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 |
|---|---|
| dsh-toolkit chengganping-ship-it/dsh-toolkit Exposes 20 deterministic tools for finance, data, content, and lifestyle tasks via MCP, A2A, and REST interfaces, enabling automation and multi-agent workflows. | |
| XAF Shadow Node chengganping-ship-it/xaf-shadow-node A stateless, anonymous MCP edge node exposing three paid JSON-RPC tools on Cloudflare Workers: digital-asset rights pre-check, C2C lead sniffing, and portfolio valuation. Requests are metered per call through an x402 testnet paywall (Base S | |
| MCP LAMMPS Server chenghao-wu/mcp_lammps A Model Context Protocol server that enables AI assistants to interact with LAMMPS for molecular dynamics simulations through natural language commands. | |
| Cloudflare Remote MCP Server chenghua926/test-mcp A template for deploying remote Model Context Protocol servers on Cloudflare Workers using Server-Sent Events (SSE). It enables the creation and hosting of custom AI tools that can be accessed via the Cloudflare AI Playground or local clien | |
| COPT-MCP chengjiale150/copt-mcp Enables AI assistants to access COPT solver documentation, example code, and citation formats via MCP protocol, reducing hallucinations when using COPT interfaces. | |
| mcp_server.py chengsiyu666-max/drone-site-selection-agent Enables MCP clients to run three-stage drone logistics site selection, load CSV/Excel data, retrieve domain knowledge, reverse-geocode coordinates, and receive progress heartbeats for long-running tasks over stdio JSON-RPC. | |
| autodl-research-pilot chengxi271-commits/autodl-research-pilot Enables Codex and other agents to discover live AutoDL GPU stock, produce cost- and time-optimized rental plans with human review, and manage approved Elastic/Pro deployments through the official API. | |
| Bayeslab ION MCP Server chengxu999/bayeslab-ion Brings industry-specific public-equity research into MCP clients, allowing reading of ION reports and queuing isolated company analyses with user approval. | |
| xinyangkb_mcp chengyangliu-lcy/xinyangkb_mcp 芯阳公司内部知识库MCP服务器，封装内部搜索API，供Codex和OpenCode调用以检索知识库信息。 | |
| mcp-utility-server chengyue2025/mcp-utility-server A Python-based MCP server providing essential utility tools: web fetching, current time, and calculator functionality. | |
| opera-houdini-mcp chengziiii/opera-houdini-mcp A Houdini MCP server fork for CsrLib-Houdini workflow, providing enhanced tools for scene management, node discovery, graph editing, and safe code execution with tiered security policies. | |
| Stock SDK MCP Server chengzuopeng/stock-sdk-mcp Provides comprehensive stock market data (A-shares, Hong Kong, US) including real-time quotes, K-lines, technical indicators, sectors, futures, and options, with built-in AI Skills and MCP Prompts for financial analysis. | |
| lmemory chenhongjun/lmemory Enables workspace-scoped structured user data and long-term memory through MCP, including entities, relations, notes, and image search with PostgreSQL and pgvector. | |
| Data Analytics MCP Toolkit chenjellay/trying_ibm_mcp An MCP server that provides data visualization and machine learning tools, featuring automated intent-based pipeline routing for data cleaning and model training. It enables LLMs to process CSV or JSON data to generate visual charts, perfor | |
| mcp_supervisor_py chenjordan/mcp_supervisor_py A Python scaffold for an MCP-style supervisor that breaks user tasks into steps, routes them to workers, retries on failures, and aggregates outputs. | |
| Smart File Organizer MCP Server chenjunwei1230-dotcom/smart-file-organizer-mcp Lets AI assistants analyze and organize local directories by file type, with dry-run support and safe sorting. | |
| easy-mysql-admin-mcp chenkumi/easy-mysql-admin-mcp High-privilege MySQL admin MCP server for database and user/grant management. | |
| easy-mysql-mcp chenkumi/easy-mysql-mcp Enables AI assistants to inspect and query a MySQL database through safe, structured tools, including schema discovery and read-only queries. | |
| easy-pg-admin-mcp chenkumi/easy-pg-admin-mcp High-privilege PostgreSQL admin MCP server for database and role/grant management. | |
| Yunleng chenlaoshiyf/yunleng A camera vision MCP server that lets AI agents capture frames, control camera parameters, recognize gestures, detect objects, and analyze scenes via local vision models. | |
| Taskade MCP Server chenle2228/mcp Enables Claude, Cursor, VS Code, Windsurf, and other MCP clients to manage workspaces, projects, tasks, and AI agents through natural language, using a hosted OAuth server or local stdio package. | |
| Joplin MCP Server chenle6992/joplin-mcp Enables AI assistants to search, read, create, update, organize, tag, import, and restore notes and notebooks in the Joplin note-taking app via the Model Context Protocol. | |
| U.S. Census Bureau Data API MCP chenle70/us-census-bureau-data-api-mcp Enables AI assistants to access official Census Bureau statistics through the Census Data API and other official sources, supporting dataset discovery, geography resolution, FIPS lookup, and aggregate data retrieval. | |
| Basecamp MCP Server chenle78731/basecamp-mcp-server Enables MCP-capable clients to read and manage Basecamp 3 projects, todos, messages, card tables, documents, uploads, and search through OAuth-authenticated API calls. | |
| pfSense MCP Server chenle8820/pfsense-mcp-server Connects Claude Desktop, Claude Code, or any MCP client to a pfSense firewall so users can query, diagnose, and change firewall rules, NAT, VPNs, DNS, DHCP, certificates, and other subsystems in natural language. Every destructive action is | |
| io.github.Hylouis233/bibverify chenle88236/bibverify Enables AI assistants to check BibTeX records for bibliographic existence and metadata consistency by querying identifier-first providers like Crossref, OpenAlex, PubMed, DBLP, and arXiv and scoring title, author, year, venue, and page evid | |
| dbt-doctor chenlebraun05/dbt-doctor Enables AI assistants to audit dbt project quality, profile warehouse data, detect schema drift, suggest tests, and generate non-destructive schema.yml documentation through natural language. | |
| 4NEC2 MCP Server chenlei2019-shanghai/4nec2-mcp Enables MCP clients to drive the 4NEC2 NEC-2 engine for natural-language antenna modeling and simulation, including building Yagi models, calculating impedance/SWR/gain/front-to-back ratio, sweeping frequency, parsing .out files, optimizing | |
| byob chenlememon371/byob Enables AI coding tools to drive your real, already-logged-in Chrome browser through an extension-based local MCP bridge, with no debugging port or headless setup required. It provides tools for navigating pages, reading content, clicking, | |
| Teams MCP chenlen45/teams-mcp Enables AI assistants to interact with Microsoft Teams and Microsoft Graph APIs for user and team management, channel and chat messaging, message editing and deletion, file upload/download, and advanced message search. | |
| byob chenleschulz89147/byob Enables AI assistants to drive the user's real, already-logged-in Chrome browser locally, so they can read and navigate pages, click, type, fill forms, take screenshots, and inspect cookies, tabs, console, and network traffic without headle | |
| read-website-fast chenletyurin/mcp-read-website-fast Enables AI agents and IDE workflows to fetch and crawl webpages locally, extracting readable content and converting it to token-efficient Markdown with preserved links. | |
| Basecamp MCP Server chenlewatson/basecamp-mcp-server Enables MCP-capable clients to read and manage Basecamp 3 projects through OAuth-authenticated API calls, with tools for projects, todos, messages, card tables, documents, uploads, comments, events, webhooks, and search. | |
| email-mcp chenliangchong/email-mcp Enables receiving and sending email via IMAP and SMTP across multiple accounts, with tools for listing, searching, reading, replying, and managing messages. | |
| knowledge-graph chenliangchong/knowledgegraph Long-term memory system for AI agents that accumulates domain expertise through mentorship, automatically recalls relevant knowledge, and supports memory decay and growth with anti-fabrication. | |
| MySQL MCP Server chenlinyang/mcp-server-mysql A Model Context Protocol server that provides secure access to MySQL databases through SSH tunnels, enabling LLMs to inspect schemas, execute SQL queries, and manage data with configurable permissions. | |
| FigmaExporterMcp chenlongbetterapp/figmaexportermcp A local bridge that lets MCP clients inspect, export, and modify Figma files through a development Figma plugin. | |
| github_local_manager chenlu882/github-local-manager Enables Codex to list local GitHub projects and tools, check npm tool updates, prepare update plans without executing them, and open the local management panel. | |
| Feifei Proxy MCP chenm1xuexi/feifei-proxy-mcp A service that converts existing MCP protocols (stdio/sse) to streamable\_http transmission type, allowing compatibility between different MCP implementations. | |
| ts-screenshot-mcp chenmiaozhan2024/ts-screenshot-mcp Enables capturing full-screen or selected region screenshots on Windows, saving them as PNG files locally and returning image data via MCP. | |
| openanalyst-mcp-server chenmo0414/tukey MCP server that turns coding agents into data analysts: attach CSV/Parquet/JSON/XLSX or databases, profile data, run read-only SQL, and render Vega-Lite charts as SVG files. | |
| MCP Example Express chennachandrika/mcp A basic example of developing and running serverless Model Context Protocol (MCP) using Netlify Functions, demonstrating how to deploy and access MCP functionality through customized URLs. | |
| iServ MCP chenning42/iserv-mcp Enables interacting with iServ school portals to read parent letters and attachments, mark letters as read, access timetables, and submit guardian sick notes. | |
| Apple Reminders MCP chenningling/mcp-applereminders A tool that enables creating and querying Apple Reminders through natural language, allowing users to set reminder content (title and notes) and specify reminder date/time. | |
| Xiaohongshu Search & Comment MCP Server chenningling/redbook-search-comment-mcp A Playwright-based tool that automates Xiaohongshu (Little Red Book) interactions, enabling users to login, search for notes, view content, and post intelligent comments through natural language commands. | |
| Xiaohongshu (RedBook) MCP Server chenningling/redbook-search-comment-mcp2.0 Enables automated interaction with Xiaohongshu (Little Red Book) platform including searching posts, retrieving content and comments, and posting AI-generated comments with persistent login support. | |
| @chenpu17/web-bridge-mcp chenpu17/web-bridge-mcp An MCP server for web search, web fetching, and Context7 documentation tools with proxy support, designed for internal network environments. | |
| Torna MCP Server chenqi146/torna-mcp Bridges Torna API documentation system with AI assistants, enabling natural language search, API discovery, detailed documentation retrieval, and curl command generation for your Torna-managed APIs. | |
| MOSS XiaoZhi MCP chenqizhi1/moss-xiaozhi-mcp Provides visual recognition and PTZ camera control for DIY MOSS (ESP32) smart assistants, bridging cloud AI with local camera capabilities via WebSocket. | |
| Telegram MCP Server chenqwwq/telegram-mcp Enables interaction with the Telegram Bot API via the Model Context Protocol to send, edit, and delete messages, photos, and videos. It allows Claude to manage Telegram communications and fetch bot updates through natural language commands. |
38,201–38,250 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.