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 |
|---|---|
| sql-guard-mcp egoring/sql-guard-mcp Enables AI agents to safely query and explore SQLite databases through read-only, guard-protected tools that block writes, sensitive table access, and runaway queries. | |
| LAML MCP Server egorkluch/mcp-laml Enables loading and accessing LAML (YAML-based markup language) documents from the filesystem through the Model Context Protocol. | |
| apple-calendar-mcp egorkurito/apple-calendar-mcp MCP server for Apple Calendar via native EventKit API with proper recurring event support. | |
| Tracker MCP Server egormak/tracker-mcp Enables LLM clients to interact with a local tracker-server for checking schedule, retrieving statistics, registering tasks, and managing timers. | |
| Personal Filebridge egormakarenkov/personal-filebridge Enables controlled local Windows file inspection, reading, writing, reversible deletion, restoration, and auditing across user-selected folder roots. Commits occur only after separate owner approval in a native desktop dialog, while the too | |
| shoptet-admin-mcp egornefedovcz/shoptet-admin-mcp Enables an AI assistant to inspect a Shoptet e-shop admin and, when explicitly enabled, make guarded changes such as creating coupons, adding redirects, updating variant price or stock, and replacing HTML or banner content through a local P | |
| Webflow MCP Server egorov01/mcp-server Enables AI agents to interact with Webflow's Data API and Designer through natural language, supporting content analysis, blog and SEO workflows, internal linking, and on-canvas design creation such as responsive sections and CTA buttons. I | |
| Canvas MCP Server egorov01543/mcp-canvas-lms Enables students, instructors, and account administrators to interact with Canvas LMS through its API, covering course and assignment workflows, submissions, grading, discussions, grades, files, enrollments, reports, and multi-account admin | |
| tmux-bridge-mcp egorov01543/tmux-bridge-mcp Enables AI coding agents running in separate tmux panes to read each other's output, send messages and keystrokes, and coordinate multi-agent workflows through standard MCP tool calls. It lets existing MCP-compatible agents communicate cros | |
| Mendix Context Bridge egorsel/mendix-local-mcp Enables AI agents to read and understand local Mendix project structure and logic by connecting directly to the .mpr file via MCP. Allows querying microflows, entities, attributes, and modules in read-only mode without requiring cloud acces | |
| yt-subtitles-mcp egoryolkin/yt-subtitles-mcp Enables AI assistants to fetch YouTube video metadata, chapters, and timestamped transcripts (including paginated and language-specific caption retrieval) so they can produce summaries, study notes, comparisons, and source-referenced answer | |
| tool-disco egoughnour/tool-disco A tool discovery MCP server that integrates with Azure DevOps wikis and code-graph-rag to match natural language goals to tools, enabling tool composition and proxy testing. | |
| chronicle egoushka/chronicle Aggregates personal events from multiple sources into a unified timeline and exposes them via MCP for AI assistant retrieval. | |
| devbox-mcp egoushka/devbox-mcp Enables an LLM to run a project's real test suite and SonarQube scan against on-disk projects using throwaway, socket-proxied containers without granting raw shell access. | |
| Oura MCP App egoushka/oura-mcp-app Enables querying daily Oura Ring metrics from a self-hosted Postgres warehouse and rendering interactive trend charts inline in compatible MCP hosts, with text summaries for hosts that lack chart support. | |
| quartet egradman/quartet MCP server enabling AI agents to collaborate in shared rooms with a document edited via compare-and-swap optimistic concurrency, plus a chat channel and change deltas. | |
| Ollama MCP Server egregory231/ollama-mcp Enables MCP-compatible applications to manage local and cloud Ollama models and perform model operations, chat, text generation, embeddings, web search, and web content fetching. | |
| Brainbase MCP Server egrigokhan/brainbase-mcp Provides 70 tools to interact with the Brainbase API, enabling management of workers, chat/voice deployments, flows, resources, and more via natural language. | |
| Bitbucket MCP egrigorev36/bitbucket-mcp Enables AI assistants to interact with Bitbucket Cloud and Server APIs by listing repositories, retrieving repository details, fetching and creating pull requests, and accessing related resources with configurable authentication and paginat | |
| MCP-GMX-VMD egtai/gmx-vmd-mcp Integrates GROMACS molecular dynamics simulations with VMD visualization, enabling setup, execution, analysis, and 3D visualization of molecular dynamics workflows through natural language. | |
| slack-mcp egumayuto/slack-mcp MCP server for interacting with Slack using a user token. It allows reading channels, DMs, threads, search, and posting messages as the authenticated user. | |
| Dart MCP Server egyleader/dart-mcp A distributable Model Context Protocol (MCP) server that exposes Dart SDK commands for AI-powered development. This server bridges the gap between AI coding assistants and Dart/Flutter development workflows by implementing the Model Context | |
| email-mcp-server egyptianego17/email-mcp-server An MCP server that enables AI assistants to send emails via SMTP, supporting simple and custom emails with attachments and CC/BCC, plus connection testing. | |
| Povio Worklog MCP Server egzonarifi/povio-worklog-mcp Automates the generation of professional worklogs by analyzing git commits with AI enhancement and seamlessly posting them to the Povio dashboard. It enables users to list projects, extract ticket numbers, and manage worklog entries through | |
| SchedulifyX MCP Bridge eh-mr-sk/schedulifyx-mcp-bridge Stages local images and videos into SchedulifyX by uploading files out-of-band and returning media IDs, enabling scheduling without passing bytes through the AI context. | |
| gcal-mcp eh24905-wiz/gcal-mcp A Model Context Protocol (MCP) server for read-only Google Calendar integration, providing calendar access to AI assistants. | |
| Jira MCP Server eh24905-wiz/jira-mcp Enables AI assistants to interact with Jira Cloud by managing issues, comments, custom fields, and sprint tasks through a standardized interface. Supports issue creation, updates, team activity tracking, and progress reporting. | |
| rn-devtools-mcp ehab-aqili/react-native-devtools-mcp Enables AI assistants to inspect React Native app performance including memory, rendering, frames, and network requests, providing plain-language summaries and shareable reports. | |
| gnews-mcp-server ehabsa/gnews-mcp-server Provides access to the GNews API for searching news articles and retrieving top headlines with advanced filtering options. | |
| Email SMTP/IMAP MCP ehanahmed/email-mcp Enables searching, reading, sending, replying to, forwarding, and organizing email across multiple SMTP/IMAP accounts. | |
| Agile Backlog MCP ehartye/agile-backlog-mcp Enables comprehensive agile project management with epics, stories, tasks, and sprint planning through natural language. Features project isolation, dependency tracking, and integrates with a web UI for visual backlog management and burndow | |
| issue-fix-mcp ehartye/issue-fix-mcp A Model Context Protocol server that enables coding agents to search for and record software issue fixes with semantic search using natural language queries. | |
| Image Context Runtime ehayes164/codex-image-context-runtime Enables Codex to run image generation and inspection as durable, resumable local jobs while keeping provider-returned media bytes outside the MCP boundary. Returns only bounded text handoffs, hashes, relative artifact references, and Job ID | |
| QMD - Query Markdown ehc-io/qmd Provides hybrid search over local markdown knowledge bases using BM25 keyword search and vector semantic search. Enables indexing, querying, and retrieving markdown documentation with dual-mode support for local and remote agents. | |
| Daiso MCP Server ehddk6-cyber/daiso-mcp Connects AI models to real-time search and inventory data for major South Korean retail chains, convenience stores, and cinemas. It enables users to check product availability at stores like Daiso and Olive Young, or view movie schedules at | |
| milltime ehellman/milltime Enables AI assistants to read and write Milltime time reports, expenses and travel allowances over stdio, with every write previewed and confirmed by token before anything is sent. Uses the login saved by the CLI, so the assistant never see | |
| MiniMax Coding Plan MCP ehenderson7756/minimax-coding-plan-mcp Enables coding-plan users to perform web searches and analyze images with AI-powered tools through MCP clients. Integrates these capabilities into code development workflows for retrieving information and understanding visual content. | |
| mcp-store ehewes/mcp-store Aggregates multiple MCP servers and custom Python tools behind a single endpoint, with intelligent context and tool discovery for AI agents. | |
| pixel-mcp ehm-93/pixel-mcp Enables LLMs to create and edit pixel art reliably with support for layers, frames, symmetry, and various drawing tools. | |
| wiri ehm-93/wiri Wiri is a headless wireframing MCP server designed for an LLM operator. It stores each screen as a small semantic scene graph, lays elements out without absolute coordinates, and closes the editing loop with deterministic renders and lint f | |
| long-video-mcp ehmad9/long-video-mcp Enables Claude to plan, script, pace, and package long-form videos by splitting a target duration into structured segments, saving and timing narration against a word-per-minute budget, tracking project progress, and generating YouTube chap | |
| policy-mcp ehrc/reliable-agentic-rag Enables searching fictional policy documents and assessing expense claims against deterministic rules via MCP, returning structured assessments and citations without an approval tool. | |
| ecommerce-catalog-agent ehrekov/ecommerce-catalog-agent Enables conversational product search and validation for e-commerce catalogs, with hybrid retrieval and live price/stock checks from a database. | |
| mcp-juridico-brasil ehrodan/lexmcp Connects AI assistants to Brazilian judicial data via DataJud CNJ, LexML, and local corpus, enabling process consultation, legal research, and document generation with Visual Law. | |
| TimeTree MCP Server ehs208/timetree-mcp Unofficial MCP server for accessing and managing TimeTree calendar data, including events, memos, and comments, with secure email/password authentication. | |
| watercooler ehs5/agent-watercooler Enables AI agents on the same machine to join a local chat room over MCP so they can coordinate tasks and hand off context, with a browser view for following along. | |
| TheGenie ehsanghorbani190/thegenie Enables AI writing assistants to retrieve citable evidence from local PDFs and verify draft citations against their sources locally, providing verifiable support for claims. | |
| Joblet MCP Server ehsaniara/joblet-mcp-server Enables AI assistants to manage distributed computing jobs through the Joblet platform, supporting job orchestration, workflows, storage, networks, and monitoring. | |
| MkDocs MCP Server ehsanmsb/mkdocs-mcp A generic, configurable MCP server that makes any MkDocs documentation site searchable and explorable from MCP clients. | |
| SciAgentKit ehsansyh/sciagentkit MCP-native scientific skills for reproducible computational biology and AI-driven drug-discovery workflows. It combines deterministic scientific tools with an MCP server to give AI agents real computational capabilities. |
47,251–47,300 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.