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 |
|---|---|
| MCP Chat ajinkyahimanshu/anthropic_introduction_to_mcp Enables command-line interactive chat with Anthropic AI models, supporting document retrieval via @ references and slash commands for custom tool execution through the MCP architecture. | |
| OpenEHR MCP Server ajinkyasabale-github/openehr-mcp Enables LLMs to interact with OpenEHR electronic health record systems by retrieving clinical archetypes, generating AQL queries from natural language, and executing queries against on-premise EHR databases. Supports OpenEHR Clinical Knowle | |
| competitor-radar-mcp ajitesh-png/competitor-radar-mcp Watches competitors on X, scrapes posts and engagement metrics, and ranks daily posts by replies, bookmarks, retweets, and likes while scoring ICP relevance to surface the content that actually resonates with your buyers. | |
| NetGuardian ajitesh1234/netguardian-mcp Enables Alexa+ to answer plain-English questions about a home network using live diagnostics such as ping latency, bandwidth, connected devices, and interface health, with optional local or AWS Bedrock LLM reasoning and safe service restart | |
| User Management MCP Server ajith-fullstack/mcp-server Enables AI-compatible MCP clients to create, retrieve, update, and delete user records through five MCP tools, plus a guide resource and a prompt that auto-generates and saves random users. User data is validated with Zod and persisted in a | |
| solana-mcp ajithjs99/solana-mcp Enables AI agents to interact with the Solana blockchain for DeFi, NFTs, and Web3 tasks through 38 tools, 10 prompts, and 7 modules. | |
| azdo-onprem-mcp ajithnow/azdo-onprem-mcp Minimal MCP server for self-hosted Azure DevOps Server (on-premises). Enables interaction with work items, WIQL search, and project listing via REST APIs using PAT and basic auth. | |
| mcp-server-ngrok ajitnk-lab/mcp-server-ngrok Exposes a local MCP server via ngrok with SSE and Streamable HTTP transports for use in Kiro Web. | |
| Acronis MCP Server ajitsharmadbg96-create/acronis-mcp-server A remote MCP server that integrates Acronis Cyber Protect Cloud with Claude, enabling natural language queries to list devices, check backup status, manage alerts, trigger backups, and generate detailed reports. | |
| dragon-work ajiumeng123/dragon-work Provides a local-first AI workspace for chatting, invoking skills, managing projects, and integrating MCP tools, with all data stored on the user's machine. | |
| garmin-claude-mcp ajjk8/garmin-claude-mcp Enables Claude to read recent Garmin training activities and wellness data (sleep, HRV, resting heart rate, recovery) through intervals.icu, then design and push structured workouts to the calendar that sync to Garmin Connect and land on yo | |
| My Coding Buddy MCP Server ajkeast/coding-buddy-mcp-server A personal AI coding assistant that connects to various development environments and helps automate tasks, provide codebase insights, and improve coding decisions by leveraging the Model Context Protocol. | |
| One Agent Harness ajmainapon/one-agent-harness Enables developers to capture verbatim conversation turns, implementation plans, task lists, modified files, terminal errors, and uncommitted git state from one AI coding agent and inject or hand them off to another with a single command. I | |
| gsc-mcp ajmalaksar25/searchlight Turns Google Search Console into an SEO copilot by enabling natural language queries for search analytics, URL inspection, sitemap management, and opportunity discovery. | |
| AutoCAD MCP ajmalpshaik/heron-autocad Enables Claude to connect to an already-running full AutoCAD instance through COM Automation, reading and drawing geometry live in the open drawing with 50 tools covering entities, layers, queries, modifications and AutoLISP escape hatches. | |
| Todoist Meeting MCP ajmastra/todoist-mcp Connects Claude to Todoist for transforming meeting notes into actionable tasks with inferred due dates and priorities. It enables full task lifecycle management, including creating subtasks, listing projects, and completing tasks through n | |
| moneta-notes-mcp ajmichels/moneta-notes MCP server exposing fast full-text and semantic search over an Obsidian vault, plus safe structured note read and write access for Claude. | |
| Software Migration Platform ajmothossain2002/mcp-server MCP server that enables AI agents to analyze legacy code, plan and execute software migrations, generate modern source code, and validate production-ready artifacts through a multi-agent pipeline. | |
| cockroach-browser MCP ajnasnb/cockroach-browser Observation-first MCP server for Cockroach Browser, enabling AI agents to snapshot, audit, and propose browser actions through a secure, policy-controlled daemon. | |
| Alan's Date Time MCP ajnx/alans-date-time-mcp Provides current date, time, and datetime with optional timezone support (local, UTC, or IANA timezone strings). | |
| CapacitiesMCP ajokunu/capacities-mcp Enables AI assistants to search, create, and organize content in your Capacities.io knowledge base, with limitations on reading object content due to API restrictions. | |
| Domain Checker MCP Server ajot/domain-checker-mcp-server Enables domain availability checking through dual verification using WHOIS lookups and DNS resolution. Supports both single and batch processing to provide detailed analysis on whether domains are likely available or already registered. | |
| library_mcp ajr543/library_mcp MCP server for college library management, enabling book issuance, returns, inventory management, and availability checks via MySQL. | |
| perfsonar-mcp ajragusa/perfsonar-mcp An MCP server for perfSONAR that enables querying historical network measurements, discovering global testpoints, and scheduling active network tests. It provides tools for monitoring throughput, latency, and packet loss through integration | |
| mcp-bonusly ajramos/mcp-bonusly Enables management of Bonusly employee recognition bonuses, including listing, creating, and retrieving bonuses with advanced filtering. | |
| mcp-gsuite-enhanced ajramos/mcp-gsuite-enhanced Comprehensive MCP server for Google Workspace with complete Gmail API coverage (27 tools) and Google Calendar integration with automatic Google Meet links, enabling advanced email management, label operations, archive workflows, and calenda | |
| outlook-mcp ajs117/outlook-mcp Local MCP server for personal Outlook.com/Hotmail/Live accounts, enabling email triage, folder management, bulk operations, and newsletter unsubscribe via Microsoft Graph. | |
| Dataverse MCP Server ajscheuer/dataverse-mcp A Model Context Protocol server that enables CRUD operations and querying on Microsoft Dataverse through natural language. | |
| gsc-mcp-connector ajshoping/gsc-mcp-connector Enables AI assistants such as ChatGPT and Claude to query Google Search Console data in natural language via four tools covering property listing, search analytics (clicks, impressions, CTR, position with filters), URL inspection, and sitem | |
| gsc-mcp-connector ajshoping/gsc-mcp-connector2 Self-hosted Google Search Console MCP server that lets ChatGPT, Claude, or other MCP clients query GSC data in natural language. It exposes tools to list sites, query Search Analytics, inspect URLs, and list sitemaps. | |
| ai-job-apply ajstars1/ai-job-apply Enables AI agents to discover postings from watched company boards ranked by keyword fit, tailor and fact-check resumes against a source-cited profile, render ATS-readable PDFs, submit applications through the user's own browser, and track | |
| pilot-browser-mcp ajstars1/pilot-browser Enables AI agents to drive the Chrome, Brave, or Edge browser you are already logged into, working in a tab of its own with a visible cursor and real trusted input. You can pause, take over, or hand back control at any time, and consequenti | |
| estat-mcp ajtgjmdjp/estat-mcp MCP server for Japan's e-Stat (Government Statistics Portal). Search statistical datasets, retrieve data tables, and access metadata from official Japanese government statistics. | |
| japanfinance-agent ajtgjmdjp/japanfinance-agent Compound MCP agent that integrates EDINET, TDNET, e-Stat, and stock price sources for comprehensive Japanese company analysis, macro economic snapshots, and earnings monitoring through a single interface. | |
| stockprice-mcp ajtgjmdjp/stockprice-mcp MCP server for stock prices, historical data, FX rates, and ticker search, powered by yfinance with no API key required. Designed for Claude Desktop. | |
| taxfolio-mcp ajtgjmdjp/taxfolio-mcp Enables tax-loss harvesting and tax-aware portfolio rebalancing via LLM agents, allowing users to identify selling opportunities and substitute holdings based on return correlation. | |
| tdnet-disclosure-mcp ajtgjmdjp/tdnet-disclosure-mcp MCP server for Japan's TDnet (Timely Disclosure network). Search and retrieve timely disclosure documents from listed companies on Japanese stock exchanges. | |
| Hoistline ajthom90/hoistline Exposes a single authenticated MCP endpoint that federates to agents running on your own machines, letting you delegate coding jobs to be worked in fresh git worktrees and pushed to a branch, or proxy the stdio MCP servers installed there a | |
| Remote MCP Server (Authless) ajtruex/remote-mcp-server-authless Enables deployment of MCP servers on Cloudflare Workers without authentication requirements. Allows users to create custom tools and connect them to AI clients like Claude Desktop or Cloudflare AI Playground through a remote endpoint. | |
| Nav2 MCP Server ajtudela/nav2_mcp_server Enables control and monitoring of Nav2 navigation operations, including navigation, waypoints, costmap management, and lifecycle control, through the MCP protocol. | |
| powerbi-mcp ajvogod/powerbi-mcp MCP server for Power BI — local PBIX file analysis, cloud API operations, report export, and semantic model extraction from Power BI Desktop. | |
| installed-api ajwann/installed-api Stop letting your agent guess at APIs. Ask the code you actually installed.
installed-api is a Claude Code plugin (an MCP server, Python standard library only) that answers "what's the signature of X?", "does Y take that argument?" and "wh | |
| Charlotte Open Data MCP Server ajwann/meck-311-mcp Enables LLMs to answer everyday questions about Charlotte and Mecklenburg County using official open data, covering area crime and crashes, 311 service requests, trash and recycling schedules, zoning and rezonings, code enforcement, capital | |
| Evernote MCP Server ak-9647/evernote-mcp A Model Context Protocol server that allows AI assistants like Claude to interact with Evernote, enabling them to create, search, read, and manage notes through natural language. | |
| bookd ak-monkey/bookd Enables AI assistants to query a local reader's current state (book, chapter, CFI, visible text, selection) and perform actions like opening books, navigating by CFI or progress, searching, and creating or clearing highlights. | |
| FoodOps MCP ak-repo/mcp Enables users to perform seeded food-order, delivery, refund, and invoice operations through Model Context Protocol tools. | |
| MCP Server ak125/mcp A centralized architecture that serves as the only data access layer between frontend/backend applications and Supabase/Redis, enforcing strict data access control while maintaining simplicity and efficiency. | |
| ABAP MCP ak1979/abap_mcp An AI-powered server that provides comprehensive coding assistance for SAP ABAP development, including tools for code generation, analysis, and refactoring. It integrates with various LLMs and the SAP ADT REST API to enable intelligent inte | |
| db-memory ak1ena/vector-db-mcp A vector-DB MCP server that gives Claude conversational memory by storing solved problems and solutions as vectors and retrieving relevant ones when a new request resembles a past solution. | |
| MCP Server Railway Starter ak40u/mcp-server-railway-starter A starter template for deploying a remote MCP server with OAuth 2.1 authorization, dynamic client registration, and a PostgreSQL database. Includes example tools for notes and whoami. |
25,401–25,450 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.