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-control andrefigueira/mcp-control MCP server that gives Claude Code full mouse, keyboard, and app control on macOS. Tell Claude what to do and watch it operate your computer. | |
| mcp.andreglegg.no andreglegg/mcp.andreglegg.no Remote MCP tool host serving tree generation tools over Streamable HTTP, returning short-lived download URLs for artifacts. | |
| treegen andreglegg/treegen MCP server for generating deterministic, stylized low-poly 3D trees. It supports multiple presets and can export GLB or OBJ assets. | |
| Rally MCP Server andrehocsis/rally-mcp-server An MCP server that provides AI assistants with tools for Mercado Libre and Shopee affiliate marketing, including product search, affiliate link generation, product analysis, copy generation, and trending product discovery. | |
| currency-bot-db andrei-blagov/mcp_hw Exposes PostgreSQL-backed currency request data to Cursor via MCP, enabling tools to retrieve recent user requests and currency query statistics. | |
| MCP Feedback Server andrei-cb/mcp-feedback-term Enables agents to request and receive user feedback during task execution through a terminal-based interactive feedback system. | |
| avemguvern andrei-vintila/avemguvern.ro Provides read-only access to the current government status of Romania via the get_government_status tool. | |
| caldav-mcp andrei06732/caldav-mcp Enables AI assistants to connect to CalDAV servers and manage calendars through natural language, including listing calendars and browsing, creating, updating, and deleting events and tasks (VTODOs). Supports recurring events, all-day event | |
| multiCAD-mcp andrei16550/multicad-mcp Enables AI assistants such as Claude for Desktop or Cursor to control CAD applications (AutoCAD, ZWCAD, GstarCAD, BricsCAD) on Windows through 7 unified tools exposing 56 commands. Supports drawing shapes, managing layers, blocks and entiti | |
| applemusic-mcp andrei6420/applemusic-mcp Enables MCP clients to search and browse music catalogs and libraries, manage playlists and favorites, control playback, and view or modify the Up Next queue across macOS, Windows, and Linux. | |
| OCHP MCP Server andreibesleaga/ochp-mcp Enables AI assistants to interact with EV charging infrastructure through OCHP (Open Clearing House Protocol) services. | |
| ocm-sdk-mcp andreibesleaga/ocm-python Enables AI assistants to interact with the Open Charge Map API, allowing exploration of endpoints, test requests, and using documentation to integrate the SDK. | |
| ocpi-sdk andreibesleaga/ocpi-sdk MCP server for the OCPI SDK that enables AI-assisted communication with EV charging infrastructure via the Open Charge Point Interface protocol. | |
| ph-compliance-mcp andreibrosmaster/ph-compliance-mcp Provides retrieval-grounded, citation-verified access to Philippine law and compliance, including statutes, jurisprudence, and government issuances across 15 compliance domains. | |
| Datadog MCP Server andreidore/datadog-mcp A Model Context Protocol (MCP) server that provides comprehensive Datadog monitoring capabilities, enabling Claude to manage CI/CD pipelines, analyze logs, query metrics, and handle monitors and SLOs. | |
| wildberries-mcp andreiexxx/wildberries-mcp Enables Wildberries sellers to monitor sales, advertising, reviews, and product funnels, and adjust bids and prices, through natural language in Claude. | |
| Weft andreifinogeev/weft-vscode Enables AI agents to manage a persistent Scrumban board through natural language, including capturing, moving, and completing tasks, with leasing, progress reporting, and human-in-the-loop decision handling. | |
| Stock Trade MCP Server andreifoster426/stock-trade-finance-api Enables programmatic access to Tiingo financial data such as stock prices, news, forex, fundamentals, dividends, and splits through MCP tools. | |
| sol-indesign-mcp andreigheo/sol-indesign-mcp Enables OpenAI Codex to inspect and modify Adobe InDesign documents through a local, authenticated MCP bridge and UXP panel. It provides typed, allowlisted operations with workspace confinement, approvals, and one-step Undo. | |
| Jenkins MCP Server andreimatveyeu/mcp_jenkins A Model Context Protocol (MCP) server that enables AI tools like chatbots to interact with and control Jenkins, allowing users to trigger jobs, check build statuses, and perform other Jenkins operations through natural language. | |
| atlassian-mcp andreimaxim/atlassian-mcp A read-only MCP server for Jira and Confluence Cloud, providing atlassian_get and jira_search tools. | |
| papertrail-mcp andreimaxim/papertrail-mcp Read-only MCP server for searching migrated Papertrail logs via SolarWinds Observability API. Provides tools to list environments and perform bearer-authenticated log queries through stdio. | |
| rollbar-mcp andreimaxim/rollbar-mcp A read-only MCP server for Rollbar investigations, enabling listing configured environments and making authenticated GET requests to the Rollbar API. | |
| mcp-secure-server andreimelneichuk/mcp-secure-server Enables AI agents to access corporate HR and CRM APIs on behalf of a specific user through OAuth 2.1 token verification, deny-by-default RBAC, token exchange, audit logging, PII masking, and untrusted-output envelopes. | |
| IDA Pro MCP Server andreiryu952/mcp-server-idapro Enables AI assistants to interact with IDA Pro for reverse engineering and binary analysis, including executing Python scripts, retrieving binary metadata, searching for values/text/bytes, and obtaining disassembly. | |
| Roundtable AI MCP Server andreiryu952/roundtable Enables a primary AI assistant in an IDE to delegate tasks to multiple specialized AI coding assistants via MCP, running them in parallel with shared project context and synthesizing a single response. It uses existing CLI tools and subscri | |
| UI5 MCP Server andreiv9869/mcp-server Provides tools for agentic AI workflows to scaffold UI5 applications and Integration Cards, fetch API documentation and development guidelines, validate manifests, run linting, inspect project metadata, and retrieve framework version inform | |
| allplan-mcp-bridge andrej-reeg/allplan-mcp-bridge Enables Claude to create, query, and modify BIM elements in Allplan via natural language, with full undo history support. | |
| ya-planka-mcp andrejberg/ya-planka-mcp A Model Context Protocol (MCP) server that enables AI clients to read and manage your Planka boards using the Planka REST API. | |
| command-executor andrelip/paginate-stdout Enables shell command execution with automatic pagination for large outputs, supporting custom directories and timeouts. | |
| ado-mcp-server andrelopes-code/ado-mcp-server Enables Claude Code to interact with Azure DevOps Server on-premises (work items, pull requests, repositories) through secure, controlled, safe-by-default access with read-only mode and explicit write confirmations. | |
| Work Researcher MCP andrem19/work-researcher-bot Enables agents to search and deduplicate UK job vacancies across multiple boards, match them against local CVs, and submit complete applications through an automated browser with persistent logins and application memory. | |
| Hello MCP Server andremir/http-mcp A simple demonstration MCP server that responds with "4" when greeted with "hello". Serves as a basic example for understanding MCP server implementation. | |
| TradingView Chart Image Scraper andremoore94/tradingview-chart-mcp Enables fetching TradingView chart images for any ticker and interval via Selenium, using browser pooling to handle concurrent requests efficiently. | |
| crispy-mysql-mcp-guard andrenalin282/crispy-mysql-mcp-guard Enables AI agents to query and modify MySQL and MariaDB databases over MCP, with each connection independently permitting selects, inserts, updates, deletes, and DDL while defaulting to read-only and rejecting anything outside the allowed o | |
| mcp-audit andreolf/mcp-audit npm audit for MCP servers. Point it at an MCP server and get a security grade (A–F) covering missing auth, SSRF surface, high-privilege tools, prompt-injection-prone tool descriptions, and leaked secrets. | |
| Typst MCP Server andrep54/typst-mcp Enables AI models to interact with the Typst typesetting system by converting LaTeX snippets, validating Typst syntax, and rendering Typst code to images. | |
| hevy-mcp andreparmar/hevy-mcp-remote An MCP server that interfaces with the Hevy fitness tracking API, enabling AI assistants to manage workouts, routines, exercise templates, and more via natural language. | |
| AnythingLLM MCP Server andreperez/anythingllm-mcp Enables MCP-compatible clients to interact with AnythingLLM, providing tools for workspace management, chat and thread operations, document operations, vector search, and system inspection. | |
| Kali Metasploit MCP Server andreransom58-coder/kali-metasploit-mcp Enables interaction with Metasploit Framework for authorized security testing, including exploit searches, payload management, network scanning with nmap, and database operations for penetration testing workflows. | |
| facturas-mcp andres2009/mcp-sidecil Enables Claude to run read-only SQL queries against the DWH.facturas table in SQL Server, including discovering its columns and asking natural-language questions about invoice data. | |
| Polar Fitness MCP Server andresaguirre08/polarmcp Enables AI assistants to access and analyze Polar device health data, including exercises, heart rate, sleep, and recovery metrics, by preprocessing raw sensor data into compact summaries to avoid context window overload. | |
| session-share andresantos09/mcp-session-share Enables AI agents on different accounts or machines to communicate via shareable rooms, with structural anti-prompt-injection defenses and optional autonomous cowork (autoloop) where agents alternate turns toward a shared goal. | |
| Who's in Space andresapitt/ceai-mcp-iss Provides AI assistants with live information about who is currently in space and the location of the ISS, using the free Open Notify API. | |
| mcp-trm-colombia andresflz/mcp-trm-colombia Enables LLMs to retrieve the official Colombian TRM (USD/COP exchange rate) with its validity window, perform currency conversions, and analyze rate series, all with auditable provenance. | |
| raw-web-search andresfortunato/raw-web-search An experimental MCP search server for Claude Code. Returns raw, verbatim web content instead of AI-rewritten summaries. | |
| Google Drive MCP Server andresfrei/mcp-google-drive-server Enables read-only access to multiple Google Drive accounts simultaneously through secure service account authentication. Supports listing, searching, and extracting content from Google Workspace documents, spreadsheets, and text files. | |
| openstudio-mcp-necb andresgallar/openstudio-mcp-necb Enables creation and validation of Canadian NECB prototype building models, application of NECB rulesets, and inspection of pinned standards/capabilities through MCP tools. | |
| Samsung TV MCP Server andresgarcia0313/samsung-tv-mcp A Model Context Protocol server that lets AI assistants control Samsung Smart TVs (Tizen OS, 2016+) over the local network. No cloud, no SmartThings account required. | |
| Databricks MCP Server andresgarciasobrado91/databricks-mcp-server A server that provides tools to interact with Databricks for cluster, job, notebook, DBFS, and SQL management through natural language interfaces like Claude-Desktop and Cursor. |
28,701–28,750 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.