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 |
|---|---|
| ERPNext MCP cec1c/erpnext-mcp Enables AI agents to read and operate ERPNext/Frappe systems through HTTP APIs, with safe-mode approval for sensitive operations and complete storage of large request and response payloads. | |
| AutoChess MCP cecilia-coding/autochess-mcp Enables AI agents and web players to join shared auto-battler rooms, read turn snapshots, submit actions, and spectate deterministic matches with replays and pluggable packs/modes. | |
| Feedback Collector MCP ceciliomichael/feedbackjs-mcp Collects user feedback with text and image support through an Electron app, allowing AI tools to gather and process user input with customizable prompts and multiple response options. | |
| mcp-filesystem ceciliomichael/mcp-filesystem Provides advanced filesystem operations for AI-assisted development, including batch file reading, renaming, moving, project structure display, and command execution with Python virtual environment auto-activation. | |
| MCP Server Template ceciliomichael/mcp-server-template A template for building Model Context Protocol (MCP) servers using TypeScript, with standard I/O transport and Zod validation for type-safe argument handling. | |
| WA MCP cecon/wamcp Exposes each authenticated WhatsApp Web session on a Windows PC as a stateless Streamable HTTP MCP endpoint, letting MCP clients list chats, read and search messages, fetch profiles, and send text messages under per-session read-only or rea | |
| Agent Search cedarsaam/agent-search A self-hosted, MCP-native web-search backend for AI agents that provides meta-search, clean extraction, RAG with citations, and GitHub project selection. | |
| CEDARScript MCP Server cedarscript/cedarscript-mcp-server Exposes CEDARScript Editor through Model Context Protocol, enabling AI agents to perform semantic-aware code transformations with security features like path validation and dry-run mode. | |
| Bolagsinfo × Notion MCP Server cedendahlkim/bolagsinfo-notion-mcp Connects Bolagsinfo.com's Nordic B2B lead intelligence platform to Notion, enabling AI agents to search, push, and enrich company leads directly into Notion databases for pipeline management. | |
| mailpit-mcp-server cedjey/mailpit-mcp-server Enables AI assistants to read, search, and manage emails from Mailpit, an email and SMTP testing tool, during development and testing. | |
| Memory-MCP cedrainteractive/memory-mcp Shared, live team memory for Claude — a remote MCP server on Cloudflare Workers + D1. | |
| mcp-telegram-facebook cedrdjio/mcp-telegram-facebook Enables fetching videos from Telegram and reposting them to Facebook Pages, with additional Facebook Page management tools. | |
| Jina AI Remote MCP Server cedric448/jina-mcp Provides access to Jina AI's web reading, search, embeddings, and reranking capabilities. Enables URL content extraction, web/arXiv/image search, document deduplication, and relevance ranking through natural language. | |
| HubSpot MCP Server cedric46098/mcp-hubspot Enables AI assistants to interact with HubSpot CRM data through tools for creating and retrieving contacts, companies, activities, and conversations, plus semantic search over previously retrieved data. Built-in vector storage and caching h | |
| MCP GitHub Project Manager cedrica81/mcp-github-project-manager Enables AI coding agents and human project managers to turn GitHub Projects v2 into an autonomous management layer for task checkout, agent coordination, review workflows, token budgets, AI PRD generation, sprint planning, issue triage, and | |
| freellmpool cedricalexiou173/freellmpool Enables agents to discover and route chat requests across a pool of 178 enabled free LLM routes and 443 cataloged models through one OpenAI-compatible endpoint, with automatic failover, per-day usage tracking, and provider health/status too | |
| meta-ads-mcp cedricarlos07/meta-ads-mcp A self-hosted Model Context Protocol (MCP) server that gives AI agents secure, multi-tenant access to the Meta Marketing API for Facebook Ads and Instagram Ads. It enables campaign management, audience targeting, insights, lead management, | |
| mcp-grok-search cedriccmh/mcp-grok-search Enables AI assistants to search the internet using Grok's built-in web browsing capabilities, with configurable effort levels and model selection. | |
| buzz-mcp cedricconday/buzz-mcp Enables MCP clients to interact with a Buzz relay as a first-class member, allowing agents to read and write signed NIP-29 messages, coordinate via blocking replies, and manage channels with full attributed audit trails. | |
| Centrapay MCP Server cedricconday/centrapay-mcp Enables interaction with the Centrapay payments API for testing NZ payment flows, including creating, managing, and settling payment requests through natural language. | |
| xe-mcp cedricconday/xe-mcp An MCP server for the Xe Currency Data API that brings live FX rates, historical analysis, and quant-flavored tools into AI tools, working out of the box with zero credentials via Frankfurter/ECB data. | |
| VulnerabilityMCPServer cedricg-dev/nvd-mcp MCP server for retrieving vulnerability data (CVE) via HTTP, testable with MCP Inspector and OpenCode. | |
| io.github.Hylouis233/bibverify cedriclim54031/bibverify Enables AI assistants and MCP clients to verify bibliographic records and metadata consistency across multiple sources, convert identifiers such as DOI, PMID, PMCID, and arXiv to BibTeX, and inspect or check .bib files non-destructively. | |
| Typst MCP Server cedricmoore1002/typst-mcp Enables AI models to convert LaTeX snippets into Typst, validate Typst syntax, browse Typst documentation, and render Typst code as PNG images. | |
| MCP Hello World Server cedricnator/mcp_hello An example MCP server demonstrating how to create custom tools for LLMs like Claude. It provides sample tools for generating personalized greetings and performing basic arithmetic calculations. | |
| threejs-devtools-mcp cedricray/threejs-devtools-mcp Enables AI agents to inspect Three.js scenes in real time and try changes live in the browser — objects, materials, shaders, textures, lights, animation, performance and memory — then turn those previews into ready-to-paste vanilla Three.js | |
| Kingdee MCP Server cedricroux995/kingdeemcp Enables AI assistants such as Claude, Cursor, Windsurf, and Cline to query and operate Kingdee Cloud Star ERP through natural language, with 87 tools spanning purchasing, sales, inventory, production, costing, fixed assets, financial report | |
| Memorious MCP cedricvidal/memorious-mcp Provides AI assistants with long-term semantic memory capabilities through local vector-based storage. Enables storing, recalling, and managing information across sessions with complete privacy using ChromaDB, with no data ever leaving your | |
| cicash cee62/cicash MCP server for CIcash, a budget system that lets AI agents spend within bounded, expiring, revocable budgets. Provides tools for budget checks, quotes, payments, delegation, and receipts, with the private key kept server-side. | |
| AGENTmagnetMCP ceedot-rock/agentmagnet a task marketplace + reputation network for AI agents.
Agents register, complete tasks, earn credits (AgMag), and build real
reputation by staking on claims — predictions, facts, data quality —
that get proven right or wrong over time.
MC | |
| alexa-pay-mcp ceedot-rock/alexa-pay-mcp Enables an AI agent to settle HTTP 402-gated resources end-to-end: quote conversions, choose from the seller's accepted rails, sign gasless EIP-712 authorizations under enforced per-call and lifetime caps, and verify settlement receipts whi | |
| Slid Phi Labs ceedot-rock/slid-phi-mcp Lab MCP for CuNi exactness, Chamber two-key JSON seal, Agent-Rider identity, and x402 catalog. Remote https://www.slidphilabs.com/mcp or npx -y spl-pay-per-suite mcp. | |
| zrw-mcp ceedot-rock/zero-range-wave-compression MCP server for Zero Range Wave Compression, enabling efficient compression and decompression of integer sequences with record-breaking performance. | |
| Questionnaire Component Governance MCP Demo ceeeebb/mcp Enables AI agents to query component governance rules, validate component props, and generate development prompts for questionnaire editors. | |
| Crypto Price MCP Server ceeyang-ai/crypto-price-mcp-server A Model Context Protocol server for real-time cryptocurrency price data, market data, trending coins, historical charts, and currency conversion using the free CoinGecko API. | |
| Doc MCP Server ceeyang-ai/doc-mcp-server Enables AI agents to generate PDFs from Markdown or URLs, extract text, merge documents, and perform text conversions via the Model Context Protocol. | |
| freqtrade-mcp-server ceeyang-ai/freqtrade-mcp-server An MCP server for cryptocurrency trading via Freqtrade, enabling trade management, balance checks, strategy configuration, backtesting, and bot lifecycle control from any MCP-compatible AI agent. | |
| Viz MCP Server ceeyang-ai/viz-mcp-server Enables AI agents to create data visualizations like bar charts, line charts, pie charts, scatter plots, and histograms, returning inline SVG or PNG files. | |
| webx-mcp-server ceeyang-ai/webx-mcp-server An MCP server for web content extraction, providing tools to fetch clean text, extract links, query by CSS selector, and search the web via DuckDuckGo. | |
| blender-mcp ceeyang/blender_mcp Enables controlling local Blender 5.2 through natural language, providing 159 tools for modeling, materials, shaders, lighting, animation, cameras, rendering, import/export, UV, geometry, rigging, assets, and more via an MCP server. | |
| Zentao Bug MCP ceeyang/zentao_mcp MCP server for Zentao that reads bugs, extracts reproduction steps, and allows AI to update bug status after fixing. | |
| Emotion Dataset Analysis MCP Server cegme/cis6930sp26-assignment1.5 This MCP server enables users to interact with and analyze the dair-ai/emotion dataset from Hugging Face containing labeled Twitter messages. It provides tools to sample data, search text, and perform statistical analysis on emotion distrib | |
| CEI Documentation MCP Server cei-devs/mcp-cei-docs Enables searching CEI documentation, procedures, and applications via Directus API with flexible filtering and field selection. | |
| Orcorus Repository Scanner ceilingduster/mcp_security_scanner Scans GitHub repositories for security vulnerabilities by cloning, performing static analysis, secret detection, build verification, and AI-powered OWASP-aligned code review, producing a scored SECURITY.md report. | |
| claude-session celados/claude-session MCP server for programmatic lifecycle management of Claude Code sessions, supporting list, create, read, send, fork, wait, and interrupt operations. | |
| wbot celados/wbot MCP server providing an Agent-first, read-only interface to authorized WeChat conversations, with CLI and plugin support for Codex and Claude Code. | |
| shush celaldrg/shush Strips noise (passing tests, progress bars, install logs, git chatter) from command output before an AI agent reads it; never hides error lines, full output always retrievable. | |
| turkiye-mcp celaldrg/turkiye-mcp Enables AI agents to query Türkiye-specific data and logic without API keys: official central-bank exchange rates and currency conversion, live AFAD/Kandilli earthquakes, the official holiday calendar with business-day math, IBAN/TCKN/VKN v | |
| Simplified MCP Server celeryhq/simplified-mcp-server A Model Context Protocol server that enables LLMs like Claude and Cursor to manage social media accounts and create posts across multiple platforms (including Facebook, Instagram, Twitter, LinkedIn, TikTok) through Simplified's API. | |
| Deep Research Agent MCP Server celestialdust/deep-research-mcp A LangGraph-powered research agent that performs iterative web searches using Google Search and Gemini models to generate structured reports with citations. It integrates with MCP-compatible clients like Claude and Cursor to enable sophisti |
37,551–37,600 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.