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 |
|---|---|
| Lark Session Bridge a4001234567/larkbridge Enables existing agent sessions to register identities, receive and acknowledge Lark message or card events, and make outbound Lark API calls directly. It supports shared broker routing, chat assignments, event retrieval and pausing, and me | |
| Shortdrama Basic a405839824-coder/shortdrama-basic Enables local creation and querying of projects, storage and retrieval of source text, reading and saving storyboard tables with revision-conflict protection, and Excel export through MCP tools backed by SQLite. | |
| CE MCP Backend a45s67/ce-mcp-backend Enables structured dynamic analysis of authorized Windows processes via Cheat Engine 7.7, exposing bounded tools for process inspection and debugging without arbitrary code execution or memory writes. | |
| Dynamic Analysis MCP Gateway a45s67/dynamic-analysis-mcp Federates multiple local debugging MCP backends behind a single authenticated MCP endpoint, enabling unified access to Cheat Engine, x64dbg, and x32dbg tools. | |
| luogu-mcp a48zhang/luogu-mcp Fetches and structures programming problem data from Luogu, enabling AI tools to query problem details such as title, difficulty, tags, samples, and limits. | |
| tencent-stock-mcp a490582878-collab/tencent-stock-mcp Provides real-time A-share stock quotes and daily K-line data from Tencent, plus a health check tool, via a read-only MCP server. | |
| codex-memory a4913994/codex-memory Provides curated long-term memory for Codex CLI via MCP, with Markdown-based storage, deduplication, and decay-based forgetting. | |
| multiCAD-mcp a494359163-byte/dsh-multicad Enables AI assistants to drive AutoCAD, ZWCAD, GstarCAD, and BricsCAD through seven unified tools covering 56 CAD commands — drawing lines, circles, rectangles, polylines, splines and tables, managing layers, blocks and entities, transformi | |
| A4A (Agent-for-Agent Network) a4a-network/a4a Open end-to-end encrypted messaging protocol and MCP server (a4a-mcp) that gives AI agents a cryptographic address (apub1...) to exchange messages, tasks, and signed agreements directly across NAT without port forwarding. | |
| agy-agent-mcp a4amk/agy-agent-mcp Delegates coding and read-only exploration tasks to the Antigravity CLI as blocking headless runs, mirroring live progress to on-disk stream transcripts and diffing git status to report touched files and out-of-scope edits. Supports resumab | |
| K-Sign MCP Server a4file/k-sign-mcp-server Provides Korean Sign Language (KSL) data through MCP, enabling search and retrieval of sign language terms and details. | |
| Wingman a526800921/wingman A wingman MCP server for Claude Code that provides auxiliary tools for file summarization, text compression, and diff review to ensure checklist items are not missed. | |
| yqztk-capabilities a565223452/yqztk-capabilities Enables MCP-capable AI agents to invoke 38 deterministic, private, auditable compute tools over stdio, covering PII masking, finance schedules, health, text, units, media, business, gaming, and scheduling without network access or dependenc | |
| Model Worker MCP a5768549/model-worker-mcp Enables bounded, local coding tasks to be delegated to OpenAI-compatible models with explicit working directory and read/write paths, pre-application unified-diff validation, and optional verification commands. It routes tasks by complexity | |
| SolTracker MCP Server a6b8/soltracker-mcp Provides unified access to real-time and historical Solana ecosystem data through 40+ API endpoints, enabling LLM agents to query tokens, wallets, trades, and DeFi metrics. | |
| etfedge-mcp a7351220/etfedge-mcp Read-only MCP server for Taiwan active ETF research database, providing tools to list ETFs, track buy/sell deltas, view stock history and PnL, and find consensus buys across ETFs. | |
| JevLens a742987/jevlens Enables coding agents to ask TypeSafe Jev for structured decisions while recording every call to a local JSONL trace, and provides tools to read back and export decision histories for debugging. | |
| mcp-server-104 a7512cs/104-mcp-server Enables natural-language search and retrieval of Taiwan 104 job bank listings, including job details and company-specific openings, with filters for location, salary, experience, and remote work through an MCP interface. | |
| mcp-production-kit a7mdme/mcp-production-kit A TypeScript MCP server starter kit supporting stdio and HTTP/SSE transports. Includes tools for system metrics, HTTP fetching with URL restrictions, and temporary key-value memory with namespace and TTL support. | |
| pi-agent-mcp a809384377/path_pi Enables MCP hosts like Claude Code and Codex to spawn, manage, and interact with persistent, reusable Pi coding-agent sessions, supporting task dispatch, status checks, and session lifecycle control. | |
| MemStack MCP Server a847840750/memstack Exposes 12 memory and multi-agent tools over stdio JSON-RPC so agents can write episodes and extracted facts, then recall them with hybrid retrieval, bi-temporal state tracking, and evidence-chain decomposition under a token budget. It also | |
| ce-mcp a8814304/ce-mcp Enables AI to directly control Cheat Engine for process attachment, memory scanning, reading/writing, address list management, speed hack, Lua/Auto Assembler execution, and CT file management via the MCP protocol. | |
| ai-video-studio-agent a895150154-star/ai-video-studio-agent MCP server that provides a local Web production console and HTTP control plane for AI video creation, exposing tools for project/revision management, media analysis, editing, review, and delivery while keeping formal rendering behind explic | |
| Computer Use MCP a8cl233395/zcode-computer-use-mcp-windows Enables MCP clients to observe and control Windows desktop applications by reading UIA element trees and capturing screenshots, then acting through UIA patterns or synthesized mouse and keyboard input. It runs standalone on an interactive W | |
| RPG Maker MZ MCP Server a951753abc/rpgmaker-mz-mcp A stable, well-tested MCP server that lets AI assistants create and edit RPG Maker MZ projects through natural language. | |
| nseap-mcp a976xw7td/nseap-mcp Enables local deliverable checks and a submission-review-notification workflow for the NSEAP education platform via stdio MCP, integrating with Cogseed. | |
| rlaif a9lim/rlaif MCP server enabling AI agents to provide real-time positive and negative feedback to users through connected devices, with configurable channels for PiShock/OpenShock (negative) and Intiface (positive). | |
| Doorknock aa-ronjs/doorknock A remote MCP server that researches a company from its own domain and DNS, scores it against a lead profile, and writes the result into HubSpot. | |
| Rain Check aa-ronjs/rain-check Enables users to check whether an Australian field-service job can be worked at a location on a given day for a specific trade, using live weather forecasts, daylight hours, and public holiday data. | |
| zentao_user_mcp aa509-del/zentao_user_mcp Enables managing ZenTao users through MCP, including token retrieval, current user info, user listing, creation, update, and deletion, over stdio or Streamable HTTP. | |
| zentao-user-mcp-python aa509-del/zentao-user-mcp-python Enables ZenTao user administration, including token retrieval, user queries, and user creation/update/delete, over stdio or Streamable HTTP transports. | |
| cwtools-mcp aa728848/cwtools-mcp Read-only MCP server exposing CWTools Paradox/Stellaris semantic tools (syntax checking, scope queries, definitions, references, diagnostics, scripted triggers/effects/enums, and shader queries) to AI agents like Codex and Claude Code, brid | |
| codex-multi-model-workers aaa17001/codex-multi-model-workers Connects Codex to local and cloud language models from MoE4All, GLM, DeepSeek, and OpenAI-compatible endpoints through a controlled MCP worker boundary, enabling read-only worker analysis, provider configuration, and VS Code model setup whi | |
| mcp-schedule-termux aaaa0ggmc/mcp-schedule-termux Enables LLMs to manage personal course timetables and flexible agendas with semester terms, week rules, swaps, conflict checks, and tasks, using SQLite persistence over stdio, Streamable HTTP, and SSE. | |
| MCP Hub aaaa0ggmc/mcphub-termux Aggregates multiple local stdio MCP services into a single HTTP endpoint and launcher-managed local processes, with a mobile-first web console for starting, stopping, monitoring logs, health checks, and usage. | |
| mcp-snippetbox aaadiaosbrk/mcp-snippetbox Enables managing notes through a simple MCP server, providing tools to add, retrieve, update, delete, and list notes for use with Claude Desktop. | |
| Codebase Explorer MCP Server aaadityag/codebase-explainer-mcp-server Analyzes any codebase to detect project type, languages, frameworks, entry points, API routes, controllers, services, components, tests, and more. | |
| whatsapp-mcp aaajrs/whatsapp-mcp Enables AI assistants to read, search, and send WhatsApp messages by linking to an account as a companion device, keeping a searchable archive of chats on the user's own Cloudflare deployment. It also exposes tools for managing contacts, gr | |
| mcp-context-guard aaameobius-crypto/mcp-context-guard Compresses, deduplicates, and filters tool outputs to optimize token usage and context window for AI agents. | |
| mcp-permission-guard aaameobius-crypto/mcp-permission-guard Intent-based permission system with risk scoring, rule engine, and audit trail for AI agents. | |
| ChatGPT Codex Bridge aaandrew233/chatgpt-codex-bridge Enables ChatGPT to securely inspect local Codex projects, read session history, and dispatch confirmed tasks to the Codex CLI through a local MCP bridge. | |
| safe_edge_bridge aaash25/safe-edge Enables MCP clients to reuse an existing logged-in Microsoft Edge session for tab management, page reading, clicking, keyboard input, and file transfers. Also supports Jupyter experiment planning, submission, status checks, and result downl | |
| MCP-Weather Server aaasoulmate/mcp-weather An intermediate agent server that enhances LLMs with weather data capabilities using the Model Context Protocol (MCP) framework, enabling retrieval of real-time weather information. | |
| GitHub PR MCP Server aaaxianyu/mcp_prdairy Automates GitHub Pull Request analysis using AI, integrating webhooks, OpenAI, and Feishu/Lark knowledge base for structured summaries. | |
| Codex-DSH Bridge aaaxlt/codex-dsh-bridge Enables an MCP client such as Codex to delegate bounded development tasks to a separate DSH agent harness, track progress, and inspect model-reported results alongside independently recorded SDK events, workspace changes, and optional verif | |
| hermes-browser-mod aaaxxs-0/hermes-browser-mod Enables Agent-driven browsing in an independent Microsoft Edge profile with navigation, snapshots, iframe/DOM interaction, screenshot-coordinate clicks, hover, typing, dialog handling, and manual take/release control. It also exposes real-t | |
| envy-mcp-hello aaazzam/envy-mcp-hello A tiny public MCP server backed by an Envy-managed Modal sandbox that exposes a hello environment with standard sandbox tools like create_sandbox, bash, read, write, edit, and grep for ephemeral file and command execution. | |
| agent-vision-mcp aabbccddwasd/agent-vision-mcp Enables non-vision LLMs to analyze images via any OpenAI-compatible vision API. Hardened against truncation, empty responses, and timeouts for reliable analysis. | |
| research-tools aabgit/autonomous-web-research-agent Exposes web search and page fetching tools via the MCP protocol, allowing integration with AI editors like Cursor for autonomous research workflows. | |
| spiderbrain aabhisrv/spiderbrain.ai-coremind Enables AI coding agents to query a repository's committed understanding layer—its structure, dependencies, and blast radius—without any setup. Provides tools like sb_blast, sb_impact, and sb_map for exploring impact and key files. |
22,551–22,600 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.