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 |
|---|---|
| armorpaint-mcp baktubak/armorpaint-mcp Enables MCP clients to drive ArmorPaint 1.0 through a file-based bridge plugin, letting agents open projects, inspect and edit materials and node graphs, paint, and export textures on an unmodified ArmorPaint installation. | |
| AgentMesh MCP bala2006/agentmesh-mcp Enables coding agents to coordinate around shared project context, durable tasks, messages, artifacts, multimodal analysis requests, design-system checks, change proposals, and review requests through a compact MCP interface. It persists st | |
| laya-browser-mcp bala2006/laya-browser-mcp Enables AI assistants to control a web browser through Playwright-compatible tools, with an on-device decision engine for autonomous task completion and optional LLM escalation. | |
| garmin-mcp balabeir/garmin-mcp Provides read-only access to authenticated Garmin Connect data through MCP, including profile and connection status. It supports secure linking without exposing Garmin credentials as tool arguments. | |
| MCP Notes Server Example balachandranaairc/mcp-notes-server-example Enables users to search, add, and reindex notes in memory, expose a notes resource template, and serve a prompt, all over stdio with structured output, progress reporting, and user confirmation flows. | |
| incident-triage balachoudry-tech/incident_mcp_ai An MCP server that helps engineers investigate service incidents using semantic log search, error aggregation, RAG-based diagnosis, and runbook recommendations. | |
| gne balaena01/gguf-neuron-explorer Enables agents to query and rank MLP neurons of GGUF models on llama.cpp, steer them, run background jobs, and highlight or annotate neurons in an open web UI. | |
| HR System MCP Server balaganaparthi/hr-mcp Enables employee information lookup, directory listing, payroll access, and time-off request management with Okta token validation. | |
| Okta MCP Server balaganaparthi/project003_oauth2.1 An MCP server for managing Okta users (CRUD operations) with full OAuth 2.1 compliance, enabling secure integration with Claude Desktop and other MCP clients. | |
| swagger-to-mcp balaji-sasikumar/swagger-to-mcp Turns any OpenAPI/Swagger specification into a functional MCP server, dynamically exposing API endpoints as LLM tools or generating standalone Python code. | |
| MCP Production Demo balaji-w/mcp-demo An MCP server providing live GitHub repository and issue search tools, with production-grade features like config validation, structured logging, authentication, and support for both stdio and HTTP transports. | |
| Ticket Management & Meeting Overview MCP Server balaji2830/ticket-management-meeting-overview-mcp-server An MCP server for managing tickets and meetings with CRUD operations, backed by PostgreSQL, and includes a REST API and React frontend. | |
| mcp-flyin balajidommeti/mcp A server that handles messaging or commands over a custom protocol | |
| splunk-mcp-server balajifunny/splunk-mcp-server A lightweight, extensible MCP server for Splunk Enterprise that enables secure, async, chat-based interaction with Splunk data via Claude Desktop or any MCP-compatible agent. | |
| Veritas MCP balajinrrbgm/sans-veritas-mcp-bn0626 Enables AI agents to conduct evidence-grounded forensic triage of compromised hosts, with architectural safeguards against evidence spoliation and hallucinated findings, supporting self-correction and chain of custody. | |
| fde-assessment balajipillalamarri/fde-assessment Enables MCP tool calls with strict schema validation and stdio isolation, while providing a security gateway for tool-level authorization, streaming PII redaction, and model failover routing. | |
| Clerk MCP Server balajisriraman/mcp-server-clerk Enables AI assistants to query and manage Clerk organizations, users, members, and metadata via the Model Context Protocol. It supports both hosted and per-request secret key modes for flexible integration with various AI environments. | |
| Quiz App MCP server balajivx/quiz-mcp-server Enables running interactive quizzes through natural language, with tools to register users, fetch questions, validate answers, generate leaderboards, and review answers. It works locally with Claude Desktop over stdio or remotely with claud | |
| Secure Code Review MCP Server balakonda-reddy/secure_code_review_mcp_server Local MCP server that scans code for security issues (secrets, dependencies, configurations, risky patterns) and integrates with GitHub Copilot in VS Code for automated pre-commit reviews. | |
| browser-relay-mcp balakumardev/localvily Unlimited, session-authenticated web search and fetch for AI tools using your own browser. Supports authenticated/paywalled pages without API keys. | |
| Perplexity MCP balakumardev/perplexity-web-wrapper Enables AI-powered web research using your existing Perplexity Pro subscription, providing tools for search, follow-up conversations, and thread management through the Model Context Protocol. | |
| shieldbot balasriharsha/shieldbot AI-powered security code review for Claude Code that runs multiple scanners (CodeQL, Semgrep, etc.) to detect vulnerabilities, secrets, and dependency CVEs, producing prioritized reports. | |
| @a-bonus/redmine-mcp balazsvargaosi/redmine-mcp MCP server for Redmine that enables interaction with issues, wiki pages, and time entries through natural language. | |
| mcp-security-server balckers/mcp-security-server Provides AI agents with standardized security scanning capabilities for authorized assessments, including host detection, port scanning, service fingerprinting, web vulnerability scanning, CVE verification, and report generation, all with u | |
| Yahoo Finance MCP Server bald-newcomer/yfinance-mcp Enables querying stock data, financial information, news, and historical prices from Yahoo Finance through a set of MCP tools. | |
| MCP BACEN baldros/mcp-bacen Provides tools to query Brazilian Central Bank public data, including SGS time series and PTAX exchange rates. | |
| private-journal-mcp baleen37/private-journal-mcp Stores journal entries locally with semantic search using multilingual embeddings, and optionally syncs to a Git remote. | |
| discord-mcp-server balhea-ai/discord-mcp-server Wraps a Discord bot as an MCP server to integrate with Claude Team, enabling reading and sending messages in Discord channels via natural language commands. | |
| iifa balidriss/iifa Enables AI agents to remember people, projects, places, and topics across conversations under a strict token budget, returning compact handles with expandable details while preserving changes, provenance, and encrypted self-hosted storage. | |
| Weather MCP Server balinux/weather-mcp Provides weather information through the Model Context Protocol, fetching real-time weather data from OpenWeather API or using simulated data when API key is not configured. | |
| checkpoint baliutkarsh2/checkpoint Enables AI agents to test and gate their own code by listing scenarios, running scenario tests, and applying statistical release gates inline via MCP. | |
| ancestry-com-mcp ball2jh/ancestry-com-mcp Lets an AI assistant do everything you would do on Ancestry.com by hand: search records, read and edit trees (people, facts, sources, citations, notes, tags, media), review hints, attach records, look at DNA matches, and read or send messag | |
| familysearch-org-mcp ball2jh/familysearch-org-mcp Enables direct interaction with FamilySearch.org's shared Family Tree and historical records, including reading and adding people, facts, relationships, sources, notes, memories, record search, and image downloads, without needing a browser | |
| findagrave-com-mcp ball2jh/findagrave-com-mcp Enables read-only search and retrieval of Find a Grave memorials, cemeteries, and places, including dates, burial details, inscriptions, biographies, family links, and photos, via the site's anonymous GraphQL API without login. | |
| fold3-com-mcp ball2jh/fold3-com-mcp Enables searching and reading Fold3 military records, including files, index records, memorials, and collection browsing, along with full-resolution page image downloads, using an existing Ancestry session in read-only mode. | |
| nist-mcp ball2jh/nist-mcp Provides structured access to the full NIST cybersecurity catalog, including SP 800/1800 publications, security controls, CSF 2.0, and the NVD database. It enables AI assistants to search and retrieve cybersecurity standards, CVEs, and comp | |
| Netlify Express MCP Server ballen333/netlify---mcp A serverless MCP server example built with Express and deployed on Netlify Functions, demonstrating how to expose MCP endpoints via a custom URL with proper redirects. | |
| mcp-federated-data baller-coder/mcp-federated-data Federated MCP server that joins relational metadata (MySQL) with timeseries values (InfluxDB) behind a single, LLM-friendly entity layer. | |
| Bitrix24 MCP Server ballindaboy/bitrix24_mcp_claudedesktop Enables language models to interact with Bitrix24 CRM, providing tools to manage deals, leads, contacts, tasks, activities, users, files, chat messages, and live chat sessions. | |
| SSH MCP Server balloonf/ssh_mcp An advanced SSH session manager that allows Claude to establish and manage multiple SSH connections, execute remote commands, and monitor connection health through the Model Context Protocol. | |
| Windows TTS MCP Server balloonf/windows_tts_mcp A PowerShell-based MCP server that enables Claude Desktop to convert text to speech using Windows' built-in Speech API, offering features like playback control, speed and volume adjustment. | |
| Weather MCP server for Claude ballyhoogroup/weather-mcp-render Enables querying current weather conditions and 1–7 day forecasts by place name through natural language, using Open-Meteo without requiring an API key. | |
| FlagForge MCP Server ballz4z4/flagforge-mcp Enables AI agents to interact with the FlagForge REST API, allowing them to search solved CTF challenges, work on live event challenges, record evidence, submit flag candidates, and write markdown writeups. | |
| mcp-stdio balneario-de-cofrentes/mcp-stdio A minimal, zero-dependency MCP server that enables defining and running tools over stdio transport, without extra features like HTTP or resources. | |
| plavecka-akademia-mcp balonik/plavecka-akademia-mcp Enables querying children's swimming course listings from plaveckaakademia.sk with complex filters and cross-category slot finding, all through natural language. | |
| Monero MCP Server baltsar/monero-mcp MCP server that gives AI agents a private Monero wallet, enabling balance checks, payment receiving, and XMR transfers through a tool interface. | |
| demo-redshift-mcp balu7771/demo-redshift-mcp Enables natural-language analysis of insurance customer migration data through CrewAI agents, providing tools for querying renewals, churn, competitor returns, and feature adoption. | |
| Home Automation MCP Server balupeddireddy08/home_automation_mcp_server A comprehensive smart home automation system that allows AI assistants to control and monitor smart home devices through natural language using the Model Context Protocol (MCP). | |
| Admin Inventory Management MCP Server balusanu/admin-inventory-management-remote-mcp-server Enables Claude Desktop to manage office inventory through natural language, including adding items, issuing stock, checking availability, and low-stock alerts. | |
| Product MCP Telegram Bot balychevtsev-coder/mcp This MCP server enables product management and mathematical calculations through a Telegram bot interface. It allows users to view, search, and add products to a database using natural language commands. |
32,801–32,850 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.