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 |
|---|---|
| German Real Estate MCP Server benthepythondev00/german-realestate-mcp Enables AI agents to search for German property listings (rent/buy) on immowelt.de with structured JSON output, no API key required. | |
| ClickUp MCP Server benthesoundguy/clickup-mcp-server A Model Context Protocol (MCP) server providing AI assistants with comprehensive ClickUp integration, covering the full API surface across 87 consolidated tools. | |
| benthic-mcp benthic-io/benthic-mcp Enables agents to ask plain-language questions of signed Benthic Data Provenance datasets through discovery, bounded single-relation queries, multi-relation joins restricted to signed join paths, and allowlisted spatial RPCs, while serving | |
| expert-mcp-server benthomasson/expert-mcp-server Enables MCP-compatible agents to query beliefs, search documents, and explore reasoning chains from expert-service knowledge bases. | |
| siftr bentlybro/siftr Enables AI coding agents to quickly find relevant code, focus reads on important parts of large files, and pick relevant items from long lists, reducing token usage and search time. | |
| MCP Polygon Renderer bentlyy/mcp-polygon-renderer Enables AI agents to overlay labeled grids, define image regions by grid cells or pixel coordinates, and render polygons or automatically detected regions using OpenCV, returning images for visualization. | |
| Google Tasks MCP Server bentohmeal/google-tasks-mcp Enables reading and writing Google Tasks checklist items through the Google Tasks API, including listing task lists and tasks, and creating, updating, completing, or deleting tasks. | |
| Tatami MCP Server bentonow/tatami-mcp-server Tatami MCP server enables querying email delivery events, bounce/deferral reasons, and deliverability report sections via the Tatami API, with optional team/project headers. | |
| Shopify MCP benwmerritt/shopify-mcp A Model Context Protocol server that connects AI agents to the Shopify Admin GraphQL API, enabling management of products, orders, customers, and more through natural language. | |
| uxship benxsha/uxship Enables AI agents to write AI-generated designs into design-tool canvases (MasterGo, Penpot) as native editable layers, and to read canvas selections back out as HTML + Tailwind, design tokens, and SVG assets. Runs locally with progressive | |
| Kira benyalgx/kira Automatically provides AI agents with proven instructions and past failure warnings for common tasks like deployment, auth, and payments, enabling flawless execution without manual configuration. | |
| mesa-mcp benyfridy/tercet Enables agents to query a read-only ledger of machine payments, exposing tools for spending totals, purchases with event chains, verdicts, payer passports, and fiscal reporting data. | |
| zebra-printer-mcp benyshen/zebra-printer-mcp Enables AI clients to build and validate ZPL II label specifications from JSON (text, 27 barcode symbologies, boxes, CJK via built-in TrueType fonts), send them over TCP raw 9100 or Windows spooler/USB, query printer status via Link-OS SGD | |
| SoloFlow MCP Server benyue1978/solo-flow-mcp A Model Context Protocol (MCP) server for project document management with 32 comprehensive prompts covering the complete software development lifecycle. | |
| sublime_mcp_server benyue1978/sublime-mcp An MCP server that exposes Sublime Text's unsaved buffers as tools via local HTTP, enabling AI clients to read, list, and close buffers without saving to disk. | |
| tradex benz16107/tradex Enables agents to discover and pay for AI services per call via USDC on Solana, supporting marketplace search, listing details, on-chain reputation, wallet info, and paid calls. | |
| Crossplane Compass benzaidfoued/crossplane-mcp Enables AI assistants to diagnose Crossplane control planes, discover resources and schemas, assess adoption and migration safety, and propose GitOps changes using evidence from actual cluster APIs. | |
| Velero MCP Server benzaidfoued/velero-mcp Provides read-only access to Velero backup and schedule resources in Kubernetes clusters, enabling AI agents to inspect backups, schedules, and generate Velero YAML manifests safely without write permissions. | |
| gymtracker benzalglez/gymtracker-plugin Universal MCP server for Gymtracker that enables AI coding agents to read and write training data. | |
| wechat benzema216/wechat-archive-harness Enables DeepSeek Harness to run bounded archive operations—diagnose, status, sync, and verify—against a local macOS chat database with integrity and privacy protections. | |
| BENZEMA's Personal Knowledge Card benzema216/wiki-mcp-server This MCP server provides LLMs with a live, curated knowledge base of AI agent research, world models, and source-code reviews, enabling personalized and context-aware responses. Users can either connect to the hosted knowledge or build and | |
| redpen benzenp/redpen Enables coding agents to capture pixel-accurate screenshots and DOM state from localhost apps, receive user-drawn instructions and reference images, and manage implementation review cycles. | |
| weather-mcp benziela/weather-mcp Provides real-time weather data and alerts from the National Weather Service API, including forecasts for US locations and active alerts for US states. | |
| inline-claude benzin8/inline-claude-public Allows invoking Claude in Telegram chats via inline mentions or business bot, with context from chat history and media transcription. | |
| MultiMind MCP Server benzinamohamed/multimind-mcp-server A structured tool that enables multiple AI agents to simulate reflective debate, where LLMs critique and refine each other's ideas to produce higher-quality solutions. | |
| codex-async-mcp benzkittisak/claude-codex-mcp Local MCP server that wraps the codex CLI asynchronously, returning a job_id immediately to avoid MCP protocol timeouts, and providing tools to start, poll, list, and cancel codex jobs. | |
| mcp-thread-persistence-demo benzytai/mcp-thread-persistence-demo Enables persisting chat-thread notes to SQLite with upsert semantics, allowing creation, update, retrieval, and listing of per-user threads via MCP tools. | |
| dssat-mcp beomseokforwork/dssat-mcp Enables natural language interaction with the DSSAT crop model for simulation, calibration, and sensitivity analysis through LLM agents. | |
| hwpConverMdMCP beomzh/hwpconvermdmcp An MCP server that enables LLMs to convert HWP and HWPX documents into Markdown for analysis and processing. It supports document conversion via local file paths or Base64 content across various MCP-compatible clients. | |
| Cloudflare Playwright MCP beparykamrul-dev/playwright-mcp-example Enables AI assistants to control a browser through Playwright on Cloudflare Workers, allowing web automation tasks like navigation, typing, clicking, and taking screenshots through natural language commands. | |
| obsidian-vault-mcp bepitulaz/obsidian-multivault-mcp An MCP server that enables Claude Desktop to read and write an Obsidian vault hosted on a VPS, using SSH or HTTP transport with OAuth authentication. | |
| Local Financial MCP Mock Server beprith/finance-personal-assistant A lightweight MCP server that simulates financial data interactions with dummy authentication and static JSON datasets for testing financial applications. | |
| Bequall MCP Server bequall/bequall-mcp-server Enables AI assistants to provide information about Bequall's services for real estate, construction, and modular development, including company overview, use cases, and fit assessment. | |
| Binance TypeScript MCP ber4444/typescript-mcp Provides a tool to fetch real-time cryptocurrency prices from the Binance API and logs server activity to file resources. It allows users to query crypto symbols and monitor MCP interactions through natural language interfaces. | |
| scratchbrief-ind-mcp beral-lab/scratchbrief-ind-mcp Enables searching IndiaKanoon's live index of Indian case law, legislation, the Constitution, treaties, and parliamentary material, then retrieving full document text with pagination and excerpt targeting. Also traces precedent chains by li | |
| metalsmarket-bot beratemek/metalsmarket-bot Enables LLM clients to query live and historical metal and commodity prices from metalsmarket.net through an MCP server. | |
| berbotu-mcp berbotu/berbotu-mcp MCP server for the Berbotu vault, providing tools to ping health, list demos and releases, and add new demos via GitHub commits over stdio. | |
| Kopern berch-t/kopern Full AI agent lifecycle platform — create, grade, optimize, deploy and orchestrate AI agents from your IDE or terminal. | |
| calagopus-mcp berdiinn/calagopus-mcp Enables querying and managing a Calagopus game server panel via natural language, covering users, servers, nodes, eggs, databases, backups, and system health. Write operations are opt-in and require explicit confirmation. | |
| MCP Learning Project berdtan/mcpharness A comprehensive learning platform for Model Context Protocol development that teaches MCP concepts through hands-on modules including text processing, file operations, and database integration. Designed as an educational tool with progressi | |
| LmsPs berejikb/lmsps Enables interaction with a persistent PowerShell session through LM Studio. Provides tools to run commands, manage directories, and handle environment variables while maintaining session state between calls. | |
| mcp-skillbox beremaran/mcp-skillbox An MCP server that aggregates agent skills from skills.sh and GitHub repositories, exposing list_skills, search_skills, and load_skill tools for context-efficient skill discovery and on-demand loading. | |
| Flameox berg52444/flameox Enables coding agents to collect bounded local runtime evidence by coordinating profilers, benchmark tools, trace processors, and direct targets, then inspect and preserve artifacts for tracing, profiling, and hotspot analysis. | |
| StarRocks MCP Server berger3434/mcp-server-starrocks Enables AI assistants to interact with StarRocks databases by executing read/write SQL, exploring schemas and tables, retrieving overviews, and generating Plotly charts. | |
| IB MCP Server berger4581/ib_mcp Enables access to Interactive Brokers' official Web API through MCP clients for account management, market data, and trading operations, using Client Portal Gateway authentication. | |
| MCP-Discord berger52247/mcp-discord Enables AI assistants to interact with Discord servers, channels, roles, members, messages, reactions, forum posts, and webhooks. | |
| Bitbucket MCP berger72541/bitbucket-mcp Enables AI assistants to access and manage Bitbucket repositories and pull requests, including listing repositories, fetching repository details, and viewing or creating pull requests. | |
| photo-organizer berhannnnd/photo-organizer Enables agents to scan and search local photo libraries, maintain persistent selections across turns, preview grouping and export plans, and create albums or copy/compress photos while keeping originals in place. | |
| native-agent-router berineyang/native-agent-router Enables orchestrator agents to route coding tasks to native CLI worker agents via MCP, providing tools for agent discovery, task submission, waiting, inspection, and cancellation. | |
| MCP-Kali-Server berixoo/mcp-kali-server Bridges Claude Code to a Kali Linux VM via MCP, enabling execution of security tools like nmap, metasploit, and arbitrary commands. |
33,701–33,750 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.