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 |
|---|---|
| QLD Legislation MCP Server callmemitch27/legislation-qld-cth-retrieval-augmented-generation- A standalone MCP server enabling semantic search over Queensland and Commonwealth legislation stored in a ChromaDB vector store. | |
| AutoMaya MCP callmeparams/automaya-mcp Enables Claude and other MCP clients to control Autodesk Maya 2024 through 244 typed tools, including modeling, rigging, previs, FX, Arnold rendering, asset libraries, AI 3D generation, and a real-time change stream for Unreal. | |
| cob-shopify-mcp callobuzz/cob-shopify-mcp A production-grade MCP server and CLI tool that enables AI agents to manage Shopify stores through 49 built-in tools across products, orders, inventory, and analytics. It supports natural language workflows for tasks like inventory tracking | |
| CallRemind MCP Server callremind/callremind-mcp Enables AI agents to make instant calls, manage CEMAS emergency notifications, pick Edge TTS voices, manage agents, leads, scheduled calls, and query call history via the CallRemind REST API. | |
| trace-canvas callsymmetryecho/trace-canvas Enables AI agents to capture coding sessions onto a shared transit map of threads and records, then list, read, fork, merge and log entries on it. It also exposes running sessions and per-thread goals and to-dos, so a new session can catch | |
| cisco-axl-mcp calltelemetry/cisco-axl-mcp An MCP server that enables AI assistants to manage Cisco Unified Communications Manager (CUCM) via AXL SOAP API, supporting provisioning, configuration, and database queries through natural language. | |
| cisco-cucm-mcp calltelemetry/cisco-cucm-mcp MCP server for Cisco CUCM operational debugging — 61 tools covering logs, device inventory, performance monitoring, packet capture, call analysis, service control, AXL discovery, certificates, backups, CTI status, and cluster topology. | |
| Cisco RIS MCP Server calltelemetry/cisco-ris-mcp Enables querying Cisco CUCM Real-time Information Service and Performance Monitor data through MCP tools for device status, CTI connections, counter monitoring, and cluster health. | |
| cucm-emulator-mcp calltelemetry/cucm-emulator-mcp Enables AI assistants and automation agents to interact with Cisco CUCM Emulator instances through dynamically generated tools for telephony operations, call simulation, routing policies, CDR buffers, and optional offline mock state. | |
| atlassian-mcp callum-smith-mns/atlassian-mcp Enables AI agents to interact with Jira and Confluence on Atlassian Cloud, supporting issue search, creation, updates, transitions, project listing, content search, page management, and comments. | |
| ssh-mcp callumbicknell/ssh-mcp Enables AI agents to safely access and administer remote machines over SSH using existing OpenSSH config, with typed tools for running commands, reading and writing files, listing directories, and retrieving file metadata. | |
| PhoneBooth MCP Server callwallagent/phonebooth-mcp Enables AI agents to make real-world phone calls with AI voice technology and provides tools to track call status, transcripts, and summaries. It supports automated communication with both live numbers and simulated businesses for testing a | |
| train-mcp-server callwatersword/train-mcp-server Enables querying train and high-speed rail schedules, durations, and seat availability between Chinese stations using 12306 data, with automatic fallback to simulated data when the API is rate-limited. | |
| CallZero MCP Server callzero-ai/callzero-mcp Enables AI assistants to make phone calls via CallZero service, with tools for call management, templates, and memory. | |
| Calq MCP calq-dev/calq-mcp A comprehensive MCP server for time tracking, project management, and AI-powered memory storage using semantic search. It enables users to log time, manage client billing, and capture shared or personal ideas through integrated tools and te | |
| MCP Label Printer calumjs/mcp.printer Enables printing labels with QR codes and text to a Brother QL-810W printer via P-touch Editor Lite, useful for creating physical labels for GitHub issues and pull requests. | |
| TimePRO MCP Server calumjs/timepro.mcp An MCP server that wraps the TimePRO API, enabling AI assistants to automatically create, view, and manage timesheets for authenticated users. It provides tools for searching clients and projects, retrieving configuration defaults, and perf | |
| restaurant-reservation-monitor-mcp caluya-rita/restaurant-reservation-monitor-mcp-captcha-capsolver Enables monitoring restaurant reservation availability while handling CAPTCHA challenges using CapSolver, with allowlisted targets and bounded resume. | |
| secure-harness-mcp calvarado2004/secure-harness-mcp Verify-and-repair secure-coding harness that generates, hardens, audits, and scores Go code with a build and security scan feedback loop, and includes a transparent proxy to harden any client automatically. | |
| Alpha Vantage MCP Server calvernaz/alphavantage Provides access to real-time and historical stock market data through the Alpha Vantage API, enabling financial analysis and market data queries through natural language. | |
| Memory MCP calvin-francis/memory-mcp A Model Context Protocol server that provides AI assistants with persistent semantic memory and knowledge graph capabilities using PostgreSQL and vector embeddings. It enables cross-session storage, hybrid search, and complex relationship t | |
| data-agent-service calvinchengx/data-agent-service Enables natural-language queries over data warehouses with catalog-grounded semantics and per-query authorization, returning answers with attached reasoning. | |
| retrace-mcp calvingunther66/retracemcpclaude Read-only MCP server for searching your local Retrace screen-history database, with tools for full-text search, segment listing, frame details, app usage, and tags. | |
| h1b-sponsor-mcp calvinlee326/h1b-sponsor-mcp Enables querying USCIS H-1B employer sponsorship history, ranking top sponsors by US state, and retrieving dataset summary. | |
| Stock Market Analysis MCP Server calvinliuu/stock_mcp_server Enables comprehensive stock market analysis with portfolio management, technical indicators, dividend tracking, sector analysis, risk metrics, and price alerts. Provides real-time stock data, trend analysis, and investment insights through | |
| MTS MCP Server calvinmagezi/mts-mcp A comprehensive suite of Model Context Protocol servers designed to extend AI agent Claude's capabilities with integrations for knowledge management, reasoning, advanced search, news access, and workspace tools. | |
| FL Studio Piano Roll MCP calvinw/fl-studio-mcp An MCP server that enables AI assistants like Claude to interact with FL Studio's piano roll, allowing users to create melodies, chord progressions, and musical patterns through natural language with automatic, real-time updates. | |
| LemonStudioMCP calvinw/lemonstudiomcp Lets MCP clients read and edit a Lemon Studio music project—tempo, notes, channels, patterns, clips, mixer tracks, effects, and plugin parameters—with batched edits that land as a single undo step, plus transport controls for play/pause/sto | |
| relative-interpreter-mcp calwtr/relative-interpreter-mcp An MCP server that enables LLMs to act as an interpreter for the Relative service, providing tools for navigating, reading, editing, executing, and managing models through natural language. | |
| Dark Stack SSH MCP Server caly1337/dark.lmphq.net Enables SSH-based remote access to dark.lmphq.net for executing commands, listing Docker containers, and reading files via the MCP protocol. | |
| HubSpot MCP Extended calypsocodex/hubspot-mcp-extended An independent MCP server built from HubSpot's OpenAPI specs, offering 106 tools for CRM automation including contacts, companies, deals, invoices, and line items. | |
| mcp-server-browser-use-ollama cam10001110101/mcp-server-browser-use-ollama Enables AI agents to automate web browsers using local Ollama models via the Model Context Protocol, supporting tasks like web search, data extraction, and e-commerce analysis through natural language commands. | |
| mcp-server-ollama-deep-researcher cam10001110101/mcp-server-ollama-deep-researcher This is a Model Context Protocol (MCP) server adaptation of LangChain Ollama Deep Researcher. It provides the deep research capabilities as MCP tools that can be used within the model context protocol ecosystem, allowing AI assistants to pe | |
| Email Processing MCP Server cam10001110101/mcp-server-outlook-email Processes emails from Outlook with date filtering, storing them in SQLite databases while generating vector embeddings for semantic search capabilities in MongoDB. | |
| JSON Canvas MCP Server cam10001110101/obsidian-jsoncanvas A Model Context Protocol server that enables creating, modifying, and validating infinite canvas data structures according to the JSON Canvas 1.0 specification. | |
| Remote MCP Server cam10001110101/remote-mcp-server A Cloudflare Workers-based implementation of the Model Context Protocol server with OAuth login, allowing Claude and other MCP clients to connect to remote tools. | |
| mcp-classroom cambar-solutions/mcp-classroom MCP server for Google Classroom enabling reading assignments, checking submission states, uploading files to Drive, and viewing attachments, with optional Playwright automation for write operations restricted by Workspace admins. | |
| kingdom-mcp cambridgetcg/kingdom-mcp Acts as the agent-side front door to the kingdom, providing tools to map services, check live status, detect FOMO, and access the agent marketplace, all through a single MCP connection. | |
| mcp-winnow cambrionic/winnow Enables agents to use many MCP servers without context bloat by exposing meta-tools (search, load, call, run_code) that reduce token usage via progressive disclosure and result trimming. | |
| trail-factors cambroussard9/trail-factors Enables Claude to answer trail and ultra running questions from a local DuckDB warehouse built from Garmin FIT files, with 29 parameterised tools that compute running-only pace by grade, matched-terrain heart rate drift, segment comparisons | |
| syn-search-mcp camcdonou/syn-search-mcp Enables MCP clients to perform web searches via Synthetic's Search API, with configurable result detail levels, AI summarization, and output truncation to manage context window. | |
| Anki MCP Server camdenclark/anki-mcp-server A TypeScript-based server that integrates with Anki via the AnkiConnect plugin, allowing you to manage flashcard decks, note models, and create Anki notes using natural language. | |
| jira-mcp camdenclark/jira-mcp Provides capabilities for searching Jira issues using JQL and retrieving detailed issue information. | |
| Camel-toolkits-mcp camel-ai/camel-toolkits-mcp A lightweight server that exports CAMEL framework toolkits as MCP-compatible tools. | |
| terminal-toolkit-mcp camel-ai/terminal-toolkit-mcp Enables LLM clients to execute shell commands safely through the MCP protocol, with features like session management, safe mode, and process control. | |
| ChatGPT WeChat MCP Events Bridge camellia041002/chatgpt-wechat-mcp-events-bridge Enables a dedicated WeChat account to route incoming messages as MCP events to ChatGPT Work automations, which can generate and send idempotent replies back to the original sender using signed webhooks and persisted pending queues. | |
| personal-ai-memory camellia041002/personal-ai-memory Provides AI-assisted long-term memory storage and retrieval with exact-phrase and semantic hybrid search, enabling save, read, delete, and admin recovery via MCP tools. | |
| CamelMailer MCP Server camelmailer/camelmailer-mcp Lets AI assistants send and inspect transactional email via the CamelMailer platform. | |
| is-it-agent-ready cameloo1/agent-friendly Provides agent-readiness audits of public websites via Cloudflare's scanner, enabling users to run scans, save reports, and enforce safety boundaries from natural language. | |
| aegea-drive-mcp camerhann/aegea-drive-mcp Enables management of Google Drive files, Docs, Sheets, and Slides through natural language using MCP, with support for file operations, search, and shared drives. |
36,551–36,600 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.