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 |
|---|---|
| Azure Database for PostgreSQL MCP Server danielvargasbm/azure-postgresql-mcp Enables AI applications to securely access and manage PostgreSQL data in Azure via MCP tools for querying, updating, and schema operations. | |
| Tophost DNS MCP danielvd/tophost-dns-mcp Enables AI agents to manage Tophost DNS records through MCP tools, including listing, creating, updating, and deleting records with safety guards, while delegating authentication and Tophost protocol handling to a separate REST API service. | |
| MCP-PostgreSQL-Ops danielveenstra21116/mcp-postgresql-ops Enables AI assistants to perform PostgreSQL database operations, monitoring, and management through natural language, including performance analysis, bloat detection, lock/deadlock monitoring, autovacuum and schema inspection, with no exten | |
| ClimaMX MCP danielvillasrc/climamx An MCP server that enables AI assistants to answer Mexico weather questions using official government data, resolving municipality names via INEGI and fetching forecasts from CONAGUA/SMN. | |
| big-mcp-b3 danielvm-git/big-mcp-b3 MCP server for B3 (Brazilian stock exchange) data, offering tools for real-time quotes, historical prices, dividends, FIIs, fundamental analysis, options, and indices via natural language. | |
| am-memory danielwanwx/am-memory Persistent memory for Claude Code — a self-evolving knowledge layer that survives across sessions, grows from every conversation, and surfaces relevant context automatically. | |
| Blender Open MCP danielwolf46/blender-open-mcp Enables AI agents to drive a live Blender session over MCP — inspecting scenes, creating and modifying objects, applying materials, rendering, and pulling PolyHaven assets — while routing natural-language prompts through a provider-agnostic | |
| Polybrain MCP Server danielwpz/polybrain-mcp Enables AI agents to connect to and chat with multiple LLM models (OpenAI, OpenRouter, custom endpoints) with conversation history management and model switching capabilities. | |
| lifeos danielyamanoglu/lifeos Enables MCP clients to search personal memory, add notes, and retrieve entities through a hybrid graph/vector knowledge engine with provenance for retrieved results. | |
| kiln danielyayla/kiln An MCP server that provides coding agents with fully-contextualized work orders from a knowledge graph, enabling them to retrieve and update work order status. | |
| MCP Interactive Service danielzhao1990/interaction-mcp An interface enabling high-frequency communication between AI tools (like Cursor and Windsurf) and users, allowing for option selection and information gathering through CLI, Web, or PyQt interfaces. | |
| mcp-server-telegram-notes danielzotti/mcp-server-telegram-notes Enables sending notes directly to your Telegram account using a Telegram bot. Provides a 'send-note' tool for programmatic note delivery via the Telegram messaging platform. | |
| mcp_dl danierli/mcp_dl A geographic tool service that exposes clustering, distance calculation, and directional sorting as MCP tools via SSE protocol. | |
| Civil 3D MCP Server danighosy/civil3d-mcp-civil3d-mcp Enables AI assistants to interact with Autodesk Civil 3D through natural language, supporting tools for surfaces, alignments, profiles, corridors, pipe networks, COGO points, and AutoCAD geometry. | |
| @memlane/mcp danii1/memlane-mcp Connects Memlane, your personal library of saved links and notes, to AI assistants via MCP. Enables semantic search, browsing, saving URLs, and managing notes and topics. | |
| Weather MCP Server danii2020/weather-mcp Provides real-time weather forecasts and alerts by fetching data from the National Weather Service API, allowing Claude to answer weather-related questions with up-to-date information. | |
| Antigravity MCP Bridge daniiislo/antigravity-mcp-bridge Enables Codex or Claude Code to orchestrate persistent Antigravity CLI workers as independent implementers and testers within restricted workspace roots. It supports asynchronous task dispatch, progress polling, result inspection, follow-up | |
| Cloudflare Workers MCP Server daniil-shumko/cloudflare-workers-mcp Enables managing Cloudflare Workers through Claude, with read-only tools for listing and viewing workers, and planned deployment of static sites and worker scripts via natural language. | |
| mnemex daniil-sokolskiy/mnemex An MCP server that ingests books into a structured, cross-linked wiki of sources, entities, concepts, and syntheses, managed by an LLM. | |
| pali-canon daniilki/pali-canon-claude Enables searching and reading Tipitaka texts with Pali alongside translations, comparing translators, exploring parallels, looking up Pali words, and retrieving Access to Insight pages with source citations. | |
| openai-image-mcp daniilpak/openai-image-mcp Enables MCP clients to generate images from text and edit or composite up to 16 input images with optional masks, choosing among several image models and quality/size/format options on each call. Generated results are saved to disk as file | |
| yt-audio-mcp daniilpak/yt-audio-mcp An MCP server that lets AI agents search YouTube and YouTube Music, download individual tracks as tagged MP3s with embedded cover art, and list previously downloaded files. | |
| mcp-odoo-jsonrpc daniilpet/mcp-odoo-jsonrpc MCP server for managing Odoo ERP tasks, timesheets, and wiki pages via JSON-RPC protocol. Supports restricted and full trust modes for secure AI assistant access. | |
| crousandgo-mcp daniilsys/crousandgo-mcp Enables an AI agent to list the 1 € Crous & Go student menus, ask which variant you want, and place and pay for the order through your own Izly account, with dry runs, a kill switch, a 1 € price cap, and explicit confirmation before any rea | |
| epitech-planning daniilsys/epiplan Enables an AI agent to read your my.epitech.eu planning — modules, events, seats, slots and existing bookings — and to register or unregister for activities with mandatory dry runs, guardrails and a write budget. Authenticates via your own | |
| @danijeun/fanar-mcp-server danijeun/fanar-mcp-server A Model Context Protocol server for Fanar API tools: Islamic RAG, image generation, and translation. | |
| paper_research-mcp danikim-blip/paper_research-mcp Enables searching PubMed papers by keyword and year range, retrieving abstracts by PMID, and summarizing/interpretation in Korean using Claude. | |
| dreamina-mcp danikvr/dreamina-seedance-mcp Enables Claude Code and Claude Desktop to drive Dreamina's Seedance 2.5 for batch video generation, including cinematic techniques, references, first/last frames, video-to-video edits, and automatic clip downloads via the SeedFlow Chrome ex | |
| OmniFlow MCP danikvr/omniflow-veo-mcp Enables Claude to drive Google Flow end-to-end: batch video generation on Veo 3 / Omni 1.1, scene chaining, keyframe transitions, video-to-video edits, and automatic downloads, all through a local bridge with the OmniFlow Chrome extension. | |
| symflow-mcp danikvr/symflow-mcp Enables Claude to operate TikTok Symphony Creative Studio through the SymFlow browser extension, including trend templates, video generation, avatars, try-on, video refresh, dubbing, and editor drafts using your own account and credits. | |
| ro-mcp danil0v3s/rathena-mcp Enables an agent to drive a real Ragnarok Online client session against a local rAthena server, allowing it to log in, walk, talk to NPCs, and fight in order to test server content end to end. | |
| chapel-support danilafe/chapel-support Enables AI assistants to work with Chapel code, including compiling, linting, and accessing educational primers. | |
| DNDzgz MCP Server danilat/mcp-dndzgz An MCP server that provides real-time information about the Zaragoza tram system, including arrival estimations and station details through the DNDzgz API. | |
| ArcLeap MCP danilaverbena/arcleap-mcp MCP server that lets AI agents bridge native USDC between networks (Ethereum, Base, Arbitrum, OP Mainnet, Polygon, Avalanche, and testnets) via Circle CCTP V2, featuring idempotent transfers, disk-persisted state, balance/gas checks, and co | |
| VMware_MCP_SERVER danilenka/vmware_mcp_server MCP server that provides AI agents with comprehensive access to VMware vSphere operations, including VM management, monitoring, and vSAN read-only monitoring, through a secure Docker environment. | |
| Codex Free Worker danilfaritovich/codex-free-worker-mcp Enables delegating bounded execution loops—such as failing test suites, large CI logs, build/diagnose/fix/rerun cycles, and routine repo exploration—to OpenCode, which inspects and iterates on the raw output internally. Returns only a compa | |
| chrome-remote-debugging-mcp danilin-em/chrome-remote-debugging-mcp Controls a running Chrome/Chromium browser via the Chrome DevTools Protocol, enabling navigation, JavaScript evaluation, tab management, and raw CDP commands through MCP tools. | |
| opensearch-dashboard-mcp danilin-em/opensearch-dashboard-mcp Enables LLM clients to interact with OpenSearch Dashboards, including reading saved objects, listing tenants and index patterns, and querying logs through the Dashboards API. | |
| figpilot danilkotelnikov/figpilot Enables users to list templates, create and build structure-biology figures, render protein structures, and run QA and palette checks through seven tools backed by structfig. | |
| zont-mcp danilmolkov/zont-mcp Enables MCP clients such as Claude to read the state of ZONT / Mega SX devices and control them, covering security arming, sirens, engine blocking, remote start, thermostats, custom commands, device management, event and sensor history, and | |
| quick-game danilo-1/quick-game-mcp Enables an MCP client to guide users through 12 stages of game creation, from concept to launch, by managing decisions, recommending skills, and generating playable HTML5 prototypes, GDDs, and backlogs. | |
| FastMCP Documentation Search Server daniloblancomotta/ai-dev-tools-zoomcamp-mcp Enables intelligent search through FastMCP documentation using TF-IDF indexing, along with utility tools for arithmetic operations, text hashing, and web page content extraction via Jina Reader. | |
| publish-linkedin danilobrando/publish-linkedin Enables publishing to LinkedIn from a Second Brain using four tools and the official API, with a handbrake that requires confirmation before posting and supports deleting posts. | |
| atlasbrain danilofacco/atlasbrain Turns a local project folder into a searchable second brain that indexes code symbols, dependencies, notes, PDFs and web snapshots, then exposes hybrid keyword and embedding search, graph traversal, impact analysis and architecture reports | |
| GLM Vision Server danilofalcao/mcp-server-glm-vision Enables image analysis using GLM-4.5V's vision capabilities from Z.AI. Supports analyzing both local image files and URLs with customizable prompts and parameters. | |
| Pair daniloko365/pair-mcp Enables users to delegate coding tasks in a chosen project to the official Codex and Claude CLI agents from within an existing chat, then convene a council of configured models to gather independent opinions and review the resulting files a | |
| localhost danilolekovic/localhost Enables MCP-capable coding agents to discover local development servers, inspect them by port or PID, and safely terminate verified listeners with confirmation and fresh discovery before signaling. | |
| n8n Workflow Builder danilonovaisv/n8n-workflow-builder-gpt Enables AI assistants to manage n8n automation workflows through natural language commands, including creating, executing, monitoring, and organizing workflows with full CRUD operations and execution management. | |
| chess-support-mcp danilop/chess-support-mcp Manages the state of a chess game for LLMs/agents without suggesting moves, providing tools to create/reset game, add moves, get status, and check legality. | |
| kiro-total-recall danilop/kiro-total-recall Enables semantic search across all Kiro conversations (CLI and IDE), allowing the AI to recall past discussions, decisions, and user preferences. |
42,101–42,150 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.