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 |
|---|---|
| aidget MCP server aidget-ai/aidget Enables AI agents to create, update, patch, move, screenshot, and delete desktop widgets through MCP tools, with guided authoring and permission-scoped capabilities. | |
| AgentConduit aididhaiqal/agentconduit Enables provider-neutral durable coordination for coding agents sharing Git work, including peer discovery, durable messaging, job progress tracking, and FIFO integration authority with fenced leases. | |
| Remote MCP Server on Cloudflare aidityasadhakim/sector-mcp A serverless Model Context Protocol (MCP) implementation for Cloudflare Workers that enables AI models to access custom tools without authentication. | |
| ziyuanzhan-monitor aidizhi/ziyuanzhan MCP server for querying the availability and status of movie resource sites, including online/offline status, response times, and search functionality. | |
| Aidlab MCP aidlab/aidlab-mcp Connects Aidlab wellness data to AI tools through MCP, providing read-only access to daily summaries, steps, heart rate, HRV, sleep, activities, and profile with OAuth authentication. | |
| MCP Gateway aidministratie/mcp Enables AI assistants to connect securely over Streamable HTTP/SSE or a local stdio bridge to specialized digital administrative colleagues for tasks such as business-card scanning, prospecting, encrypted file management, approval queues, l | |
| AI Engineer MCP aidotengineer/aie-mcp MCP server for the AI Engineer Conference 2025, enabling talk submissions and conference information retrieval. | |
| camoufox-research aidvizhhub/camoufox-research MCP server for web research using anti-detect Camoufox browser. Enables search, page reading (including JS/SPA), batch fetching, clicking, typing, and live browsing sessions with caching and retries. | |
| marionette-mcp aidvizhhub/marionette-mcp Enables web search and browser automation against a real, locally installed Firefox driven over its built-in Marionette TCP protocol. Exposes tools for multi-engine search, JS-rendered page text and link extraction, screenshots, cookie save | |
| engram aiengram/engram Global shared procedural memory layer for AI agents via MCP. Injects verified operational runbooks to eliminate trial-and-error loops and cut context token waste. | |
| Vercel MCP Web Crawler aieterprise/mcp-web-crawler Provides lightweight web crawling and scraping capabilities, enabling users to fetch pages as clean Markdown, recursively crawl domains, extract metadata, and perform search-and-crawl operations. | |
| mcp-ethostron-live aiethos-ai/ethostron-mcp Agent-native Generative Engine Optimization (GEO) audits, crawler analysis (GPTBot, Perplexity, Claude), and Schema.org direct-answer remediation. | |
| Tanod MCP server aiexp1/tanod-mcp One remote MCP server with about 260 tools (also split into 11 focused servers, below) for AI agents: https://tanod.dev/mcp.
Connection: streamable HTTP and stateless, with no API key, no account and no OAuth.
Setup for 20 clients: https: | |
| DocketBird MCP Server aif-of-counsel/docketbird-mcp Enables searching and downloading court documents, listing cases, and retrieving case details via the DocketBird API. It supports secure OAuth 2.0 authentication for remote access and a standard local mode for personal use. | |
| aifais-mcp-server aifais/aifais-mcp-server Headless document processing for AI agents. Invoice extraction, contract analysis, and Dutch business verification. Pay-per-use via X402 on Solana. No API keys needed. | |
| AiFinPay Wallet MCP Server aifinpay/gpt-wallet-aifinpay Enables ChatGPT to interact with multiple blockchain networks for reading balances and managing wallet operations through a non-custodial local vault and policy engine. | |
| Local Utilities MCP Server aiforhumans/local-utils-mcp Provides essential utility tools for text processing, file operations, hashing, temperature conversion, password generation, and date/time operations through a comprehensive MCP interface. | |
| codex-desktop-bridge aiforlove/codex-desktop-bridge Enables durable bidirectional handoffs between any MCP client and OpenAI Codex Desktop tasks, with persistent callbacks, acknowledgements, and session-scoped state across restarts. | |
| Excel MCP Server aifornorms/excelmcp A Model Context Protocol server that enables AI agents to create, read, and modify Excel workbooks without requiring Microsoft Excel installation. | |
| aiganak-aiops-mcp aiganak/aiganak-aiops-mcp Enables autonomous infrastructure diagnostics, log root-cause analysis, and safe code patching via tools for querying logs, inspecting Python AST, and applying git-safe patches. | |
| A1D MCP Server aigc-hackers/mcp-server A universal AI server that provides image and video processing tools (background removal, upscaling, vectorization, etc.) for any MCP-compatible client with simple setup. | |
| AIGEN Protocol aigen-protocol/aigen-workspace MCP/REST endpoints for token safety scans, honeypot checks, ecosystem stats, and on-chain task rewards. | |
| safeagent-token-safety aigen-protocol/erc-token-safety-score Token safety oracle for AI agents. Honeypot detection, 17 scam pattern checks, LP lock verification across 6 EVM chains. Score 0-100 with risk flags. ERC Token Safety Score standard. | |
| AgentLinkWP aigenart/agentlinkwp Enables MCP-compatible AI agents to securely manage multiple self-hosted WordPress sites, including content editing, theme management, and maintenance operations with fine-grained permission controls. | |
| OpenAI Image MCP Server aigentive/openai-image-mcp Enables conversational image generation, editing, and refinement through OpenAI models with session memory for iterative creative workflows. | |
| youtube-gemini-mcp aigentive/youtube-gemini-mcp Enables conversational analysis of YouTube videos using Gemini 2.5 Pro, supporting multi-turn sessions, direct URL processing, and local video uploads. | |
| Market Fiyatı MCP Server aigile-era/market-mcp-serkan A Model Context Protocol server for querying Turkish market prices, comparing products, and getting AI-powered shopping recommendations. | |
| TR Dizin Search MCP Server aigile-era/smithery-trdizin-search-mcp Enables searching the TR Dizin (Turkish Academic Index) database for publications, journals, and authors with advanced filtering and sorting options. | |
| MCP Development Framework aigo666/mcp-framework A powerful Model Context Protocol framework that extends Cursor IDE with tools for web content retrieval, PDF processing, and Word document parsing. | |
| WeCom Mail MCP aiguicai/wecom-mail-mcp 通过企业微信官方邮件API发送普通邮件，并支持查询邮箱信息，兼容stdio、sse和streamable-http传输方式。 | |
| aihu-mcp aihu-project/aihu-mcp An MCP server that exposes aihu_example and aihu_validate tools over stdio, enabling cookbook retrieval and compiler-verified validation for Aihu. | |
| mcp-server-wslc aihuali213/mcp-server-wslc Enables AI agents to manage WSL containers and images via the wslc CLI, supporting container lifecycle, network, volume, and registry operations through natural language. | |
| llm-toolkit aihunter9892/mcpserver An MCP server that turns an LLM API into MCP tools, providing four LLM-powered tools (ask_llm, summarize, translate, extract_json) and running locally over stdio or remotely over HTTP. | |
| Figma MCP local aihustlerahul-ui/figma-mcp-local A local, high-performance replacement for the hosted Figma MCP server that caches Figma files and exposes a local MCP endpoint for Cursor or any MCP client. | |
| metax-docs-mcp aiianz/metax-docs-mcp Enables agents like Codex to search and read MetaX official documentation, MetaX-MACA GitHub content, and Docker image catalog entries from a local offline index, with source citations returned for each result. | |
| KASA aikadimsoy/kasa-mcp A local-first memory vault MCP server for Windows that exposes an encrypted user memory store to agents via a permission-brokered protocol, ensuring user ownership and control over browsing data. | |
| jyotish_mcp aikanysh7/jyotish-mcp Vedic astrology MCP server that computes birth charts, dashas, transits, and ashtakavarga using Swiss ephemerides, enabling Claude to provide astrological interpretations. | |
| wilma aikarjal/wilmai Connects AI assistants and agents to Finland's school system, enabling retrieval of schedules, homework, exams, grades, messages, absences, and related school information for all of a family's children across multiple accounts. It runs loca | |
| claude-codex-mcp aikazu/claude-codex-mcp Lets an MCP client hand coding tasks, second-opinion reviews, and image-asset generation to the official OpenAI CLI agent running locally, returning final messages, session IDs, and saved files. Jobs run sandboxed with prompts over stdin, w | |
| Database MCP Server aike1202/db-mcp-server-npx Enables AI assistants to interact with relational databases such as MySQL, PostgreSQL, SQLite, SQL Server, and Oracle. Provides tools for querying, data inspection, and schema analysis with optional read-only mode. | |
| serac aikogilpin/serac-agents Sovereign E2E cloud storage for AI agents. MCP-native, zero-knowledge, RGPD-compliant, built in France. | |
| YouTube Trending MCP Server aikong2024/youtube-trending-mcp Collect YouTube trending videos without web scraping via yt-dlp MCP server. No API keys required, supports category filtering and daily rankings. | |
| o1-base-launcher ailauncho1/o1-base-launcher Enables reading o1 Launchpad data on Base Mainnet, preparing Standard token launches and exact-input buys/sells, preparing direct ETH/ERC-20 transfers and creator fee claims, and routing transaction approval to a local browser wallet for si | |
| Home Assistant MCP ailearncoder/home_assistant_mcp Enables control and monitoring of Home Assistant smart home devices through MCP protocol. Automatically manages authentication tokens and provides simplified tools for device discovery, switch control, and light brightness adjustment. | |
| Claude Document Management MCP Server ailecksandr/claude-course-mcp-task This MCP server enables Claude AI to read and edit documents through natural language, leveraging tools, resources, and prompts for document management in a Ruby-based CLI application. | |
| mcp-vkontakte ailenreiko1977-tech/mcp-vkontakte Enables authenticated users to read VK profile, community, wall, dialog, statistics, product, and photo data within granted permissions, and to prepare posts or other changes that execute only after browser confirmation. It also supports co | |
| resume-markdown-mcp ailenshen/resume-markdown-mcp Write your resume in Markdown and export to PDF with AI assistance, using a built-in stylesheet and tools for conversion. | |
| mcp-guardian ailian0206/mcp-guardian A gateway that enforces permissions, sanitization, approval, and audit for AI agent MCP tool calls, with a policy engine and local proxy CLI. | |
| easyeda-bridge-mcp ailiasdesu/easyeda-bridge-codex-plugin It bridges Codex to a running EasyEDA Pro (JLCEDA) instance over the official Run API Gateway, so the agent can check bridge status, list and select connected EDA windows, and execute JavaScript against the live editor runtime. This enables | |
| cathedral-mcp ailife1/cathedral Persistent memory and identity infrastructure for AI agents. Cross-session wake protocol, drift detection, immutable snapshots, and shared memory spaces —
free hosted API |
25,101–25,150 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.