| companycam-mcp bos-automations/companycam-mcp-server Enables managing CompanyCam projects, photos, tags, comments, and users through natural language, using the CompanyCam API. | |
| Claude IPC MCP bos52147/claude-ipc-mcp Enables different AI assistants to send messages to each other across platforms and sessions using simple natural language commands, with persistent message storage and optional authentication. | |
| filesystem-mcp-with-FastMCP-server bosaj/filesystem-mcp-with-fastmcp-server Provides a sandboxed filesystem API for AI agents, enabling natural-language file read, write, append, delete, move, list, create, and metadata operations through MCP tools. | |
| emsesp-mcp-server bosch-buderus-wp/emsesp-mcp-server Enables LLM applications to query and visualize data from Bosch/Buderus heat pumps via ems-ESP, including temperatures, statistics, and heat curves through natural language. | |
| MT5 MCP Server boschi404/mt5-mcp-server A 34-tool MCP server that bridges LLMs to MetaTrader 5, enabling EA development, backtesting, optimization, advanced analytics, live trading, and portfolio management. | |
| tc39-atlas bosens-china/tc39-atlas Provides TC39 proposal indexing and querying capabilities via MCP, including proposal details, changes, and daily synchronized data from the official TC39 dataset. | |
| Roblox Studio MCP Server boshyxd/robloxstudio-mcp An AI-powered server that provides access to Roblox Studio data through a plugin architecture, enabling AI tools to interact with file systems, studio context, properties, and project structure. | |
| Moke MCP bosong/moke_mcp Brings Mockplus design data into AI coding assistants, enabling automated design-to-code workflows. | |
| continuum bosprimigenious/continuum Provides read-only MCP tools to inspect imported history sources, list sessions, search literal text, and read paginated event history from a local SQLite index. | |
| xtiandos bossayan9999/xtianos Enables any MCP client to access xtiandOS's brain, memory, chat, message bus, shell, Docker, and artifact capabilities through tools, resources, prompts, roots, and sampling. | |
| weibo-hot-search-mcp-server bossdong955/mcp-server-example MCP server that fetches Weibo hot search trends. Supports Stdio, SSE, and Streamable HTTP. | |
| BOSSCORE MCP PACK bosserpnext/bosscore-mcp-pack Modular MCP capabilities package for the BOSS ecosystem, enabling WordPress site management, file reading, and cPanel deployment with 63 tools across three profiles (wordpress, files, full) and two transport modes (stdio and HTTP/SSE). | |
| Datetime MCP Server bossjones/datetime-mcp-server This server enables users to store, manage, and summarize notes using a custom URI scheme, with functionality to add new notes and generate summaries with varying levels of detail. | |
| jira-dc-mcp bossproto/jira-dc-mcp Enables read-only Jira Data Center insights by default, with opt-in audited write tools, sprint and release health summaries, and structured issue search via MCP. | |
| Agent Farm bossx429/agent-farm An orchestration platform for deploying parallel swarms of tool-enabled AI agents to perform complex tasks like code generation, system monitoring, and multi-perspective analysis. It features a unique chunked write pattern that enables the | |
| gsc-coverage boston617delta/gsc-coverage-mcp Enables MCP clients to pull complete Google Search Console performance data by paginating past the API's 25,000-row cap, with large results written to CSV or JSON files and only a preview returned inline. Every response includes a coverage | |
| WSL Manager bostrot/wslmanager Lets AI agents manage local virtual machines: create macOS and Linux VMs on Apple silicon and WSL distros on Windows, start/stop, clone, back up, and run commands inside them. | |
| TastyTrade MCP Server bostrovsky/tastytrade_mcp_server Connects your TastyTrade trading account to AI assistants like Claude Desktop and ChatGPT for conversational trading and portfolio management. | |
| User MCP Server bot-qianjinyan/mcp-servers Streamable HTTP MCP server that exposes user and billing management tools, resources, and prompts through a REST API, enabling natural language interaction with user profiles, bills, and sharing features. | |
| agmind-mcp botagi/agmind-mcp Read-only MCP server exposing AGmind Systems Lab's measured local-LLM benchmark claims (TTFT, inter-token latency, task success, etc.) on AMD Strix Halo and DGX Spark hardware via search, claim lookup, and measured-combination listing tools | |
| Crossref MCP Server botanicastudios/crossref-mcp A Model Context Protocol server that enables querying the Crossref API to search for academic publications by title, author, or DOI, returning structured metadata about scholarly works. | |
| MCP Host RPC Bridge botanicastudios/mcp-host-rpc A server that bridges MCP tool calls to JSON-RPC function calls over socket connections, allowing external applications to expose functions as MCP tools. | |
| Botdigit MCP botdigit-official/botdigit-mcp-server Connect AI agents to BotDigit's freelancer marketplace and project workspace. Discover freelancers and services, manage projects and tasks, retrieve project context, connect repositories, track development activity, and coordinate software | |
| local-browser-mcp-server botdojo-ai/local-browser-mcp-server Enables browser automation (navigation, screenshots, clicking, typing) and AI image generation using Puppeteer and Google Gemini. | |
| Copiloto Financeiro MCP Server botelho31/copiloto-financeiro Enables AI agents to manage personal finances for Brazilian users through MCP tools, including categorizing transactions, reconciling debts, checking cash-flow projections, and adjusting budgets, with integration to Open Finance Brasil via | |
| Finance MCP Server botextractai/ai-mcp-server-client-fastmcp A Model Context Protocol server built with FastMCP that provides financial data tools for AI agents, enabling them to access and analyze stock market information from Yahoo Finance through natural language queries. | |
| BotHire-OKX bothirelab/bothire-okx Enables autonomous agents to discover and call BotHire's paid agent skills via MCP, with per-call payments settled in x402 on X Layer. | |
| jev-browser-mcp bothuany/jev-browser-mcp Enables AI agents to control a real browser through intent-based tools—reading pages, filling forms, clicking, and replaying self-healing recipes—while returning only concise answers instead of the DOM. | |
| archicad-mcp boti-ormandi/archicad-mcp MCP server for Archicad automation, enabling AI assistants to run Python scripts against running Archicad instances via the Tapir JSON API for complex workflows. | |
| memscope-mcp boti-ormandi/memscope-mcp Enables AI agents to perform low-level Windows process memory research, including process attachment, memory scanning, reading/writing, pointer chasing, remote code execution, and inline hooking via MCP tools and Lua scripting. | |
| tor-browser-mcp boti-ormandi/tor-browser-mcp Enables AI agents to control Tor Browser with full anonymity preservation, including navigation, Tor circuit management, and traffic interception. | |
| Reins botinfo-ai/botinfo An MCP server that lets an AI agent operate an owner-connected robot only through the owner's pre-approved, bounded actions, enforcing rate and motion limits, leases, replay and expiry checks, owner-only confirmation and stop controls, and | |
| chromium-sync-mcp botterusik/chromium-sync-mcp Enables access to browser data from Brave, Chrome, and Chromium — open tabs across all synced devices, browsing history with search and date filters, and bookmarks — by reading local profile files directly without authentication or network |
35,151–35,200 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.