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 |
|---|---|
| InstaServer codesbyfebin/instaserver Enables AI agents to deploy and manage Docker containers on your own machine via MCP tools, providing public HTTPS URLs through free Cloudflare quick tunnels. | |
| PostgreSQL MCP Server codescept/postgres-mcp Enables users to perform SQL query execution, schema exploration, and performance analysis on PostgreSQL databases through any MCP-compatible client. It prioritizes security with read-only protection by default and provides guided workflows | |
| LeadSpark MCP codeserg21/leadspark-mcp Enables AI agents to research companies and find contacts with structured data from multiple free sources, including company info, tech stack, and email addresses. | |
| ClimateTriage MCP Server codeshark-net/climate-triage-mcp Enables users to search and filter open source issues related to climate change and sustainability projects through the ClimateTriage API. | |
| ShopSignal codesk90/shopsignal-mcp DTC competitor intelligence: catalog snapshots, price history, cross-brand product comparison, and drop/restock detection for 84 Shopify-powered brands. Pay-per-call via Apify. | |
| AutoCAD MCP codesknight/autocad-mcp Enables AI clients like Claude Desktop to control AutoCAD through natural language commands using the Model Context Protocol. | |
| AtlasOS codesmiths2026/atlasosv1 Enables AI assistants to orchestrate multi-step workflows by converting natural language into executable plans, coordinating tools, agents, and services via the Model Context Protocol. | |
| MCP Chess.com Server codesnippetsforall/mcp-server-basic-chess-dot-com-apis Provides access to Chess.com's public API, allowing AI assistants to fetch player information and statistics. | |
| mcp-dev-brasil codespar/mcp-dev-latam 37 MCP servers for agentic commerce and Brazilian services. Covers Stripe ACP, x402 (Coinbase), AP2 (Google), Google UCP, plus 14 traditional Brazilian payment rails, fiscal, banking, communication, logistics, ERP, identity, and crypto APIs | |
| read_file MCP Server codespicer/ollama-react-agent Exposes the agent's sandboxed file tool over stdio so any MCP client can retrieve the contents of a UTF-8 text file inside the working directory, with failures returned as recoverable error strings instead of exceptions. It lets the same Re | |
| mcp-router-local codespriha/mcp-router-local Aggregates multiple MCP servers behind a single local endpoint, letting LLM clients connect to one router that exposes a unified set of tools, resources, and prompts. | |
| Terraform Plan Analyzer MCP Server codessrockman/terraform-plan-mcp-server Provides tools to execute Terraform commands, analyze plan outputs for resource changes, and generate detailed markdown reports. It supports custom environment variables and filtering patterns to streamline infrastructure analysis and manag | |
| cs-agent-mcp codestable/cs-agent-mcp A local stdio MCP service that unifies coding agents like Codex and Claude into cs_agent_* tools, enabling the root agent to create, invoke, and manage child agents with recursive delegation. | |
| Raindrop.io MCP Server codester1000/raindrop-mcp Enables AI agents to access and manage Raindrop.io bookmarks, collections, tags, and highlights through the Model Context Protocol. Supports CRUD operations, advanced search, file uploads, and bulk editing of bookmarks. | |
| sevdesk-mcp codestra/sevdesk-mcp Integrates with the sevdesk German accounting API, providing 76 tools for full CRUD operations across contacts, invoices, vouchers, orders, credit notes, bank accounts, transactions, parts, tags, addresses, and communication ways. | |
| x402-stellar-kit/mcp codestrux/x402-stellar-kit Enables HTTP 402 payment protocol interactions on Stellar, allowing payment intent probing, guarded paid fetches, and budget status queries. | |
| Plone Dynamic Pages MCP Server codesyntax/cs-dynamicpages-mcp Enables LLMs to manage Plone sites with dynamic page layouts, supporting CRUD operations on content and layout components via the cs_dynamicpages architecture. | |
| @hyperscript-tools/mcp-server codetalcott/hyperscript-tools MCP server providing parser-backed validation, parsing, documentation, and editor assistance for AI agents working with _hyperscript. | |
| Mutual-Funds-Groww-MCP codeterrayt/mutual-funds-groww-mcp MCP server that lets AI assistants search and analyze live Indian mutual funds via Groww's API, supporting filters and detailed fund diagnostics. | |
| PaaSMCP codevanzi/paasmcp Enables AI agents to deploy and operate self-hosted applications on Linux servers and homelabs through Docker Compose, including zero-config buildpack builds, encrypted secret storage, one-second PostgreSQL/Redis provisioning, and one-call | |
| codeweb codeweb-hq/codeweb An MCP server that maps code symbol relationships and provides tools for impact analysis, caller lookup, and duplicate detection to help coding agents understand codebases efficiently. | |
| Computer Use codewhale-hq/codewhale-cu-plugin Enables MCP hosts to observe and operate macOS apps by reading accessible controls, entering text, clicking, scrolling, capturing screenshots, and performing on-device OCR, with background app control and explicit human authorization. | |
| Weather MCP Server codewith1984/weather-mcp-server-typescript A Model Context Protocol compatible server that provides weather information for any city using Ollama's LLM capabilities through an exposed get-weather tool. | |
| Stock Analyzer MCP codewithadvi/stockanalyzermcp Production-grade MCP server that enables AI assistants to access real-time financial market data with intelligent fallback mechanisms, supporting stock prices, comparisons, fundamentals, and market summaries via Yahoo Finance and CSV. | |
| reforge-mcp codewithaiyan/reforge-mcp An MCP server that connects Claude Code to your codebase for automated code cleanup with scanning, planning, atomic fixes, and rollback safety. | |
| jupyter-kernel-mcp codewithcheese/jupyter-kernel-mcp Enables AI agents to execute Python, TypeScript, and JavaScript code in persistent Jupyter kernels with stateful variables and imports across interactions. | |
| OpenZeppelin MCP Server codewithdpk/openzippelin-mcp Enables users to generate and retrieve secure, audited smart contract templates from OpenZeppelin including ERC20, ERC721, ERC1155 tokens, access control, governance, and finance contracts through natural language prompts. | |
| netdiag-mcp codewithehtisham/netdiag-mcp Provides read-only network diagnostics for a target host, including DNS, TLS, HTTP, and registry data. | |
| Robots Compliance Scrape Workflow MCP Server codewithkate/webscraping-mcp-server An MCP server for AI-agent web scraping that enforces robots.txt compliance and requires user confirmation of scrape plans, packaging scraped data with provenance evidence. | |
| MCP Math Server codewithmsunke/mcpmathtools Provides basic mathematical operations including arithmetic, square root, and number theory functions like GCD and LCM. Built with TypeScript and includes proper error handling for edge cases like division by zero. | |
| mcp-blockend codewithnuh/blockend Blockend MCP Server lets AI coding agents manage production-ready backend building blocks directly in a project. Agents can discover available blocks, analyze project configuration, preview file changes, install backend utilities, diagnose | |
| MCP Server + Clerk OAuth codewithpassion/cf-mcp-server-clerk A remote Model Context Protocol server template for Cloudflare Workers with built-in Clerk OAuth authentication and role-based access control. Enables secure deployment of MCP servers with user authentication and customizable tool access ba | |
| agnt-lock codewithriza/agnt-lock Prevents AI agents from overwriting each other's work by providing file locking and coordination via MCP tools. | |
| Astrail codewithriza/astrail Enables importing OpenAPI, Swagger, Google Discovery, GraphQL, and HTTP MCP definitions and generating typed agent tools whose calls map to HTTP endpoints under explicit execution policies such as allow, approval, or block. A hosted runtime | |
| StudyFlow AI MCP Server codewithsarthak21-oss/amazon-developer-hackathon-studyflow-ai Enables students to create and track study tasks, retrieve prioritized daily study plans, complete sessions, and monitor progress through MCP tools over Streamable HTTP. | |
| agentic_actions_mcp codewithyasho/mcp_deployment Enables file IO operations and terminal commands via agentic actions using the MCP protocol. | |
| ragify_docs_mcp codewithyasho/ragify_docs_mcp Scrapes documentation sites, chunks and embeds content locally, then retrieves relevant passages for queries. Enables agents to ask questions grounded in documentation. | |
| obsidian-mcp codex-tm/obsidian-mcp MCP server for Obsidian vaults — multi-brain manager with templates, persistent registry, search, CRUD, frontmatter, wikilinks and context bundling. Works with Hermes Agent and Claude Code simultaneously. | |
| Adobe Commerce / Magento MCP codexpect/adobe-commerce-mcp MCP server for integrating with Adobe Commerce and Magento REST API to manage products, categories, customers, pricing, and attributes. | |
| Gobernador IA MCP Server codexpromptusiuris/gobernador-ia-mcp-server- MCP server de auditoría de compliance de IA que expone el motor de reglas de Gobernador IA como tools para agentes Claude, contra Ley 21.719 (Chile), ISO/IEC 42001:2023, y el EU AI Act. | |
| stackoverflow-mcp-server codexveritax/stackoverflow-mcp-server Enables AI assistants to search and access Stack Overflow content, including questions, answers, and error solutions. | |
| Morrow Desk MCP Server codeyogi911/able Enables operators to manage support desk operations, including case queues, customer relationships, and communications, through an agent-first MCP interface with exact lifecycle and authorization controls. | |
| Shopify MCP Server codeyogi911/shopify-mcp Connects your Shopify store data to Claude Desktop, enabling access to products, orders, customers, inventory, and more through natural language. | |
| Yahoo Mail MCP Server codezella/yahoo-mail-mcp-server Enables users to manage their Yahoo Mail account through natural language, including listing, reading, searching, deleting, archiving, flagging, and moving emails via IMAP. Supports both local Claude Desktop integration and remote access wi | |
| mcp-oauth2-token-provider codezerowork/mcp-oauth2-token-provider Acts as an authenticated proxy between AI IDEs and remote MCP endpoints, handling OAuth2 client_credentials token generation and transparently injecting bearer tokens into all proxied requests. | |
| reasoning-engine-mcp codibre/reasoning-engine-mcp MCP server for deep algorithmic and mathematical reasoning, wrapping any OpenAI-compatible LLM endpoint to return only the final distilled answer without reasoning traces. Supports per-call model and endpoint overrides, defaulting to vibeth | |
| Cloudflare MCP codigoreactivo/cloudflare-mcp Remote MCP server to manage Cloudflare domains, zones, and DNS records via OAuth authentication. | |
| e2e-verifier coding-crashkurse/agentic-e2e-testing---mcp-server Reproduces and verifies website bug tickets in a real browser, returning annotated video, Playwright trace, screenshots, logs, and a verdict per acceptance criterion. | |
| click-to-mcp coding-dev-tools/click-to-mcp Converts any Python Click or Typer CLI into an MCP server automatically — zero-code transformation that introspects CLI commands and exposes them as MCP tools. | |
| worktracker coding-nyx/worktracker Enables unified management of work items from multiple tools through a kanban, providing CRUD, status transitions, comments, links, enrichment, dispatch, and board tools via MCP. |
39,801–39,850 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.