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 |
|---|---|
| solidworks-mcp-pro anylxb/solidworks-mcp-pro Enables connecting MCP clients to local SolidWorks for automated 3D part creation, template generation, file export, and basic review via natural language. | |
| mcp-api-toolkit anyrxo/mcp-api-toolkit Comprehensive API development and testing MCP server for Claude Code. Integrates OpenAPI parsing, testing, SDK generation, and documentation generation into Claude workflows. | |
| Proton Drive MCP anyrxo/proton-drive-mcp A Model Context Protocol server that enables AI assistants to interact with Proton Drive files, supporting operations like listing, reading, creating, and deleting files and folders. | |
| ProtonMail Pro MCP anyrxo/protonmail-pro-mcp Enables comprehensive ProtonMail management through SMTP and IMAP, supporting email sending/reading, folder operations, analytics, and contact tracking with advanced search and automation capabilities. | |
| AnySearch anysearch-ai/anysearch-mcp-server Unified real-time search engine skill for AI agents. | |
| HDW MCP Server anysiteio/anysite-mcp-server A Model Context Protocol server that provides comprehensive access to LinkedIn data and functionality, enabling data retrieval and user account management through the HorizonDataWave API. | |
| voiceconsole anyuer678/voiceconsole A local MCP server that lets users control their computer via voice commands, executing CLI tools, searching files, and receiving spoken feedback, with safety gating and confirmation. | |
| anyvm-mcp anyvm-org/mcp Enables AI assistants to run, manage, and debug BSD/Illumos VMs through natural language. Supports creating FreeBSD, OpenBSD, NetBSD, and OmniOS VMs, executing commands inside them, accessing console logs, and managing snapshots. | |
| dataloom anzar-ahsan-commits/dataloom Enables schema-aware synthetic test data generation with deterministic replay, relational integrity, and business rules through MCP tools for introspection, classification, dataset generation, and gap suggestions. | |
| SimuLoom MCP anzar-ahsan-commits/simuloom-mcp Contract-driven service virtualization and synthetic test-data management server that enables simulating APIs from OpenAPI contracts through MCP tools. | |
| dockashell anzax/dockashell DockaShell is an MCP server that provides AI agents with isolated Docker containers for persistent shell access, file operations, and full audit trails, enabling autonomous development and self-evolving workflows. | |
| whatsapp-mcp anzmage/whatsapp-ai-bot Enables MCP clients such as ChatGPT, Claude or Grok to search and read the user's own WhatsApp message history through a linked device. Messages are stored encrypted at rest, and access is read-only unless the optional send tool is enabled. | |
| agent-session-recorder ao3575911/agent-session-recorder Enables any MCP host to start, log, and end agent sessions and export them as a normalized, redacted timeline while keeping all data local. | |
| Vision MCP aoa3ng/vision-mcp An MCP server that gives AI agents visual understanding, image generation, and video generation capabilities, with a Windows installer and manager that supports multiple model providers and agents. | |
| Personal LINE Agent aoaibiz/personal-line-agent Enables AI clients to operate a personal LINE account through MCP, listing friends and groups, retrieving and searching message history, and sending text, mentions, and registered media. Also supports group creation, display-name changes, a | |
| opencode-mcp aoalejo/opencode_mcp Lets Claude Code delegate tasks to the OpenCode CLI, choosing cost-effective models by intelligence tier and tracking usage. | |
| oanda-mcp aobathree/oanda-mcp Enables read-only access to OANDA v20 forex trading data, including price quotes, candlestick history, account summaries, positions, and transactions, via Claude. | |
| Firestorm MCP aochitoxx/firestorm-mcp Enables AI agents to inspect exports, operate mesh previews, control viewer UI and camera, capture visual evidence, and query avatar, scene, settings and event data in an installed Second Life viewer through LEAP. | |
| aoci-code aoci-spec/aoci-code A persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Local-first MCP server + CLI in Go: a governed repository index of code knowledge that gives Claude Code, Codex, | |
| Ollama MCP Server aoda4021/ollama-mcp Enables MCP-compatible applications to access local and cloud LLM model management, text generation, chat, embeddings, and web search/fetch through Ollama SDK tools. | |
| Live Bridge aoe1928/live-bridge Enables MCP clients to control Ableton Live through a Max for Live device and optional Remote Script, covering tracks, clips, MIDI notes, mixer settings, transport, and plugin search and insertion. | |
| hanzi-write aohuideqiang/hanzi-write Provides tools for Chinese character stroke order animation with tracing practice and real-time weather queries for major cities. | |
| Minecraft dots MCP aoi-dottttttt/minecraft-dots-mcp Enables an MCP client to run and control an authorized local Minecraft Java game session with guarded inventory/crafting checks, a persistent backend, and a restartable controller while keeping configuration and game state local. | |
| secfeed aoi-future/secfeed Aggregates security intelligence feeds (vulnerabilities, news, threat intel) into a local SQLite database and provides MCP tools for AI agents to query and analyze them. | |
| AOJ Workbench aojdevstudio/gdrive Private remote HTTP MCP server that provides a unified endpoint to interact with Google Workspace services (Drive, Sheets, Gmail, Calendar, Docs, Forms) and other toolkits through the Composio provider layer. | |
| Simple Memory MCP Server aojdevstudio/simple-memory-mcp A lightweight MCP server that provides persistent knowledge graph storage for AI assistants, enabling memory across sessions through entity-relationship storage with JSON file persistence. | |
| Simple Hono MCP Server aoki-collabo/simple-hono-mcp-server A lightweight MCP server built with Hono and Cloudflare Workers that provides a tool for prime factorization. It serves as a minimal implementation for deploying remote MCP servers to serverless edge environments. | |
| accurate-schema-mcp aol-integration/accurate-schema-mcp Schema-aware MCP server for Accurate Online, providing tools to list resources, lookup endpoint schemas, make authenticated API calls, and refresh database host resolution. | |
| pz-nitrado-mcp aolmosj/pz-nitrado-mcp MCP server for managing a Nitrado-hosted Project Zomboid server. It lets you check status, edit sandbox settings, manage mods, and tail logs through natural language. | |
| Chat Context MCP aolshaun/chat-context-mcp Enables AI to automatically search, retrieve, and organize your Cursor chat history across sessions. Supports tagging, nicknames, project-scoped search, and full-text search to maintain context between conversations. | |
| SEC-MCP aomala/sec-mcp MCP server for analyzing SEC filings (10-K, 10-Q, 8-K) with industry-aware financial extraction and BERT-based NLP. | |
| codebadger aomar66/codebadger Provides AI agents and LLMs queryable access to a codebase's structure and data flow via Joern Code Property Graphs, enabling CPGQL querying, taint tracing, program slicing, and vulnerability hunting across many languages. | |
| AON MCP Server aon-pro/aonpro-mcp AON(Agent Offer Network) MCP connects AI agents to real, buyable products and services with live pricing and tracked links—enabling builders to earn developer revenue share from attributed clicks and conversions. AON MCP Server owned by aon | |
| Spatial Lakehouse MCP aoneil42/spatial-lakehouse-mcp An Iceberg-native geospatial MCP server powered by DuckDB that provides tools for spatial SQL queries, catalog discovery, and data management. It enables LLM agents to interact with Apache Iceberg lakehouses to perform complex spatial analy | |
| MyCourseVille MCP Server aongzera/mcv-mcp Enables an AI agent to access a user's MyCourseVille account to retrieve assignments with deadlines, course materials, released grades, and a feed of what has changed since the last sync. | |
| ttrss-mcp aooiuu/ttrss-mcp An MCP server that enables AI assistants to manage Tiny Tiny RSS feeds, including reading articles, updating statuses, and searching content. It also provides tools for feed management and generating automated daily reports. | |
| Markdown + Mermaid to PDF MCP Server aoprisan/mcp-md-mmd-pdf Converts Markdown files and standalone Mermaid diagrams into high-quality PDF or PNG documents using Puppeteer and SVG rendering. It supports custom CSS styling and provides tools for professional document generation from markdown-based con | |
| java-class-analyzer-mcp aorls/java-class-analyzer-mcp Enables AI to analyze Java classes from Maven project dependencies, with support for decompilation strategies and configurable groupId mappings. | |
| Glance aortiz44111/glance Enables Claude Code to drive a real browser through MCP, so it can navigate pages, click and type, capture screenshots and accessibility snapshots, run multi-step test scenarios with assertions, and monitor console and network activity. | |
| Local Lens aotakeda/local-lens A 100% local development monitoring tool that captures browser console logs, network requests, and backend server output for analysis by AI assistants via MCP. It enables LLMs to debug applications by providing structured, real-time access | |
| DICOM API MCP Server aotal/dicom_api_mcp_project Exposes DICOM operations as tools for AI agents to interact with medical imaging systems and PACS. It enables searching for studies and series, querying instance metadata, and retrieving pixel data from DICOM entities. | |
| Polygate MCP Server aotemma-bit/polygate-mcp-server Enables AI clients to discover and invoke business tools for identifying inactive customers, searching internal knowledge, drafting follow-ups, and creating sales tasks. | |
| humanizer-mcp aousabdo/humanizer-mcp Measures AI-detection risk in text and provides a line-by-line rewrite plan to lower the score. | |
| GetOutpost MCP Server aoutpost2-rgb/getoutpost-mcp-server Provides real-time Indian options market data and volatility analytics from GetOutpost.in, enabling analysis of implied volatility, realized volatility, volatility risk premium, and skew patterns for data-driven options trading insights on | |
| genesis-ai-bridge aowdgenesis/genesis-ai-bridge Provides a local MCP server for securely analyzing files, ZIP archives, and directories with Ollama or other providers, and generating correction proposals that are applied only after explicit user confirmation. | |
| San9MCP aoye516/san9mcp Enables AI agents to connect to and control a windowed copy of Romance of the Three Kingdoms IX with Power Up Kit, letting them observe the game UI, gather officer/city intelligence, issue facility/transport commands, and advance turns thro | |
| firsty-mcp aoyn1xw/firsty-mcp An MCP server that wraps the Firsty telecom API, allowing AI agents to manage eSIMs, data plans, phone numbers, and network coverage. | |
| Charlotte aozkan496/charlotte Gives AI agents token-efficient browser access by returning compact, structured page summaries, targeted element queries, and on-demand detail instead of full accessibility-tree dumps. Supports navigation, interaction, monitoring, and sessi | |
| Pentest MCP aozkan613/pentest-mcp Enables professional penetration testers to orchestrate reconnaissance, web/content scanning, brute-force checks, traffic capture, privilege-escalation auditing, wordlist generation, and client reporting through MCP transports with optional | |
| bugsink-mcp ap-justin/bugsink-mcp Enables Claude Code and claude.ai to read error tracking data and triage issues from a self-hosted Bugsink instance through a remotely deployed, OAuth-gated MCP server. |
29,751–29,800 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.