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 |
|---|---|
| BuildAutomata Memory MCP Server brucepro/buildautomata_memory_mcp Provides AI agents with persistent, searchable memory that survives across conversations using semantic search, temporal versioning, and smart organization. Enables long-term context retention and cross-session continuity for AI assistants. | |
| gamebook bruceweir/gamebook Enables LLMs to play interactive choose-your-own-adventure stories through MCP tools for starting adventures, making choices, managing inventory, examining scenes, requesting hints, and checking player status. | |
| ChatGPT Apps MCP Server brucewilliamchen/mcp-server Enables interactive React components to render inline in ChatGPT conversations, featuring a calculator widget with history and demonstrating how to build custom UI components for ChatGPT Apps. | |
| Fiken MCP bruchris/fiken-mcp Enables interacting with Fiken accounting data—companies, accounts, contacts, purchases, and attachments—through the Model Context Protocol, with write previews and confirmation requirements. | |
| Folio MCP bruchris/folio-mcp Enables interaction with Folio financial data through the Model Context Protocol, covering accounts, transactions, events, receipt bytes, categories, and payment drafts with preview-and-confirm writes. | |
| IndeCX MCP brudarko/indecx-mcp Enables MCP clients to query the IndeCX public API for survey data, including actions, questionnaires, answers, invites, non-respondents, categories, blocklists, and branches. | |
| Jobber Automation MCP bruhmaster32/jobber-automation-mcp Enables ChatGPT to inspect Jobber data and manage controlled automations with scheduling, approval workflows, and audit trails. | |
| paperclip-mcp bruhsb/paperclip-mcp MCP server that exposes the Paperclip control plane API as tools for Claude Code agents — manage issues, coordinate agents, post comments, and orchestrate work without direct API calls. | |
| MCP-TUPAD brujoh88/mcp-tupad Enables AI assistants to query the UTN distance learning Moodle campus, providing tools to list courses, view content, check deadlines, see grades, and more. | |
| Datadog MCP Server brukhabtu/datadog-mcp A Model Context Protocol server that enables AI assistants to interact with Datadog's observability platform through natural language. | |
| Jira MCP Server brukhabtu/jira-mcp A production-ready server that automatically exposes your entire Jira instance through the Model Context Protocol, allowing seamless interaction with Jira's API features including issue management, project administration, and user managemen | |
| Rope MCP brukhabtu/rope-mcp A Model Context Protocol server that exposes Python Rope refactoring capabilities to Claude Code, enabling safe symbol renaming, method extraction, code analysis, and more. | |
| labsolu-mcp-test brulure1/labsolu-mcp-test Enables developers to deploy a Model Context Protocol server to Render with bearer token authentication, allowing custom tools to be connected to MCP clients like Claude Desktop and Cursor. | |
| Snippy bruna27463/snippy Enables AI assistants to save and retrieve code snippets with vector embeddings for semantic search, generate language-specific code style guides, and create comprehensive wiki documentation. It also orchestrates multi-agent workflows that | |
| Sub-Agents MCP Server bruna646/sub-agents-mcp Enables users to define task-specific agents in Markdown files and run them through a chosen coding CLI (Codex, Claude Code, Cursor, and others) from any MCP-compatible client, with results returned to the same conversation. Supports shared | |
| jevcore-mcp brunas433/jevcore Enables MCP hosts to pose typed questions — yes/no, choice, and score — and receive calibrated probabilities instead of prose, over a stdio transport. Runs offline against a synthetic mock by default, with every transmission to a live provi | |
| GUARDIAN MCP brundhas26/guardian-mcp Enables secure runtime mediation of tool requests from MCP-connected AI agents, enforcing least-privilege policies, validating intent and inputs, detecting multi-step attacks and information leaks, and supporting explainable decisions, audi | |
| Stegstr brunkstr/stegstr Hide a message inside a photo so it survives being sent through WhatsApp, Telegram, Instagram, Facebook or X. Tools: embed, decode, detect, and calibrate a channel from a sent/returned image pair. Platform targets are calibrated against rea | |
| mcp-github-explorer-server bruno-gabrieldev/mcp-github-explorer-server MCP server for exploring GitHub public data. It provides tools to fetch user profiles, list top repositories, and calculate language usage statistics, which AI agents can invoke dynamically. | |
| Google Search Console MCP Server brunoaires22/gsc-mcp-server Connects AI assistants to site performance and indexing data, enabling listing of verified properties, querying organic traffic metrics, and inspecting URL indexing status. | |
| mcp-server-reference brunoaquino/mcp-server-reference Enables MCP hosts to list, look up, and describe a static catalog of OpenAPI operations, and to inspect a governing contract and explicit deny-list that define what the server refuses to do. | |
| memory-as-history brunobanana/memory-as-history Provides a SQLite-backed MCP server that records agent memory as history, enabling explicit consolidation, source checks, revisions, narrative versions, and accountable forgetting. | |
| Vercel MCP Adapter brunobenavent/mcp-vercel Enables real-time communication between applications and AI models using the Model Context Protocol, supporting features like custom tools and multiple transport options for Next.js applications. | |
| Cinema4D MCP Server brunobishop55087/cinema4d-mcp Connects Claude to a running Cinema 4D instance so users can build and edit 3D scenes through natural-language prompts, including primitives, cameras, lights, materials, MoGraph cloners, dynamics, keyframes, and rendered previews. It also e | |
| threejs-devtools-mcp brunobishop55087/threejs-devtools-mcp Enables AI agents to inspect and edit live Three.js scenes in the browser—objects, materials, shaders, lights, textures, animation, performance and memory—without modifying the project. Live tweaks can be previewed, captured as before/after | |
| SceneScout brunoboto96/scenescout This MCP server enables AI agents to perform exploratory UI testing of live web apps by providing a structured view of page elements, deterministic correctness oracles, enforced read-only or opt-in write policies, persistent cross-run memor | |
| MS 365-21V MCP Server brunoc4426/ms-365-21v-mcp-server Enables MCP-capable AI clients to act on behalf of a user against 21Vianet-operated Microsoft 365, querying mail, calendars, OneDrive and SharePoint through Microsoft Graph China while respecting existing user permissions, confirmation prom | |
| Nearest Tailwind Colors brunocpf/nearest-tailwind-colors-mcp Finds the closest Tailwind CSS palette colors to any given CSS color value. Supports multiple color spaces and customizable result filtering to help match designs to Tailwind's color system. | |
| livechat-mcp brunocramos/livechat-mcp Enables continuous voice conversation with AI coding assistants by locally transcribing speech with Whisper and delivering utterances as text prompts. | |
| Excalidraw Architect MCP brunod187/excalidraw-architect-mcp Enables AI coding assistants to turn architecture descriptions into auto-laid-out, hand-drawn diagrams across 25 types, then revise them in natural language and export SVG/PNG. It can also persist and query a version-controlled architecture | |
| lgtv-control-mcp brunofgmag/lgtv-control-mcp An MCP server for controlling LG webOS TVs via SSAP protocol, enabling AI clients to adjust settings, switch inputs, launch apps, and more. | |
| OpenProject MCP Server brunofin/openproject-mcp Enables AI agents to interact with OpenProject's APIv3 for autonomous project management, including task tracking, member administration, and project configuration. It supports comprehensive operations for managing work packages, projects, | |
| wow-mcp brunofin/wow-mcp A comprehensive MCP server that wraps the complete World of Warcraft retail API into 197 tools for Game Data and Profile information. It enables users to query character statistics, achievements, collections, and game mechanics across all g | |
| jurisprudenciaia-mcp brunoflma/jurisprudenciaia-mcp Self-hosted MCP connector for querying Brazilian legal jurisprudence via JurisprudenciaIA. Enables natural language legal research using Claude.ai, with tools for consulting, searching, and comparing jurisprudence and legal theses. | |
| mcp-databricks-server brunofqueles/mcp-databricks-server MCP server for Databricks Unity Catalog, enabling table listing, schema description, and read-only SQL query execution via natural language. Built from scratch to demonstrate JSON-RPC 2.0 protocol depth. | |
| Athena Investigation MCP Server brunofreitas-br/athena-investigation-mcp-server Enables governed, read-only investigations of Amazon Athena access logs by searching exact user, IP, or correlation indicators and summarizing activity by correlation ID, with parameterized queries, validation, and result limits. | |
| MCP Project Guard brunogar6/mcp-project-guard This MCP server automatically analyzes project architecture and finds similar code patterns to maintain consistency across different programming languages. | |
| Instagram DM MCP Server brunohalas3821/instagram_dm_mcp Enables sending, reading, and managing Instagram Direct Messages from your own account through Claude Desktop or Cursor, including sending text, photo, and video messages, listing and searching chats and threads, downloading media from mess | |
| orbit-mcp-server brunojmd1/mpc-upunity-lovable Enables Claude to manage Orbit tasks directly through natural language, including creating, listing, updating, changing status, completing, and deleting tasks via the Orbit REST API. | |
| JMComic AI MCP Server brunokomarov91/jmcomic-ai Enables AI agents to search, browse, favorite, download, track tasks, post-process, configure, and log in to adult comic services through standardized MCP tools and knowledge resources. | |
| caldav-mcp brunokwon/caldav-mcp Enables AI assistants to connect to CalDAV servers and manage calendars, events, and tasks through MCP tools. | |
| MongoDB MCP Server brunol28/mongodb-mcp Enables AI assistants to interact natively with MongoDB databases, including schema discovery, CRUD operations, aggregation pipelines, and index management via natural language. | |
| mal-mcp brunolm/mal-mcp A Model Context Protocol server that provides access to MyAnimeList's API for anime and manga data. It enables users to search, view rankings, manage their personal lists, and get recommendations through Claude and other MCP clients. | |
| steam-mcp brunolm/steam-mcp MCP server for the Steam Web API, exposing your game library, playtime, achievements, friends, wishlist, and the Steam store to MCP clients over stdio. | |
| FastAPI CRUD MCP brunolnetto/fastapi-crud-mcp A minimal CRUD API for items that exposes FastAPI endpoints as MCP tools, enabling natural language interaction with a database through PydanticAI agents. | |
| MCP Design System Bridge brunonepomuceno/mcp-design-system-bridge-cursor Enables bidirectional synchronization between IDEs and Figma for Design System management, allowing developers to generate React components and synchronize design tokens, icons, and components across platforms. | |
| MCP Evolution API Supergateway brunonuzzi/evo-mcp Acts as a gateway to interface with the Evolution API, exposing an MCP server via SSE for remote connections. | |
| Stride28 Search MCP brunonxu/stride28-search-mcp Enables AI assistants to search real content from Xiaohongshu and Zhihu, supporting keyword search, note details, and question retrieval. | |
| mcp-confluence-context brunoog-ciet/mcp-confluence-context Enables searching and retrieving Confluence pages, listing children, and updating pages as drafts, integrating Confluence documentation as context in Claude Code. | |
| brunopark-mcp brunopark852/brunopark-mcp AI-orchestrated security testing via 6 Python tools (recon, port scan, subdomain hunting, frontend scanning, API fuzzing, and nemesis orchestrator) exposed as MCP tools for use by AI agents. |
35,751–35,800 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.