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 |
|---|---|
| Open Reach abangbroy/ooh_reach_mcp An MCP server for out-of-home (OOH) site-reachability tooling that provides geospatial catchment scoring and multi-site comparison for billboard/ad-site evaluation using open data. | |
| osm-mcp abangbroy/osm-mcp An MCP server that provides live geospatial data such as geocoding, POI search, isochrones, and area density from open data sources to LLM clients like Claude, Cursor, or Claude Code. | |
| EduChain MCP Integration Server abanindra3/educhain-mcp An MCP-compatible Flask server that integrates with the educhain Python library to dynamically generate educational content for Claude Desktop, including multiple-choice questions, lesson plans, and flashcards. | |
| mcp-google-drive abanka27/mcp-google-drive Enables reading and searching Google Drive files, Google Docs, and Google Sheets via a CLI or MCP server, with support for section-based content extraction and Markdown import. | |
| catalog-agent abanobnageh/catalog-agent Enables MCP clients to search a product catalogue and safely change product prices and stock. It offers bounded read and write tools with version-checked, dry-run updates, least-privilege access modes, and actionable errors that help the mo | |
| hacker-news-mcp abanoub-ashraf/hacker-news-mcp Provides Hacker News tools with founder-research features for analyzing Show HN launches, Ask HN discussions, and extracting startup insights. | |
| mcp-server-starter-demo abanoub-rodolf/mcp-server-starter-demo A minimal TypeScript MCP server that provides echo and text_stats tools for text validation and word/character counting over stdio. | |
| ABAP MCP Server SDK (mcp2) abap-ai/mcp2 A stateless ABAP SDK for building MCP servers that support tools, resources, prompts, and tasks. It targets the 2026-07-28 protocol while maintaining backward compatibility with legacy versions. | |
| sap-mcp abap-studio/sap-mcp MCP server for SAP S/4HANA via the ADT API, enabling querying and reading SAP systems with production write protection. | |
| abap-adt-mcp abap0917/abap-adt-mcp Enables AI agents to read, write, activate, and transport ABAP code in SAP systems via ABAP ADT REST API, without needing SAP GUI. | |
| MCP ABAP ADT abap0917/abap-mcp-adt-main MCP server for SAP ABAP development, enabling AI assistants to read, create, update, and delete ABAP objects via ADT APIs. | |
| GET4AGENT MARKET abay94/get4agent-mcp MCP server for the AI-agent economy: free Kazakhstan / Central-Asia utilities (Kazpost parcel tracking, IIN/BIN & IBAN validation, GLEIF LEI lookup, KZT/ECB FX rates, weather) callable with no account, plus per-call purchase of KYA-verified | |
| @abbababa/mcp abba-baba/abbababa-mcp An MCP server providing 46 tools for A2A commerce discovery, agent orchestration, and dispute protection, enabling marketplace search, agent registration, escrow disputes, and more. | |
| mystic-tutor-mcp abbabon/mystic-tutor-mcp Provides AI assistants with real-time access to Magic: The Gathering card data, prices, rulings, search, and synergy discovery via the Scryfall API. | |
| DeepSeek-MCP abbas-f-r/deepseek-mcp MCP server that enables Claude Code to delegate tasks to DeepSeek and other LLMs, offering 20 tools for code review, analysis, testing, and code generation. | |
| Secure MCP Starter abbas-zaidi-5/secure-mcp-starter A reference MCP server demonstrating authentication, authorization, approval workflows, and audit logging for a notes domain with secure defaults. | |
| Data Engineer Agent abbasnosrat/mcpserveragent Enables AI agents to interact with a retail cars database using SQL queries. Supports adding new car advertisements and searching existing cars based on user preferences through natural language. | |
| comsats-timetable-mcp abbdullahjan/comsats-timetable-mcp Enables fetching and analyzing COMSATS University timetables via natural language, bridging Claude Desktop with the live university timetable system. | |
| oss-mcp abbilville/oss-mcp Enables cross-repository architecture discovery and dependency routing across multi-service codebases, with automated scanning and batch AST indexing for AI agents to trace request lifecycles and navigate service boundaries. | |
| QuantLive MCP abbmahdin/quantlive-mcp Exposes trading operations tools (CSV reconciliation, XAUUSD signals, walk-forward backtests, position audits) over MCP with x402 payments. Enables agents and workflows to run micro-trademax trading ops and reconcile broker vs ledger data. | |
| foro-demo-mcp abboskhonov/foro-demo-mcp This server enables AI agents using MCP to test round-trip communication, roll dice, store and recall in-memory values, verify caller identity via authenticated headers, and make authenticated outbound calls to a backend on behalf of the ve | |
| Shopmonkey MCP Server abbottdevelopments/shopmonkey-mcp-server Enables AI agents to interact with the Shopmonkey REST API to manage shop management data including work orders, customers, vehicles, and inventory. It provides 33 tools across 9 resource groups with built-in support for rate limiting, conc | |
| golive-mcp abbylester1/golive-mcp Enables AI agents to deploy code to any hosting provider by creating PRs, building, and verifying health checks, all from a single natural language command. | |
| mcp-claudecode abc407859-collab/mcp-claudecode Implements 41 tools from Claude Code, including bash, file operations, web search, task management, and more, all accessible via MCP protocol. | |
| sync-vault-agent abcamus/sync-vault-agent An MCP server that enables AI assistants to search, read, and manage files across multiple cloud drives (Baidu, Aliyun, 115, OneDrive, Quark) through a unified interface. | |
| Gaddi abcastor/gaddi Lets AI agents work in existing Chrome tabs using the browser and logins you already have, while routing sensitive actions through signed owner approval. | |
| qa-ai-agents abchahal/qa-ai-agents Enables automated QA testing by running a pipeline of AI agents that generate test scenarios, architect test layers, write Playwright tests, and review code, all grounded in feature requirements and API contracts. | |
| requirements-risk-analyser abchahal/requirements-risk-analyser AI-powered pipeline that analyzes user stories and PRDs for gaps, ambiguities, and missing acceptance criteria before coding, with MCP tools for requirement analysis and risk reporting. | |
| jms-mcp abchw517/jms-mcp Enables MCP clients to expose selected JumpServer 3.10.15 REST API operations as tools over Streamable HTTP or SSE, with configurable read-only filtering and separate inbound/upstream authentication. | |
| MCP Server Deepdive abckiran/mcpserverexample A Model Context Protocol server implementation that provides mathematical operations and extensible tools for deepdive deployment scenarios. | |
| ezbookkeeping-mcp-server abco20/ezbookkeeping-mcp-server MCP server for the ezBookkeeping HTTP API, enabling read and write access to transactions, accounts, categories, tags, templates, analytics, and exchange rates via natural language. | |
| IMAP MCP abconsultdev/imap-mcp Lets Claude Desktop read any IMAP mailbox and send emails via SMTP, with support for multiple mailboxes and locally stored credentials. | |
| xmcp Application abcprintf/mcp-server-app A template/starter project for building MCP servers with structured directories for tools, prompts, and resources that are automatically discovered and registered. | |
| mcp-cli-catalog abcpro1/mcp-cli-catalog An MCP server that publishes CLI tools on your machine for discoverability by LLMs | |
| google-suite-mcp abcreativ/google-suite-mcp Read and write Google Sheets, Docs, Drive, and Apps Script from any MCP client. 82 tools with OAuth2 auth, tested against live Google APIs. | |
| Google Play Console MCP abd3lraouf-studios/google-play-console-mcp Enables managing releases, monitoring Android vitals, analyzing earnings and search terms, optimizing ASO, and preflighting store assets through natural language, with a confirmation gate before destructive writes. | |
| Specter MCP abd3lraouf/specter-mcp Enables AI agents to build, test, debug, and interact with Kotlin Multiplatform Mobile (Android/iOS) applications through automated build pipelines, UI automation, crash analysis, and app state inspection. | |
| qemu-mcp-server abdalla-eldoumani/qemu-mcp-server An MCP server that gives AI agents direct control over QEMU virtual machines. | |
| odouche-mcp abdallah-abdelsabour/odoo-sh-toolkit Enables AI coding agents to see their Odoo.sh projects by listing projects, branches and builds, waiting for a build to finish, reading build and server logs, and optionally rebuilding branches or updating the firewall. It runs read-only by | |
| NotebookLM MCP Server abdallah-nasir/notebooklm-mcp Enables interaction with Google NotebookLM through a real Chrome browser, allowing natural language queries, source ingestion, and audio overview generation. | |
| Screen MCP Overlay abdallah913/screen-mcp-overlay Enables MCP clients to view the user's screen and draw click-through annotations, highlights, and numbered step indicators directly on the live desktop, while keeping the user in control of mouse and keyboard. | |
| Lokalise MCP Server abdallahaho/lokalise-mcp Connects AI assistants to Lokalise translation management platform with 59 tools across 11 domains, enabling localization teams to manage projects, translations, tasks, and workflows through natural conversation. | |
| Support Ticket MCP abdallahfathi371-sketch/support-ticket-mcp An AI-powered support ticket management system that lets users retrieve, search, and update support tickets using natural language. | |
| jira-work-logger abdalrahmanalqaroot/jira-work-logger Enables an AI coding agent to scan a day's git commits across work repositories and group them into Jira tickets, creating or updating them with estimates and logged time. It also surfaces actionable, categorized errors so an agent knows wh | |
| github-mcp abdeebuilds/github-mcp GitHub MCP server for Claude Code, Cursor, Cline, Windsurf, and any MCP-compatible client. Exposes GitHub tools (issues, pull requests, code search, file content) to your LLM via the Model Context Protocol. | |
| Iron Bridge Construction — MCP Equipment Safety Server abdel7amed129/ironbridge-mcp-project MCP server for heavy equipment management with role-based access, supervisor authentication, and high-risk request elicitation/sampling. | |
| Example Next.js MCP Server abdelatifabualya/model-context-protocol-mcp-with-next-js A drop-in MCP server implementation for Next.js projects using Vercel MCP Adapter, allowing developers to integrate model context protocol functionality with custom tools, prompts, and resources. | |
| draft1-mcp abdelhadi-azouni/draft1-mcp MCP server for generating and editing architecture diagrams from natural language or code, supporting formats like Terraform, docker-compose, Kubernetes, SQL, Mermaid, and PlantUML. | |
| WebMorph abdelhafzdev/webmorph Serves validated, read-only tools and skills generated from a website, letting AI agents query and interact with that site over MCP without driving a browser. Tools are derived from observed HTTP endpoints with a browser fallback, and only | |
| TrustMRR MCP Server abdelhakrazi/trustmrr-mcp Connects AI assistants to the TrustMRR API to browse, filter, and analyze startup listings by revenue, MRR, and growth metrics. It enables detailed retrieval of startup financials and pricing for comprehensive deal analysis. |
22,851–22,900 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.