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 |
|---|---|
| freellmpool dangandersson0068/freellmpool Enables MCP clients to send chat completions through one OpenAI-compatible endpoint that pools 178 enabled routes across 23 free-tier and keyless LLM providers, with automatic failover, per-day usage tracking, and keyless start when an enab | |
| zotero-mcp dangandersson0068/zotero-mcp Enables AI assistants and MCP clients to search a Zotero library, retrieve item metadata, and fetch full text from stored documents via the local desktop or Zotero Web API. | |
| Snippy dangaydin647/snippy Enables AI assistants to save, retrieve, and semantically search code snippets, generate language-specific style guides and comprehensive wiki documentation, and orchestrate multi-agent workflows through discoverable MCP tools. | |
| Fantasy World MCP Simulator dangerblack/fantasy-world-mcp Generates and evolves fantasy worlds procedurally, simulating centuries of history, geography, and culture from a simple starting event. | |
| mellos-mapping danggarcia9837/mellos-mapping Enables an MCP client to declare a layering-first design as ghost nodes and then track it as code lands: nodes show a spinner while under construction and turn solid green only once verified, with dependency edges constrained to point downw | |
| Agentdocs dangishii50738/python-mcp-server-client Enables AI models and MCP clients to search for and fetch the latest technical documentation from eight popular agent frameworks (including LangChain, LlamaIndex, AutoGen, Agno, OpenAI Agents SDK, Camel-AI, and Crew-AI) via domain-restricte | |
| IP-API MCP Server dangkoolwat/ip-api Enables looking up approximate location of public or specific IP addresses, returning country, city, ISP, and coordinates via ip-api.com. | |
| Open Library Subjects MCP Server dangkoolwat/openlibrarysubject Fetches books by genre or subject from the Open Library API without requiring an API key, returning titles, authors, and publication years. | |
| backlog-mcp danglephuc/backlog-mcp Syncs Backlog issues to local markdown files for management within MCP-compatible editors like Cursor or Claude Desktop. | |
| Redmine MCP Server danglephuc/redmine-mcp-server A read-only MCP server for querying Redmine issue data via the Redmine REST API, designed for seamless integration with AI assistants. | |
| Weather MCP Server dangogh/weather-mcp Provides current weather conditions and 5-day forecasts for any location using the OpenWeatherMap API. Supports flexible location queries including city names, coordinates, and zip codes. | |
| jetson-llm-mcp dangraf/jetson-llm-mcp An MCP server that exposes local LLMs running on a Jetson AGX Xavier to Claude Code, enabling Claude to ask questions and check the status of those models. | |
| LunchMoney MCP Server dangraza82523/lunchmoney-mcp Enables AI assistants and other MCP clients to read and manage personal finance data through LunchMoney's API, covering transactions, categories, tags, budgets, recurring items, accounts, crypto, and balance history. Delivers token-efficien | |
| MCP OCR Server dangvinh/mcp-ocr-server High-performance OCR server using native Tesseract (C++) for text extraction from images, integrable with ChatGPT Desktop and other MCP clients. | |
| GitLab MCP Server dangvusontung/mcp-ts Integrates AI assistants with GitLab API to manage projects, issues, merge requests, files, and more through MCP tools and resources. | |
| Project Context Reader dangzitou/codex-context-reader Enables ChatGPT to inspect a selected local project on demand, retrieving project overviews, code search results, file excerpts, and Git context without pasting entire repositories into the conversation. | |
| Transport NSW API Client MCP danhussey/transportnsw-mcp An MCP service for interacting with Transport NSW's API that enables users to find transport stops around locations and retrieve information about transport alerts and disruptions. | |
| recruiter-lens dani-aisystems/recruiter-lens Audits GitHub repos and profiles for hiring signal, providing tools audit_repo and recruiter_scan for use with MCP clients. | |
| MCP Chat dani-tc/anthropic-mcp-chat Enables interactive command-line chat with AI models via the Anthropic API, supporting document retrieval with @mentions and slash-command prompts with tab auto-completion. | |
| mac-mcp daniakash/mac-mcp A read-only MCP server that exposes data from native macOS apps (Mail, Notes, Calendar, Reminders, Contacts, Messages, Spotlight) to AI agents over stdio, currently in early development with no domain tools wired yet. | |
| WhatsApp MCP Server danialadzhar/mcp-whatsapp-claude-desktop Gives Claude Desktop read-only access to your WhatsApp chats and message history via a local MCP server. | |
| Job Board MCP Server danialesss/job-board-mcp Enables searching and retrieving job listings from multiple platforms through MCP. | |
| passClaude daniardel/nopeeking Lets Claude Code log into websites and use API keys and passwords stored in Windows Credential Manager without the values ever appearing in the chat, transcripts, or model. Secrets are entered once via a PC popup or an encrypted one-time ph | |
| Remote MCP Server danibedz/remote-mcp-server A deployable Model Context Protocol server on Cloudflare Workers that enables AI tools integration without authentication requirements. | |
| mcp-weather danibencz/mcp-weather A minimal MCP server that provides current weather and forecasts for any city using the free Open-Meteo API, no API key required. | |
| laravel-forge-mcp danie1net0/laravel-forge-mcp Manages Laravel Forge servers, sites, deployments, SSL certificates, databases, and more through the Model Context Protocol. | |
| Dependency-Track MCP Server daniel-brenner-fnt/dependency-track-mcp-server Enables querying projects, fetching findings, triggering analysis, uploading CycloneDX BOMs, and checking async token status for OWASP Dependency-Track. | |
| Diorama daniel-ddtech/diorama MCP server for recording and validating Chrome extension demo videos from YAML beat sheets, enabling agents to script and generate pixel-perfect videos. | |
| Unreal Engine Assistant MCP daniel-eder/unreal-engine-assistant-mcp Connects to Epic's Unreal AI Assistant to provide accurate, up-to-date documentation, C++ code snippets, and Blueprint guidance through the Model Context Protocol. | |
| AWS Documentation MCP Server daniel-levesque/aws-documentation-mcp-server Provides tools to access AWS documentation, search for content, and get recommendations for both global and China AWS regions. | |
| mcp-perplexity daniel-lxs/mcp-perplexity MCP Server for the Perplexity API. | |
| maestro daniel-madrid-07/maestro Enables Claude Code to launch and supervise multiple concurrent Claude Code sessions in tmux, sending them briefs, reading their progress, answering their prompts, and managing isolated git worktrees. | |
| servidor-mcp daniel-riv/servidor-mcp Enables AI clients to operate Linux servers over SSH through user-opened, time-limited sessions without exposing passwords, providing tools for system status, logs, file reads/writes, and shell command execution with read-only and blocked-c | |
| BlackBook MCP daniel-wambua/blackbook A source-grounded cybersecurity knowledge & research MCP server that provides read-only search, exact citations, and a knowledge graph, designed to run alongside execution MCPs. | |
| TrainerML daniel-was-taken/mcp_project Advanced machine learning platform with MCP integration that enables automated ML workflows from data analysis to model deployment, featuring smart preprocessing, 15+ ML algorithms, and interactive visualizations. | |
| netbird-mcp daniel100097/netbird-mcp Enables managing NetBird network resources through the NetBird REST API, exposing tools for peers, groups, policies, routes, DNS, users, and related operations via MCP. | |
| t3code-mcp daniel100097/t3code-mcp Lets coding agents create and manage threads in a running T3 Code server over MCP. | |
| mcp-human-approval-gate daniel221287/mcp-human-approval-gate Enables an AI agent to prepare an action, have a human approve the exact preview via a local token-protected page, and then execute it once with no replay. Provides read-only status, revocation, expiry, and verified readback so uncertain or | |
| TasteBridge daniel221287/tastebridge-qloo Enables AI agents to find movies, shows, books, music, podcasts, games, places, destinations, or brands that two people are likely to enjoy together. It resolves favorites to Qloo entities, compares taste profiles, ranks candidates for fair | |
| Equibles daniel3303/equibles Self-hosted financial data terminal for AI agents. Scrapes and serves SEC filings (full-text search), 13F institutional holdings, insider and congressional trades, FINRA short data, FRED economic indicators, CFTC futures positioning, VIX/pu | |
| MCP Manager daniel3303/mcpmanager Self-hosted MCP proxy and aggregation platform. Register multiple upstream MCP servers and expose them through a single unified endpoint with namespace routing, multi-transport support (HTTP/SSE, stdio, OpenAPI→MCP), per-tool overrides, and | |
| WorkFlowy MCP Server daniel347x/workflowy-mcp-fixed Integrates WorkFlowy's outline and task management capabilities with LLM applications, enabling hierarchical node creation, updates, completion tracking, and navigation through WorkFlowy's API. | |
| NEXUS daniel347x/workflowy-nexus Enables MCP-capable agents to read, file, slice, and map a shared Workflowy outline, giving them the same live context a human sees—including source code mapped from disk—without exports or copies. | |
| Visual MCP daniel69zz/visual_draw_mcp A Model Context Protocol server that gives an LLM a structured visual layer to describe what exists and get back a clean, precise SVG diagram instead of ASCII art. | |
| Typst MCP Server daniel7108/typst-mcp Enables AI models to work with the Typst typesetting system by converting LaTeX, validating syntax, retrieving documentation, and generating images from code. | |
| MCP REST API Tester daniel86394/mcp-rest-api Enables testing and interacting with any REST API endpoint directly from MCP clients like Claude and Cline. Supports GET, POST, PUT, DELETE, and PATCH requests with configurable authentication (Basic, Bearer, API Key), custom headers, SSL v | |
| Forest Fire Visualization MCP Server daniel8824-del/forest-fire-mcp A Python-based MCP server that collects, analyzes, and visualizes forest fire occurrence data on maps, allowing users to access regional fire information, risk analysis, and map visualizations. | |
| Joplin MCP Server daniel9683/joplin-mcp Enables AI assistants to interact with Joplin notes, notebooks, and tags through a standardized interface, with tools for searching, creating, updating, deleting, organizing, importing, and restoring content. | |
| korean-dart-mcp daniela67478/korean-dart-mcp Enables users to query OpenDART disclosure, financial, ownership, and XBRL data through 15 AI-assistant tools, including insider-signal clustering, accounting-risk scoring, Buffett-style quality checks, and HWP/PDF attachment conversion to | |
| Sub-Agents MCP Server daniela7119/sub-agents-mcp Enables Markdown-defined, task-specific coding agents to be run from any MCP-compatible client, delegating work such as code review, test writing, investigation, and documentation to a chosen coding CLI and returning results to the same con |
41,901–41,950 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.