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-shodan dorothyhedlund512/mcp-shodan Enables AI agents to perform internet reconnaissance, device search, DNS lookups, and CVE/CPE vulnerability analysis through read-only Shodan-powered tools. | |
| knowledge-base-server dorothyinoue80287/knowledge-base-server Enables AI agents to share persistent memory by ingesting knowledge from sources like Obsidian, code, documents, web clips, and terminal sessions, then providing token-optimized search, context, classification, synthesis, and capture tools | |
| MiniMax Coding Plan MCP dorothymaas/minimax-coding-plan-mcp Enables AI coding assistants to run web searches that return organic results with related queries and to analyze images from URLs or local files via prompt-driven vision models. It connects to MCP clients such as Claude Desktop, Cursor, and | |
| Sugar dorothymartinez015/sugar Provides a local-first, cross-session memory layer that lets AI coding agents store and semantically search per-project decisions, preferences, error patterns, and research alongside global guidelines. Also supports an optional task queue f | |
| MCP Proxy Sidecar dortegau/mcp-proxy-sidecar A modified JetBrains MCP Server that adds WebSocket monitoring capabilities, allowing users to monitor MCP tool calls in real-time while maintaining compatibility with the original implementation. | |
| ai2dev-mcp dorthyuser/mcp-trial-python An MCP server that designs software projects by drafting design documents with an LLM, refining them, answering questions, and creating projects via the AI2DEV API. | |
| WaWarden dortort/wawarden A self-hosted WhatsApp gateway that connects a personal WhatsApp account to AI agents and applications over REST and MCP. It maintains a local message archive and enforces per-client, per-chat permissions for reading and sending messages. | |
| Harness Council dorukanc/harness-council Local multi-harness orchestration for Claude Code, Grok CLI, and AGY CLI, enabling spawning, management, and coordination of AI coding agents in a visible terminal grid. | |
| mdbp-server dorukyelken/model-database-protocol Enables AI systems to securely query databases using structured intents (MDBP) with automatic schema discovery and policy enforcement. | |
| dosbox-mcp dosbox-automation/dosbox-mcp Bridges AI agents to a DOSBox emulator, enabling control of DOS programs via MCP tools for typing, screen reading, video capture, Lua scripting, and memory access. | |
| GraphJin dosco/graphjin Enables AI assistants to query databases using natural language, with automatic schema discovery and SQL compilation. | |
| ira-universe doshirush1901/ira-universe Public-safe visitor MCP for Claude Code and Cursor that explains what Ira is, how it is built, and how to adopt a factory-specific fork without sensitive data. | |
| MCP Stock Tracker dosinga/mcp_app_stocks Provides real-time stock price tracking with an interactive dashboard, fetching data via Alpha Vantage API. | |
| PyKernel MCP dosinga/pykernel_mcp MCP server that provides a persistent IPython kernel for executing Python code with pre-loaded numpy, pandas, and matplotlib, supporting stateful computation and inline visualizations. | |
| Torreable dosinga/torreable Publish static websites as Tor hidden services (.onion sites) via MCP. | |
| Glyph Hold MCP dosk3n/glyphhold-mcp MCP server that connects Codex and other MCP clients to a running Glyph Hold instance via its HTTP API, enabling memory and secret management. | |
| vegavisuals dosquartsdedocs/vegavisuals Provides a stdio MCP server for rendering Vega-Lite and Vega specifications to SVG, PNG, or PDF with reproducible Docker isolation and immutable provenance. | |
| Dossin MCP Server dossincargas/dossin__mcp Enables natural language interaction with the Dossin database system, allowing users to query trucking and logistics data, execute SQL queries, and compile React components via the backend API. | |
| sii-mcp dostertags/sii Enables users to interact with Chile's SII tax authority through natural language, including checking tax documents, invoices, filings, and administrative requests. It supports browser-based login and optional write operations when explicit | |
| bottari dostevskii/bottari Enables Claude Desktop to synchronize and manage your CLI setup (skills, settings, sessions, projects) across machines via encrypted Google Drive, with conflict resolution and version history. | |
| Voicevox MCP Server dosugamea/voicevox-mcp-server A server that enables Claude 3.7 and other AI agents to access VOICEVOX-compatible speech synthesis engines (AivisSpeech, VOICEVOX, COEIROINK) through the Model Context Protocol. | |
| zendesk-help-center-anon-mcp-server dosugamea/zendesk-help-center-anon-mcp-server MCP server to retrieve information from Zendesk Help Center using anonymous authentication. Provides tools to list categories, sections, articles, and search articles. | |
| onenote-mcp dosxnjos/onenote-mcp Enables Claude and other MCP clients to read, create, and edit OneNote pages on a personal Microsoft account via Microsoft Graph, restricted to an allowlist of sections and without any delete operation. | |
| MCP (dot-do) dot-do/mcp A framework that provides search, fetch, and do primitives to enable AI agents to orchestrate complex tasks via sandboxed TypeScript code execution. It optimizes performance and security by reducing multiple sequential tool calls into a sin | |
| Fathom AI MCP Server dot-fun/fathom-mcp Enables AI assistants to access Fathom meeting recordings, summaries, transcripts, teams, and webhooks through the Model Context Protocol. | |
| SnappShop MCP Server dot1mav/snappshop-mcp Enables LLMs to search products, fetch detailed specifications, and browse categories from SnappShop in real-time. | |
| productive-io-mcp dotcollective-joel/productive-mcp Enables interaction with Productive.io task management platform, allowing users to retrieve tasks and filter by assignee, status, or project. | |
| ContextForge MCP Lab dotdigitize/contextforge-mcp-lab A local MCP-style server for managing task records and seeded documents through controlled tool functions, using SQLite and JSON seed data. | |
| Workforce Orchestrator MCP dotfrankruan/workforce-orchestrator-mcp Turns an MCP-capable planner such as Codex into a supervisor over pluggable worker backends, letting it run task-DAG workflows in isolated git worktrees with budgets, roles, acceptance tracking, metrics, and durable state that survives rest | |
| code-intel-mcp dothinh115/code-intel-mcp Enables efficient codebase exploration with tools to list exports, get file outlines, read targeted regions, and find references without loading entire files. | |
| mcp-glama-demo dotku/mcpm mcp-glama-demo | |
| ImageMcp dotlab-hq/imagemcp A full-featured image processing MCP server for AI assistants, exposing ~55 tools across 11 categories for editing, layers, conversion, AI segmentation/cleanup/generation, design analysis, and screenshot-to-code. | |
| @dotlab-hq/vector-store-mcp dotlab-hq/vector-store-mcp MCP server for OpenAI Vector Store API, managing vector stores, files, file batches, and semantic search. | |
| DeepSeek Web Research MCP dotm5/deepseek-web-research-mcp Enables local stdio access to DeepSeek Search/Fetch for web search, page extraction, bounded site discovery, code context, and asynchronous SQLite-backed research with secure credential storage. | |
| edinet-mcp dotmd-projects/edinet-mcp Enables access and analysis of Japanese corporate financial data (PL/BS/CF) via EDINET API. Supports searching companies, listing reports, and comparing financials through natural language queries. | |
| mcp-recon dotmuny/mcp-recon Enables AI agents to run reconnaissance tasks such as DNS, WHOIS, certificate transparency, TLS certificate, HTTP header, and limited port checks against explicitly authorized domains and IPs. Scope permissions, deny rules, default-deny res | |
| notes-gpuix dotnacer/notes-gpuix Enables AI assistants to read, create, update, delete, and search markdown notes stored locally. | |
| SimpleTgChatMcp dotneteeer/simpletgchatmcp Enables Claude to send messages, media, and manage Telegram chat messages through a Telegram bot, including sending photos, documents, and editing or deleting messages. | |
| infomesh dotnetpower/infomesh Fully decentralized P2P web search engine for LLMs. Crawls, indexes, and searches the web via a peer-to-peer network — no API key, no billing. Exposes 5 MCP tools: web_search, fetch_page, crawl_url, fact_check, and status. | |
| Fandom Wiki MCP Server dotnetrule/mcp-fandomwiki A generic MCP server that allows searching and retrieving articles, summaries, category members, and wiki info from any Fandom wiki. | |
| ProDoctor MCP Server dotojr123/mcp-prodoctor Exposes the ProDoctor Cloud API as MCP tools for AI agents to manage appointments, patients, users, and procedures. | |
| dotpm dotpm/cli Enables coding agents to manage Obsidian projects and tasks through MCP tools over stdio, bridging the plugin's local API without needing a secret in client config. | |
| swiftadopt-mcp dotreflection/swiftadopt-mcp An MCP server that helps developers migrate Swift projects to Apple's 2026 platforms by adopting new frameworks and best practices from WWDC 2026. | |
| MCP Context Server dotteduniverse/model-context-protocol-server A secure multi-tenant server that provides real-time context to LLMs via REST API, using JWT authentication and PostgreSQL row-level security for tenant isolation. | |
| ChatGPT Remote SSH MCP double-wk/chatgpt-mcp-bridge Enables users to run remote commands, inspect projects, transfer files, and execute scripts on authorized Linux servers through natural-language tool calls. It supports listing servers and groups, executing commands individually or across g | |
| blooketsimulator-mcp double2dev/blooketsimulator-mcp An official MCP server for Blooket Simulator to simulate unboxing, check drop rates, and fetch blook info via AI. | |
| CognitiveBiasLabs-MCP double2dev/cognitivebiaslabs-mcp An MCP server that enables LLMs to detect cognitive biases and logical fallacies in text, list supported biases, and provide links to relevant psychology tests. | |
| freeaudiototext-mcp double2dev/freeaudiototext-mcp 100% Free AI audio and video transcription with speaker diarization and YouTube support. | |
| imposter-game-mcp double2dev/imposter-game-mcp MCP server for playing the Imposter Game (Spyfall alternative) with AI as host. Provides tools to get categories and generate game words with secret roles. | |
| online-tone-generator-mcp double2dev/online-tone-generator-mcp An official MCP server for Online Tone Generator. Discover audio frequencies for instrument tuning, acoustic testing, meditation, and generate direct listening links. |
45,651–45,700 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.