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 |
|---|---|
| xcode-mcp-server (drewster99) drewster99/drews-xcode-mcp Enable Claude Code, Cursor, or your favorite LLM to interact with Xcode, building your projects the same way you do, and seeing the same errors. Greatly increases productivity when working on iOS, iPadOS, macOS, visionOS, tvOS projects & Sw | |
| Pokemon Showdown MCP Server drewsungg/mcpkmn-showdown Provides Pokemon Showdown competitive battle data to AI assistants, enabling lookup of Pokemon stats, moves, abilities, items, type matchups, and strategic information through natural language queries. | |
| MCP AI POC drewtech/mcp-ai-poc Provides AI-powered development tools including code generation, refactoring, debugging, performance optimization, and test generation, along with smart prompts for code analysis and documentation, and a built-in knowledge base of coding be | |
| Maverick Bank drewxa/maverick-bank Enables Claude Code and Codex to save and retrieve local, editable Markdown-based long-term memory, including durable preferences, decisions, and lessons with source, line, revision, and date provenance. | |
| Astro Docs MCP Server dreyfus92/astro-docs-mcp An MCP server that provides AI assistants with access to Astro documentation, enabling them to search and reference Astro docs when helping users with Astro-related tasks. | |
| KIMP MCP Server drfirstlee/kimp-mcp Enables users to query Kimchi Premium (KIMP) data for cryptocurrencies, showing the price difference between Korean and international exchanges for assets like Bitcoin and Ethereum. | |
| Demaciains MCP Server drgalio/demaciains-mcp Provides 19 AI-powered business intelligence tools for tasks such as SEO audits, company enrichment, and market analysis. These services are accessible through a pay-per-use model utilizing the x402 protocol on the Base network. | |
| Ring MCP drgost1/ring-mcp An MCP server for Claude Code that shows always-on-top notification popups with sound when tasks complete, with OS-native notification fallback. | |
| Roblox Studio MCP Server drgost1/robloxstudio-mcp Bridges AI assistants to Roblox Studio with 51 tools for exploring, editing, and automating game development, all locally via HTTP polling. | |
| codex-upwork-mcp-bridge drharunyuksel/codex-upwork-mcp-bridge Enables Upwork's MCP server to work with OpenAI Codex and ChatGPT by normalizing protocol incompatibilities, allowing their tools to be listed and used. | |
| agentskills-mcp drhir2460/agentskills-mcp A FastMCP server that helps users discover, browse, and install agent skills from curated GitHub collections, with support for adding new skill sources. | |
| gametrans drhushi/gametrans Enables AI agents to drive an end-to-end game localization pipeline — scan, plan, translate, write back, and pack — turning a Ren'Py or RPG Maker MV game folder into an installable Chinese patch. Includes term-consistency management, placeh | |
| RISA-3D MCP Server driegonunez/risa3dmcp Enables AI assistants to read, query, compare, edit, QA/QC, and export RISA-3D .r3d structural models through natural language, with a standalone CLI for local diagnostics and reporting. | |
| DriftHound MCP Server drifthoundhq/mcp-server Enables Claude to discover and understand infrastructure-as-code drift by listing projects with drift, analyzing Terraform plan outputs, and providing remediation information. | |
| DriftOS MCP Server driftos/driftos-mcp-server Enables intelligent semantic conversation routing that automatically branches, maintains, and routes between conversation topics instead of relying on entire conversation histories for context. | |
| @sandboxapis/mcp driftwork-llc/sandboxapis-mcp Enables AI agents to read realistic, coherent data—repos, pull requests, issues, commits, users—through API-compatible, read-only replicas of 21 developer platforms including GitHub, Jira, Linear, Slack, Sentry and Salesforce, all preloaded | |
| HA MCP Server driin0/ha-mcp-server An MCP server that exposes Home Assistant's REST and WebSocket APIs as 182 tools, enabling clients like Claude Code to control lights, climate, media, automations, and more. It also provides a status dashboard and supports running as a Home | |
| DrillerDB MCP Server drillerdb/drillerdb-mcp Enables natural-language querying and management of drilling projects, customers, invoices, crews, schedules, and well logs through any MCP client. | |
| feiertage-mcp drilongit/feiertage-mcp Enables MCP clients to query German public holidays by Bundesland and school holidays, check whether dates are holidays, find upcoming holidays, and count working days using offline, sourced data. | |
| mcp-browser-bridge drima-code/mcp-browser-bridge Enables agents to inspect and interact with user-approved existing Firefox website tabs through a Firefox extension and local native host, supporting bounded snapshots, form actions, and file uploads under per-tab or explicit automatic appr | |
| Web Research MCP Server drintoul/web-research Exposes web search, site mapping, scraping, crawling, schema-validated structured extraction, and stateful Playwright browser interaction as MCP tools, routing every call through the same authenticated REST gateway used by the platform's HT | |
| Karma MCP Server driosalido/mcp-karma Enables Claude to interact with Karma Alert dashboard to monitor and analyze Kubernetes alerts. Provides tools to check alert status, filter by cluster/severity, get detailed alert information, and analyze alert statistics and trends. | |
| Budgetsco MCP Server drishit96/budgetsco-mcp-server Enables personal finance management through Budgetsco, supporting transaction tracking, budget management, recurring transactions, custom categories, and multi-currency support for comprehensive financial tracking. | |
| Langfuse MCP Server drishtantkaushal/langfusemcp Model Context Protocol server for Langfuse observability. Query traces, analyze accuracy, detect failures, track costs, debug latency, manage prompts and datasets. | |
| Browser MCP drisplabs/browser-mcp Gives AI agents a compact, semantic interface to the browser, returning structured page snapshots with stable element IDs instead of raw DOM. Enables agents to navigate, interact, and extract information from web pages efficiently. | |
| Calendar MCP Server driti2906/calendar-mcp A production-quality MCP server for calendar management with robust timezone handling, recurrence support, and idempotency guarantees. | |
| MCP System Info Server driti2906/mcp A lightweight MCP server that provides real-time hardware statistics including CPU, memory, disk, and NVIDIA GPU usage. It enables users to monitor system performance and retrieve comprehensive host machine specifications through a standard | |
| TiresVote MCP driveate/tiresvote_mcp Enables agents to search a public tire catalog and professional tire test data — finding tire models, checking their known size variants, comparing 2-4 models, and collecting cited test results — through 12 read-only tools and four workflow | |
| prayog-repo-fleet drivestream-lab/prayog-repo-fleet Exposes code graphs across multi-program repositories via MCP, enabling humans and agents to query the fleet with evidence. | |
| Auto dev drivly/auto-dev-skill Automotive Data for AI Agents | |
| just-bash-mcp drizjet/just-bash-mcp Sandboxed bash execution MCP server for AI agents, using an in-memory virtual filesystem overlay to prevent real filesystem damage, with configurable network access, timeouts, and optional Python/JS runtimes. | |
| MCP Server for Things3 drjforrest/mcp-things3 Enables integration with Things3, allowing the creation and management of tasks and projects via the MCP protocol, including synchronization with Agenda projects. | |
| mcp-app drjkuo/mcp-app Fetches public GitHub repositories and uses an LLM to generate a json-render UI specification. | |
| ghl-internal-cli drkavner/ghl-internal-cli Enables AI agents to interact with GoHighLevel's internal v2 API, managing Agent Studio, Voice AI, and Knowledge Base features through natural language commands. | |
| remote-mcp-server-authless drkazaminim/remote-mcp-server-authless Deploy a remote MCP server on Cloudflare Workers without authentication, enabling custom tools and connection to clients like Cloudflare AI Playground and Claude Desktop. | |
| Overshoulder drknowhow/overshoulder Lets AI agents lease a single Windows window or a whole screen, see its controls, click, type and hotkey inside it (in the background, so the user keeps their own mouse and keyboard), and record what they did as a step-by-step tutorial. Eve | |
| DLF Agency MCP Server drleadflow/dlf-ghl-mcp Enables AI agents to manage GoHighLevel workspaces through natural language, with 508 tools across 18 domains for complete CRM, marketing, and workflow automation. | |
| GHL MCP Server drleadflow/ghl-mcp Enables AI agents to programmatically manage GoHighLevel accounts through a Cloudflare Workers-based server. It currently supports CRUD operations for custom fields, custom values, and object folders with plans to include contact and pipeli | |
| freecad-print-mcp drmarcelofrodrigues-ctrl/freecad-print-mcp Enables Claude to model 3D-printable parts by running Python scripts in a headless FreeCAD instance and exporting STL/3MF/STEP files. It also lets Claude visually inspect renders, check mesh integrity and overhang printability, measure volu | |
| thetadata-mcp drmartell/thetadata-mcp MCP server that wraps the Theta Data API to provide AI assistants with real-time and historic stock, options, and index data, including OHLC, trades, quotes, Greeks, and more. | |
| @drmaxbdc/productboard-mcp drmaxbdc/productboard-mcp MCP server for the Productboard API v2. Provides 30 tools covering entities, notes, relationships, configurations, members, and analytics. | |
| jev-mcp drmedia/jev-mcp Lets MCP clients ask typed questions — yes/no, choice, or score — about structured state, including images, and receive calibrated probabilities from System One decision models such as TypeSafe Jev and Cloudflare Clef. Supports TypeSafe, Op | |
| PhotoshopMCP drmedia/photoshop-mcp Enables controlling Adobe Photoshop from an MCP client, providing tools for layers, adjustments, masks, selections, filters, text, actions, and file operations, with configurable permission levels and extension support. | |
| claude-beacon drmf-cz/claude-beacon MCP server that pushes GitHub Actions CI/CD results and PR events into Claude Code sessions, enabling automatic investigation and remediation. | |
| mcp-opnsense drmfar/mcp-opnsense MCP server for managing OPNsense firewalls, providing read-only tools for firewall rules, aliases, interface statistics, and gateway status with multi-instance support. | |
| draftgate-mcp drmm101/draftgate-mcp Enables email agents to send emails with granular trust levels per contact, ensuring human approval for high-risk or unknown recipients while allowing automatic sending for trusted ones. | |
| Arr MCP drmogie/arr-mcp Enables Claude to monitor and manage a self-hosted media stack—including Sonarr, Radarr, Prowlarr, Bazarr, Overseerr, qBittorrent, and Jellyfin—through tools for status, queues, searches, additions, requests, downloads, and now-playing chec | |
| Nginx Proxy Manager MCP drmogie/nginx-proxy-manager-mcp Enables Claude to read and modify an Nginx Proxy Manager instance through its API, covering proxy, redirection, and 404 hosts, streams, certificates, access lists, audit logs, and any other API endpoint. Changes are merged into existing obj | |
| PiKVM MCP drmogie/pikvm-mcp Enables Claude to inspect and configure PiKVM devices through the web API and SSH, including power control, screenshots, keyboard input, virtual drives, health checks, configuration, and services, with safeguards that require confirmation f | |
| server-mcp drmogie/server-mcp Lets Claude manage Linux servers and Docker over SSH or locally, with previews and approval before every change. |
46,001–46,050 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.