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 |
|---|---|
| blender-server-mcp-docker battlehawk00/blender-server-mcp-docker Enables remote control of Blender through MCP, allowing code execution, scene manipulation, rendering, and file transfer in a containerized environment. | |
| Ghidra MCP server for Cline battlepriestbarbara/ghidra-mcp-tool Enables AI assistants to import binaries into Ghidra, trigger analysis, browse functions, symbols, strings, and imports, and read decompiled C code and disassembly via MCP tools. | |
| Microservice Control Panel (MCP) battyht/ad_mcp A platform that integrates and manages APIs from ByteDance's Ocean Engine (巨量引擎) advertising platform, providing unified access interfaces for e-commerce traffic acquisition scenarios. | |
| InfraClaude batu-sonmez/infraclaude An MCP server that enables Claude to manage infrastructure across Kubernetes, Docker, Prometheus, and Terraform through natural language. It provides over 42 specialized tools with a safety-first design, including risk-based command classif | |
| mcp-sql-server batuhansutculer/mcp-sql-server An MCP server that lets Claude query a mock business SQL database in plain language through read-only tools, with server-side guardrails that enforce SELECT-only queries and block access to sensitive payment data. | |
| Frontend Bug Investigator MCP batyrkhan-sk/tracekit-mcp Enables AI clients to reproduce reported UI issues in an isolated, policy-restricted browser context, gather sanitized evidence, distinguish observed facts from candidate causes, and produce structured reports plus reviewable Playwright reg | |
| math-rigor bauerelizabeth07139/math-rigor Enables rigorous, auditable mathematical proving with machine-checked steps, honestly distinguishing proven, refuted, and inconclusive results while disclosing unverified gaps. | |
| mcp-simple-image bauerelizabeth07139/mcp-simple-image Generate images from text prompts using StepFun-compatible APIs. Configurable endpoint, API key, and model with zero external dependencies. | |
| opencode-eyes bauerelizabeth07139/opencode-eyes MCP server that provides image description capability using StepFun Step-3.7-flash multimodal model, enabling models to 'see' images by converting them into detailed text descriptions. | |
| opencode-eyes-nvidia bauerelizabeth07139/opencode-eyes-nvidia MCP server that gives non-multimodal models 'eyes' by describing images via NVIDIA NIM's MiniMax-M3 model, with tools to describe images and list available vision models. It supports multiple NVIDIA API keys with automatic failover and rota | |
| contextshrinker bauhaus28/contextshrinker Zero-dependency Go MCP server that indexes codebases into an embedded Kùzu graph DB—enabling 90%+ token reduction, precise call-chain queries, and AI architectural health audits. | |
| optiq-mcp baukaalm/optiq MCP server (stdio, TypeScript) for optimising the images in a project with verified quality. Tools: analyze_images (read-only dry run) and optimize_images (in place or to a folder). Source: mcp/ in this repository; npm: optiq-mcp; MCP Regis | |
| aseprite_mcp bauneaustin/aseprite_mcp Enables AI sprite generation and semantic tools for Aseprite, allowing LLMs to create pixel art, add animations, and manage projects with visual feedback. | |
| Bauplan MCP Server bauplanlabs/bauplan-mcp-server Enables AI assistants to interact with Bauplan lakehouse operations, including querying tables, schema inspection, branch management, and pipeline execution. | |
| Alibaba Cloud Token Plan Proxy for Claude Code bautimartinez-kumi/alibaba-token-plan-to-claude-code Enables Claude Code to use Alibaba Cloud Token Plan models via a local proxy that maps Anthropic-style model names to Alibaba IDs and provides missing endpoints like model discovery. | |
| UTN FRM MCP bautistaalosmartorell/utnfrm-mcp Connects MCP-compatible AI clients to a university Moodle campus locally so users can query courses, assignments, materials, grades, forums, and calendar events, including reading attachments and PDFs. It is a read-only beta that does not m | |
| CollabMCP bautistapessagno/collab-mcp Provides shared real-time context for Claude Code agents, including scope awareness, prior decisions, and anti-overlap, using only files in the repo. | |
| Bavimail MCP Server bavlio/bavimail-mcp-server No longer maintained. Use the Bavimail REST API or SDKs: bavimail.com/docs/quickstart | |
| light-mcp-server bawaaaaah/light-mcp-server Enables AI-driven control of Art-Net/sACN DMX lighting, including scenes, effects, groups, safety rules, MIDI/OSC, and Ableton Live integration through a unified command layer. | |
| wing-mcp-server bawaaaaah/wing-mcp-server Enables control of a Behringer WING digital mixing console through MCP clients, exposing 116 typed tools for mixing, processing, automation, presets, scenes, and other console features, along with a web dashboard. | |
| StudentHub MCP bawes-universe/studenthub-mcp Read-only MCP server for the StudentHub recruitment database. Enables BAWES agents to search candidates, retrieve profiles, and query hiring pipeline data, with strict SELECT-only safety guarantees. | |
| Universe Imagine MCP bawes-universe/universe-imagine-mcp Enables AI image generation from text prompts by wrapping local ComfyUI as a Streamable HTTP MCP server, supporting synchronous generation, queue management, and history tracking. | |
| Imagine Music MCP bawes/universe-imagine-music-mcp Generates music from text prompts via a local ACE Step API, providing tools for music generation, result checking, and listing generations. | |
| 1TA MCP Server bawzenit-glitch/1ta-mcp Enables querying Chilean Primer Tribunal Ambiental court cases, case files, daily status updates, and documents through natural language, with tools for searching causes, viewing case details, accessing expedientes, reading PDF documents, a | |
| infotecnica-mcp bawzenit-glitch/infotecnica-mcp Provides access to as-built technical data of Chile's National Electric System (SEN) equipment, enabling query of installation types, companies, and detailed technical sheets with certification status via public API. | |
| SNIFA MCP Server bawzenit-glitch/snifa-mcp Connects Claude to public environmental enforcement data from Chile's Superintendencia del Medio Ambiente (SNIFA), enabling search and retrieval of sanctions, inspections, measures, and registrable units filtered by category, region, and en | |
| tc-mcp bawzenit-glitch/tc-mcp Enables querying Chilean Constitutional Court cases and jurisprudence, including full-text search and detailed records. | |
| Tribunal Ambiental MCP Server bawzenit-glitch/tribunal-ambiental-mcp Enables searching and reviewing public case information from the Second Environmental Tribunal of Santiago, including case details, motions, and court documents, through natural language. | |
| Coverity MCP Server baxishrey/coverity-mcp-server-typescript A TypeScript MCP server that connects AI agents to Black Duck Coverity Connect for static analysis defect management, enabling browsing projects, streams, and defects with event traces. | |
| mcp-lnav-canbus baxtheman/mcp-lnav-canbus A Model Context Protocol (MCP) server that exposes lnav log file analysis capabilities to AI assistants, specifically optimized for Kvaser Plain Text Log Frame CAN bus log processing. | |
| Dida365 MCP Server bayinl/dida-mcp Enables AI assistants to directly manage Dida365 (TickTick) tasks, including creating, editing, completing, and setting priorities, deadlines, subtasks, reminders, and recurring tasks via natural language. | |
| hostproto-dap-core bayleafwalker/hostproto-dap-core Enables any debugger to become a HostProto host by supplying an EngineBinding, exposing revision-scoped debugging semantics through an MCP surface. It computes targets, preconditions, receipts, recovery, and earned capabilities without requ | |
| hostproto-dap-debugpy bayleafwalker/hostproto-dap-debugpy Enables launching and controlling a debugpy debug session through MCP, including setting breakpoints, stepping, evaluating expressions, and observing debugger state and events. | |
| hostproto-dap-delve bayleafwalker/hostproto-dap-delve Enables MCP clients to launch and control a Delve DAP session for debugging Go programs, including breakpoints, goroutine inspection, and variable manipulation. | |
| Load Planner MCP bayraak/load-planner-mcp Enables optimal freight-mode selection (air, sea-LCL, full container) by solving 3D bin-packing, cost optimization, and delivery-risk analysis behind two tools: solve for deterministic planning and explain for hallucination-proof natural-la | |
| webshare-proxy-mcp bayramlcm/webshare-proxy-mcp Enables HTTP requests to be routed through Webshare proxies with exit-IP verification, proxy rotation, and strict no-fallback fetching, plus generation of permission-restricted proxy environment files. | |
| ffmpeg-skill bayshier/ffmpeg-skill-zh Gives coding agents a local FFmpeg video-editing engine exposed over MCP, enabling them to probe, cut, join, reframe, caption, normalize audio, and verify the resulting media without cloud services or API keys. Every operation returns struc | |
| godspeed bayshores/godspeed Desktop study app with a local MCP server. Point Claude Code, Codex or any other MCP agent at it and the agent tutors you from your class files, with your past lessons, answers and confidence ratings saved between sessions. | |
| applyfit bayuh85/applyfit Enables scoring job postings offline, tailoring a CV, drafting cover letters, and generating interview prep sheets stored as plain files in a shared workspace. Also supports adding postings from files or URLs, listing applications, setting | |
| ctxtrim bayuh85/ctxtrim Enables coding agents to shrink bulky tool output, logs, test runs, and file dumps down to compact briefs, and to record and recall decisions in a small session ledger. This keeps long-running tasks within context limits while preserving er | |
| Graphloom MCP Server bayuh85/graphloom Enables coding agents to query an offline repository knowledge graph through MCP tools, including term lookup, shortest paths, node explanations, and cited LLM answers with file:line evidence. | |
| skimsearch bayuh85/skimsearch Enables coding agents to search a locally indexed repository and get back a token-budgeted deck of ranked code and doc snippets instead of a full-tree grep dump, with lexical, semantic, and prose-answering modes plus index status reporting. | |
| VeniAI-Hukuk-EmsalKarar-MCPServer bayyyyyuuu/veniai-hukuk-emsalkarar-mcpserver An AI-powered legal research tool that enables users to search for and retrieve legal precedents and case law decisions through a Model Context Protocol server. It supports both Turkish and English, providing lawyers and researchers with st | |
| bazhuayu-mcp bazhuayu-team/bazhuayu-mcp Converts natural language collection requests into cloud scraping tasks by searching templates, validating parameters, executing tasks, and exporting structured data. | |
| MCP VKUSVILL bazilio-san/mcp-vkusvill MCP server for integrating AI assistants with VkusVill services, allowing natural language access to VkusVill data and operations. | |
| MCP Code Executor bazinga012/mcp_code_executor Allows LLMs to execute Python code in a specified Conda environment, enabling access to necessary libraries and dependencies for efficient code execution. | |
| exercise-mcp bazni/gym-mcp MCP server providing access to 1,324 exercises in 10 languages with animation GIFs, offering tools to list facets, search exercises, get exercise details, and build workouts. | |
| CommandCore bazobehram/commandcore Enables AI/MCP clients to enumerate, select, and operate authorized remote computers through one OAuth-protected, self-hosted endpoint, with devices connecting outbound and keeping their own cryptographic identities. It layers OAuth scopes, | |
| Desktop Commander MCP bazovyy/desktopcommander-windowscontrol Enables AI clients to capture Windows screens via DXGI with GDI fallback, control mouse and keyboard input, focus and manage windows, handle multi-monitor coordinates, and schedule patched Remote startup with Windows reliability fixes. | |
| webots-mcp bazucas/webots_mcp An MCP server that gives AI agents full control and observability of the Webots robot simulator, enabling launch and monitoring of simulations, reinforcement learning training, model evaluation, and interactive scene manipulation. |
33,201–33,250 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.