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 |
|---|---|
| QiuChi chain-engine/x-qiuchi A production-grade MCP server framework with plugin system, middleware pipeline, and multi-transport support for building LLM tool services. | |
| homelab-mcp chain-p/homelab-mcp Exposes a Raspberry Pi homelab's systemd service health, disk usage, CPU temperature, and LAN game-server status as read-only MCP tools, letting MCP clients answer questions like "how's the homelab doing?" without SSHing in manually. | |
| whisper-mcp chain-p/whisper-mcp Enables MCP clients to transcribe audio/video files locally, generate SRT subtitles, and burn captions into videos via tool calls, without a cloud API. | |
| Keplr Wallet MCP chainapsis/keplr-wallet-mcp Your AI-powered wallet for Cosmos. Send, stake, swap — just ask. | |
| ChainAware Behavioural Prediction MCP Server chainaware/behavioral-prediction-mcp The Behavioural Prediction MCP Server provides AI-powered tools to analyze wallet behaviour prediction,fraud detection and rug pull prediction. | |
| agentkey chainbase-labs/agentkey AgentKey is the execution layer between AI agents and the real internet. One MCP install gives your Claude / Cursor / n8n agent unified access to web search, scraping, and 20+ social platforms — no API juggling, one bill. | |
| Cryo MCP chainbound/cryo-mcp Enables natural language querying of blockchain data, including blocks, transactions, logs, and more, powered by Cryo and Reth, with optional micropayment integration via Payflow. | |
| codegraph-mcp chainchen1103/codegraph-mcp Provides efficient code navigation and graph-based analysis for AI agents, enabling symbol resolution, callers, implementations, and type schemas with minimal token usage. | |
| TOONer chaindead/tooner MCP proxy that wraps any MCP server and transparently converts JSON responses in tools/call to TOON format — a token-efficient alternative to JSON optimized for LLMs (~40% fewer tokens). | |
| ChainFETCH MCP Server chainfetch/chainfetch-mcp-server Enables AI-powered analysis of Ethereum blockchain data through semantic search, natural language queries, and structured filtering. Provides comprehensive access to addresses, transactions, blocks, tokens, and smart contracts with real-tim | |
| @chainpayto/mcp-server chainpayto/mcp-server Enables AI agents to directly operate ChainPay cryptocurrency payment system, including order creation, balance checks, and withdrawals. | |
| automation-health-mcp chainwright/automation-health-mcp An MCP server for auditing automation health, finding failures, stale logs, and non-functional endpoints that report success while quietly failing. | |
| chainz-sentinel-mcp chainz-blockchain/binance-agent-mcp Enables Binance Agent OS to perform pre-trade risk assessment, parse natural language trade intents, benchmark yield arbitrage opportunities, and execute hedged trades with automated safety gating. | |
| music-assistant-mcp-plus chair15/music-assistant-mcp-plus A comprehensive MCP server that enables AI assistants to control music playback, manage users and access, configure providers, and administer a Music Assistant setup through natural language commands. | |
| @staticpayload/gemini-mcp chaitanya-archive/gemini.mcp Bridges Google's Gemini CLI to MCP-compatible AI assistants, enabling prompt execution, model listing, and raw CLI commands. | |
| NotePilot chaitanya-jadhav11/notes-mcp A Python MCP server that exposes note management tools (create, search, update, delete notes) over stdio, enabling Claude AI to manage notes through natural language conversation. | |
| triage-mcp chaitanya40/postgres-mcp-bug-triage Enables read-only, time-boxed Postgres queries with SQL validation and PII masking, supporting automated bug triage through Claude. | |
| Fifth Elephant MCP Server chaitanyaatlan/fifth-elephant-mcp-workshop A demonstration MCP server providing basic tools for returning greetings and performing mathematical addition. It serves as a practical workshop guide for setting up and configuring Model Context Protocol servers from scratch using Python. | |
| MCP Database Tools Server chaitanyaiscoding/mcp_database_tools- An MCP server designed to automate Django database setup and management, including PostgreSQL database creation and extension configuration. It enables users to update environment files and execute Django management commands through integra | |
| YouTube MCP Server chaitanyapandey09/youtube-mcp-server Enables AI assistants to extract educational content from YouTube videos by fetching timestamped transcripts and visually meaningful frames, returning them as base64 JPEGs for analysis. | |
| Job Pilot chaitu0608/jobpilot A local-first MCP server that lets any MCP agent drive a job-search cockpit: scan for roles, inspect and click/type in your real logged-in Chrome tabs via a built-in extension, capture postings, gate eligibility, pre-fill applications witho | |
| reprove chaitu0608/reprove Enables a coding agent, over stdio MCP, to scan a project for security flaws, list and explain findings, propose and apply patches, and re-run recorded exploits to prove each fix actually holds on the patched app. Tools include scan_project | |
| DoorDash MCP Server chaituredd/doordash-mcp-server Enables AI agents to search restaurants, place delivery orders, and track real-time delivery status using the DoorDash Drive API. It includes a built-in mock data mode that allows for testing and demonstrating delivery lifecycles without re | |
| WinCommander chaiyuhao/win-commander Turns any Windows device into a remotely controllable MCP toolset, allowing a mobile AI agent to execute CLI, GUI, browser, and system commands on Windows without an API key. | |
| Proxmox MCP Enhanced chajus1/proxmox-mcp-enhanced Provides a complete MCP server for managing Proxmox VE infrastructure with 115 specialized tools, enabling AI assistants and automation systems to perform complex virtualization tasks seamlessly. | |
| Singapore News MCP Server chakarai1234/news_mcp Provides real-time news feeds from major Singapore news sources including The Straits Times, Business Times, and Channel News Asia. Delivers live news updates through Server-Sent Events for up-to-date information access. | |
| GraphQL MCP Server chakit22/graphql-mcp-server A generic MCP server that converts .graphql query files into tools for Claude, enabling interaction with any GraphQL API without coding. | |
| Ollama MCP Server chakkritte/ollama-mcp A lightweight MCP server that exposes Ollama Cloud models as tools for chat, web search, and web fetching, with dynamic model switching. | |
| MCP Filesystem Assistant chakorabdellatif/filesystem-mcp-with-fastmcp-server An AI-powered file manager that enables natural language filesystem operations including reading, writing, organizing, and managing files within a secure sandboxed workspace through a web interface. | |
| Semiconductor Component RAG Search chakradharkalle03-arch/mcp2 Enables semantic search and question-answering over semiconductor component data stored in Excel files using ChromaDB vector database and HuggingFace language models through a RAG pipeline. | |
| Personal Research Assistant MCP chakri01/research-assistant-mcp Enables semantic search and conversational querying across a personal research library of PDFs, DOCX, and other documents using a vector database. It provides tools for document summarization, finding related papers, and high-accuracy retri | |
| ripple chakri192/ripple A data-incident triage agent for DataHub that traverses downstream lineage, ranks affected assets by criticality, resolves owners, and records incidents back into the catalog. | |
| Excel MCP Server chakri444-web/excel-mcp Gives Claude deep tool-level control over Microsoft Excel files (.xlsx, .xlsm, .csv, .tsv) with 164 tools across 24 modules for reading, writing, formatting, formulas, charts, data analysis, and more. | |
| MCP Leave Manager Server chalamalasettichamundeswari/mcp_leave_manager_server Enables managing employee leave requests, balances, and approvals through natural language with Claude Desktop, using SQLite for persistence and fuzzy name matching. | |
| Odoo MCP server chaldeastudios/chaldea_mcp Enables MCP clients to query, create, update, and delete records in a self-hosted Odoo instance, with tools automatically derived from live model introspection. | |
| IDA Pro MCP Server chalermchai260/mcp-server-idapro Enables AI assistants to control IDA Pro for reverse engineering and binary analysis by running Python scripts and querying binaries. It supports retrieving strings, imports, exports, and functions, searching immediate values, text, and byt | |
| IMAP MCP Server chalermchai44/imap-mcp-server Enables AI assistants to search, read, send, reply to, organize, and bulk-delete email across multiple IMAP/SMTP mailboxes, with connection pooling and AES-256-encrypted credential storage. Supports 15+ providers through a web-based setup w | |
| UI5 MCP Server chalermchai67/mcp-server Enables agentic AI tools to scaffold UI5 applications and integration cards, fetch API documentation, validate manifests, run UI5 linter, and apply UI5 development guidelines. | |
| FirstData MCP chalermchai704/firstdata Enables users and AI agents to turn natural-language data questions into authoritative primary-source recommendations with verified URLs, metadata, APIs, and step-by-step website navigation for retrieving the original data. | |
| locklens chalermchai770/locklens Enables users to audit npm, Yarn, and pnpm lockfiles from local directories or remote Git repositories via a stdio MCP interface, with configurable vulnerability thresholds, registry, dev-dependency skipping, retry, and text/JSON output. | |
| AWS FinOps MCP Server chalermchai7797/aws-finops-mcp-server Enables users to analyze AWS cloud costs, audit for wasted resources like stopped EC2 instances and unattached EBS volumes, and check budget status through natural language in any MCP-compatible AI assistant. Supports multi-profile and mult | |
| MiniMax-Coding-Plan-MCP chalermchaicampos/minimax-coding-plan-mcp Enables coding-plan users to perform AI-powered web searches and analyze images from URLs or local files via MCP clients, supporting code-development workflows. | |
| MCP Proxy Server chalermchaidabrowski997/mcp-proxy-server Enables clients to connect to multiple backend Model Context Protocol servers through a single unified interface, aggregating and routing their tools and resources while supporting authentication and concurrent sessions. | |
| threejs-devtools-mcp chalermchaifernandez4464/threejs-devtools-mcp Enables AI agents to inspect and live-edit Three.js scenes in the browser — objects, materials, shaders, textures, lights, animation, performance and memory — then turn those previewed changes into ready-to-paste code. It also supports webs | |
| Yolfi MCP Server chalermchaifoster024/yolfi-agent Enables AI coding agents to add stablecoin checkout, payment links, payment status checks, webhook verification, and webhook-based entitlements to applications. | |
| Project OS for Codex chalermchaigauck/project-os-for-codex Enables AI agents to read Git-backed project context and append validated, audited, idempotent progress events through short-lived, scoped credentials, supporting resumable work and safer handoffs. | |
| Frappe MCP chalermchaiklein07691/mcp Enables Frappe Framework apps to function as Streamable HTTP MCP servers, with registered tools callable through a WSGI-compatible endpoint. | |
| Luma MCP chalermchaikowalski20960/luma-mcp Provides a unified image-understanding tool for AI assistants without native vision, letting them analyze screenshots, error messages, UI layouts, and documents via multiple vision LLM providers. It supports local files, remote URLs, Data U | |
| remote-mcp-server-authless chalermchaile/remote-mcp-server-authless Deploys a stateless remote MCP server on Cloudflare Workers that requires no authentication, enabling tool calls from remote MCP clients while remaining compatible with legacy clients. | |
| remote-mcp-server-gemini chalermchaile/remote-mcp-server-gemini Enables deploying a stateless remote MCP server on Cloudflare Workers without authentication, supporting the MCP 2026-07-28 spec and legacy client tool calls. |
37,801–37,850 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.