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 |
|---|---|
| browser-mcp djyde/browser-mcp A MCP server that allows AI assistants to interact with the browser, including getting page content as markdown, modifying page styles, and searching browser history. | |
| MCP Git/PR Assist dk-niwamoto/sample_mcp Enables Git and GitHub pull request operations through Claude AI, including repository management, branch operations, commits, and PR creation/commenting. Streamlines development workflows by providing Git commands and GitHub API integratio | |
| Architectural Decision Log (ADL) System dk123579/adl-mcp Enables AI assistants to manage architectural decisions through CRUD operations integrated with a GraphQL backend and SAP/LeanIX fact sheets. It provides tools for creating, reading, updating, and deleting ADL entries to maintain a structur | |
| Termius MCP dk23lhl/termius-mcp Enables AI agents to read terminal output, run commands, switch sessions, and follow native SFTP uploads by connecting to a locally running Termius via its debugging interface. Provides explicit session IDs, command-output markers, and nati | |
| MySQL MCP Server dkabx/mcp-mysql-server Enables AI assistants to interact with MySQL databases by executing SQL queries, describing table schemas, and listing tables. It provides seamless database integration for tools like Cursor through the Model Context Protocol. | |
| multi-gmail-mcp dkaleganov/multi-gmail-mcp A self-hosted MCP server that gives an AI client read, search, triage, drafting, attachment/export and label-management access to several Gmail or Google Workspace accounts at once, with each call naming an explicit account. Sending is disa | |
| SandBase MCP dkaminski2652/cli Enables AI clients to discover, inspect, and run 2,000+ AI models and data APIs—including LLMs, image, video, and audio generation—through a single authenticated local bridge with per-call pricing shown before execution. It also supports ru | |
| Mailganer API MCP dkanster/mailganer-api-mcp Caches Mailganer API documentation and Postman collection locally, enabling search, sync, and cross-reference between API docs and Postman requests. | |
| Samotpravil MCP dkanster/samotpravil-api-mcp MCP server wrapping Samotpravil API documentation, providing tools to search for methods, parameters, and examples, with optional proxy to the live API. | |
| LeetCode MCP Server dkaraca39148/leetcode-mcp-server Enables automated access to LeetCode problems, solutions, contests, and public data, with optional authentication for user-specific features across leetcode.com and leetcode.cn. | |
| Tubist MCP Server dkasaj/tubist-mcp-server Enables AI assistants to control the Tubist macOS menu bar player to play YouTube videos using natural language commands, allowing uninterrupted background audio. | |
| pik-mcp dkasipovic/pik-mcp Exposes the OLX.ba marketplace API as MCP tools, enabling LLM clients to authenticate, browse and manage listings, read categories/attributes/locations, and run sponsorship/discount actions. | |
| mcp-data-server dkautomation23/mcp-data-server Provides read-only, guarded access to business databases via MCP. Enables natural language querying with built-in security barriers like table allowlists, PII masking, and audit logging. | |
| MCP AI Service Platform dkb12138ggg/python-rag-mcp-client A powerful AI service platform that provides complete MCP tool calling capabilities and RAG knowledge base functionality, enabling users to connect to multiple MCP servers and perform intelligent document search. | |
| postgres-mcp dkbearsong/postgres-mcp-tool A secure PostgreSQL MCP server allowing AI models to read, write, update, and delete database records with parameterized queries, transactional dry-runs, disposable testing, and automated backups. | |
| cave-motion dkc-engineering/motion-library Enables users to search curated motion recipes and prepare deterministic, customized prompts for coding agents to implement animations, product films, explainers, and procedural scenes in their projects. It returns instructions and requirem | |
| obsidian-bridge dkdottk/obsidian-bridge MCP server that connects Cursor agents to a local Obsidian vault via the Local REST API, enabling note reading, writing, searching, patching, and organizing through natural language. | |
| map-mcp dkedar7/map-mcp Enables AI agents to perceive and control a live MapLibre GL map over MCP, allowing querying rendered features, reading popups, navigating, and toggling layers. | |
| aws-architecture-scanner dkeeno/aws-architecture-scanner Scans AWS environments and generates professional architecture diagrams showing VPC networking, compute, storage, and security resources. | |
| aws-mcp-server dkeeno/aws-mcp-server An MCP server that provides tools for creating and managing AWS resources using boto3, including EC2, S3, VPC, subnets, security groups, and RDS. | |
| AWS EKS MCP Server dkeeno/eks-mcp-server Enables creating and managing AWS EKS clusters via Terraform, including VPC, node groups, add-ons, and kubectl configuration. | |
| github-mcp-server dkeeno/github-mcp-server Enables comprehensive GitHub operations including repository management, push, releases, issues, PRs, GitHub Actions, secrets, security, profile, search, and a unique portfolio push tool to create repos from local folders. | |
| gitlab-mcp-server dkeeno/gitlab-mcp-server Enables AI agents to automate the full GitLab DevOps lifecycle including repos, pipelines, CI generation, security scans, runners, tokens, and merge requests. | |
| Kubernetes MCP Server dkeeno/kubernetes-mcp-server An MCP server for generating Kubernetes manifests (deployments, services, configmaps, secrets, ingresses, namespaces) and performing kubectl operations like apply, delete, get, describe, logs, and exec. | |
| Terraform MCP Server dkeeno/terraform-mcp-server Enables generating, validating, planning, and applying Terraform configurations to manage infrastructure through natural language. | |
| gitlab-mcp dkeken/gitlab-mcp A Model Context Protocol server for self-hosted GitLab instances, enabling users to manage issues, merge requests, pipelines, and more via Claude Code. | |
| OMP Instances Control Plane dkeken/omp-instances-control-plane Local MCP control plane for managing multiple Oh My Pi processes via Unix sockets, enabling discovery, messaging, and lifecycle operations. | |
| studio-state dkf2studios/studio-state-public A stateless MCP server for AI film and video production that tracks project state, shot status, and updates, enabling consistent characters and continuity across generative video tools. | |
| lastfm-mcp dkfancska/mcp-lastfm An MCP server for the Last.fm API that enables LLM agents to access music data including user profiles, listening history, top charts, search, and artist/album/track metadata. | |
| alt-festival-mcp dkfmaekdnjfk/alt-festival-mcp An MCP server that lets Claude read live transcripts and notes from Alt, a real-time lecture/meeting transcription app, while a recording is in progress, pulling only new lines each time. | |
| ARWP Resolver MCP dkharlanau/agent-ready-web-profile Enables MCP clients to discover the concrete interfaces a website actually exposes—llms.txt, OpenAPI, Agent Skills, WebMCP, MCP, A2A—and select the right one for a given intent without site-specific code. | |
| aim-lt-archive dkiaulakis/aim-lt-archive-tools Enables searching and reading the public AI Mastermind LT community archive, including full-text search, message retrieval, and access to shared links and files, through natural language queries. | |
| Northstar Ask dkjager/northstar-ask Enables MCP clients to ask natural-language business questions over a retail dataset, keep multi-turn conversations, receive spoken text with structured cards, generate weekly briefs, and submit corrections for improved answers. | |
| mesh-memory dklymentiev/mesh-memory Self-hosted semantic memory for AI agents. Save worklogs, decisions, and notes via MCP, then recall them across sessions by meaning rather than keyword. Backed by Postgres + pgvector with local embeddings (multilingual-e5-base). | |
| screenbox dklymentiev/screenbox Provides AI agents with isolated virtual desktops containing a real Chromium browser, enabling them to see, click, type, and navigate like a human, with features like snapshots and remote control. | |
| mcp-azure-tablestorage dkmaker/mcp-azure-tablestorage Enables interaction with Azure Table Storage directly through Cline. This tool allows you to query and manage data in Azure Storage Tables. | |
| mcp-function-app-tester dkmaker/mcp-function-app-tester A TypeScript-based MCP server that enables interaction with Azure Table Storage directly through Cline. This tool allows you to query and manage data in Azure Storage Tables. | |
| perplexity-server dkmaker/mcp-perplexity-server A TypeScript-based MCP server that implements a simple notes system with resources, tools for creating notes, and prompts for summarization. | |
| mcp-rest-api dkmaker/mcp-rest-api A TypeScript-based MCP server that enables testing of REST APIs through Cline. This tool allows you to test and interact with any REST API endpoints directly from your development environment. | |
| tavily-server dkmaker/mcp-tavily-server A Model Context Protocol server that implements a simple notes system with resources for notes, a tool to create notes, and prompts to summarize notes. | |
| System Information MCP Server dknell/mcp-system-info Provides real-time system metrics and information through a Model Context Protocol interface, enabling access to CPU usage, memory statistics, disk information, network status, and running processes. | |
| MCP Tool AI dkokane0/mcp-tool-ai A configurable MCP gateway that runs multiple Streamable HTTP MCP servers and exposes all their tools through a single endpoint, enabling tool aggregation and routing for MCP clients. | |
| Notion MCP dkoterwa/notion_mcp Enables interaction with Notion via natural language, allowing page creation, calendar management, expense tracking, and custom tool integration. | |
| SQL Server MCP Server dkp5897/sql-server-mcp Enables AI agents to interact with SQL Server databases for debugging and data issue resolution, providing tools for query execution, schema inspection, and diagnostics. | |
| loremotion-mcp dkpiec/loremotion-mcp Enables video generation through a persistent, Google-authenticated browser session, with tools for text/image-to-video creation, history lookup, downloads, and UI probing. | |
| Flutter Tools MCP Server dkpoulsen/flutter-tools Enables interaction with the Flutter SDK by providing tools to analyze and apply fixes to Dart and Flutter files. | |
| OpenSCAD MCP Server dkpoulsen/openscad-mcp Enables AI assistants to create and manipulate 3D CAD models using OpenSCAD. | |
| customer-mcp dkreme514/quilr-ai-solutions-engineer-assessment Enables retrieval of customer records and triggering refunds via MCP tools, supporting both stdio and streamable HTTP transports. | |
| context-kernel dkritarth/context-kernel Enables Claude to pull curated context from self-hosted Markdown files via a remote MCP connector, with an append-only journal for agent notes manually promoted by the owner. | |
| Jenkins MCP Server dkropachev/jenkins-mcp Enables interaction with Jenkins instances to manage jobs, builds, and nodes through the Model Context Protocol. It provides capabilities to trigger builds, read console outputs, and search log sections using regular expressions. |
45,051–45,100 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.