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 |
|---|---|
| orbit-mcp akira69/orbit-mcp Enables MCP clients on Windows and macOS to query and index a Linux development server's local GitLab Orbit code graph over SSH, including repository listing, search, context retrieval, indexing, and status checks. | |
| AKIMCP akirachaudhry31897/aki-mcp-sv Enables web-based AI clients such as Claude, ChatGPT, Grok, and Postman to securely operate a local machine through a single OAuth-gated MCP endpoint exposing 38 governed tools. Covers file read/write/edit, whitelisted shell commands, searc | |
| EasyMCP akirahunt/easy-mcp Enables developers to build Model Context Protocol servers in TypeScript with minimal boilerplate, declaring tools, prompts, resources, and resource templates through either an Express-like API or experimental decorators. Arguments, input s | |
| MiniMax MCP JS akirahunt/minimax-mcp-js Enables MCP-compatible clients to generate images and videos, synthesize speech, clone voices, and design custom voices through the provider's APIs. | |
| nix-playwright-mcp akirak/nix-playwright-mcp A Nix-wrapped version of the Playwright MCP server with Chromium from Nixpkgs, enabling browser automation on NixOS. | |
| Unity Build Automation MCP akirakido/unity-build-automation-mcp Enables checking build status, starting/canceling builds, and managing Unity Cloud Build targets directly from Claude Code. | |
| MCP Python Interpreter akiraking50150/mcp-python-interpreter Enables LLMs to manage Python environments, execute Python code and scripts, install packages, and read or write files within an isolated working directory. | |
| MiniMax Coding Plan MCP akirakowalczyk175/minimax-coding-plan-mcp Enables coding-plan users to run AI-powered web searches and analyze images from URLs or local files, integrating these capabilities into MCP clients for enhanced code development workflows. | |
| Yolfi Agent Kit MCP Server akiraleone14632/yolfi-agent Enables AI coding agents to register a Yolfi workspace, create crypto paylinks and hosted checkout, poll payment status, and configure or verify signed webhooks so applications can accept stablecoin payments. Provides these payment workflow | |
| mcp-bing-webmaster akiramatsumoto-github/mcp-bing-webmaster Provides secure, read-only access to Bing Webmaster Tools analytics and non-destructive URL submission for indexing, without destructive site management capabilities. | |
| VSCode MCP akiramiller8649/vscode-mcp Enables AI coding agents to query a running VSCode instance for real-time LSP data such as diagnostics, hover/definition/signature info, and symbol references instead of waiting on slow tsc or eslint runs. Also supports workspace-wide symbo | |
| ComfyUI Local MCP Server akiravd/local-image-mcp-server Enables MCP clients to generate and edit images using local Stable Diffusion models in ComfyUI, with tools for text-to-image, img2img, ControlNet, UI frames, upscaling, and background removal—no cloud API or API key required. | |
| figma-mcp-lite akiraz1/figma-mcp-lite Enables Claude Code to build entire Figma screens from a compact JSON spec using the design system tokens, styles, and components already in the file, with a local Figma plugin bridge and screenshot verification. It reduces token use by del | |
| Synology Download Station MCP Server akitchin/synology-download-mcp A Model Context Protocol server that enables AI assistants to manage downloads, search for torrents, and monitor download statistics on a Synology NAS. | |
| browser-memory akiva1132/browser-memory Proxies every Playwright MCP tool so agents drive a real browser, while automatically attaching per-site lessons, self-firing fixes, saved procedures and the site's observed internal API to each navigation. Later sessions on the same domain | |
| vision-mcp akiyakun/vision-mcp Enables MCP clients to analyze a user-specified image from a NAS share through a single analyze_image tool, sending the image and a short prompt to OpenAI and returning concise observation text for final reasoning. | |
| websearch-mcp akiyakun/websearch-mcp Enables MCP-compatible AI applications to perform web searches via OpenAI's web search tool and receive concise factual results with source URLs, while leaving comparison and final reasoning to the calling AI. | |
| energy-emissions-mcp akkapur/energy-emissions-mcp Enables AI agents to retrieve and rank US facility greenhouse gas emissions from EPA's GHGRP via Envirofacts by state, county, and year, returning totals and citable source details. | |
| EnergyPlus MCP Server akki-24/autonomous-building-energy-optimization-poc-with-mcp-and-energyplus Exposes EnergyPlus simulation control (run, parse metrics, edit schedules) as LLM tools for autonomous building energy optimization. | |
| Ankr API MCP Server akki91/ankr-mcp An MCP server that fetches on-chain blockchain data via the Ankr API, allowing LLMs to retrieve token balances for wallet addresses on specific networks. | |
| microsoft-todo-mcp-server-self-hosted akkilesh-a/microsoft-todo-mcp-server-self-hosted A self-hosted Model Context Protocol server for Microsoft To Do. The key problem this solves: the Microsoft Graph API silently omits user-created lists on personal accounts (GET /me/todo/lists only returns well-known lists like "Flagged Ema | |
| azure-mcp-platform akkireddy-challa/azure-mcp-platform MCP server for Azure resource management, AI Foundry, and Entra ID — inspect and operate Azure infrastructure through AI agents. | |
| grafana-mcp-observability akkireddy-challa/grafana-mcp-observability Enables AI agents to query Grafana dashboards, alerts, and datasources for observability insights and incident investigation. | |
| phoenix-mcp-eval akkireddy-challa/phoenix-mcp-eval MCP server for Arize Phoenix enabling AI agents to perform LLM tracing, evaluation, and dataset management for automated quality assurance. | |
| minqual akley-design/minqual Enables coding agents to compile supplied files, run optional focused tests, and get static findings across ten programming languages, providing a deterministic feedback loop on the code they are about to return. | |
| Internal Documentation Search aklianeva/mcp1 Exposes an internal engineering knowledge base to AI assistants, allowing users to search and retrieve standards, runbooks, and architecture decisions. It supports RAG-enhanced search, document scraping, and specialized prompts for incident | |
| scryer-mcp aklos/scryer Enables AI agents to read, modify, and build from architecture models, keeping the model as the source of truth for intent and synchronized with code. | |
| Amazon Neptune MCP Server akm-2018/tmp_amazon_neptune_mcp_server Enables querying Amazon Neptune databases and analytics graphs using openCypher or Gremlin. It provides tools for executing queries, retrieving graph schemas, and monitoring connection status. | |
| AWS CDK MCP Server akm-2018/tmp_cdk_mcp_server Provides guidance and tools for the AWS Cloud Development Kit, including infrastructure patterns, GenAI constructs, and security compliance via CDK Nag. It streamlines development by generating Bedrock Agent schemas and providing comprehens | |
| Fetch MCP Server akm-2018/tmp_fetch Enables LLMs to fetch and process web content by converting HTML into markdown for easier consumption. It supports chunked reading via pagination and provides configuration options for robots.txt compliance and proxy usage. | |
| vedit akm-8byte/vedit Enables Claude to create, edit, validate, and animate video projects through structured project files, including rendering frames or exports, inspecting previews, and applying themes, templates, effects, and subtitles. | |
| Drizzle Sentinel MCP akmalkhaniub/drizzle-sentinel-mcp Enables database governance for Drizzle ORM projects by inspecting schemas, linting migrations for unsafe operations, detecting schema drift, and explaining query plans with performance checks. | |
| Model Context Protocol (MCP) Server + Google OAuth akmalnurfauzii-dev/loyverse-sales-agent Enables remote MCP connections with Google OAuth authentication, allowing secure access to MCP tools and resources. | |
| TestRail MCP Server akoehler3/testrail-mcp Enables managing TestRail projects, suites, cases, sections, runs, tests, results, plans, milestones, and shared steps directly from MCP-supported AI clients. | |
| pto-mcp akoffice933-maker/pto-agent Exposes 15 MCP tools over stdio and HTTP for construction QA workflows: reading DXF drawings and takeoffs, recognizing scanned as-built documentation and handwritten markups, applying drawing edits only with human confirmation, batch-proces | |
| zom-brain akolazabal/zom-brain A nightly local pipeline that ingests zom codebases and their GitHub activity, compiles them into a queryable markdown brain, and serves it to Claude Code over MCP with strong privacy guarantees. | |
| gitl akomyagin/gitl AI code reviews and git activity digests with machine-readable risk scoring, available as an MCP server for use within an agent session. | |
| Modular RAG MCP Server akon-max/modular-rag-mcp-server Exposes knowledge retrieval to AI tools over MCP with dense, sparse, and hybrid search, RRF fusion, configurable reranking, and modular ingestion of PDF/Markdown documents including image captioning. It also provides query tracing and Ragas | |
| hcl-mcp akontadakis/hcl-mcp Enables natural-language-driven human-centric lighting analysis, including CIE S 026 α-opic and circadian metrics, spectral sky reconstruction from EPW files, and Radiance daylight/electric/glare simulation. | |
| rad-mcp akontadakis/rad-mcp Enables AI assistants to run local Radiance lighting and daylighting simulations on user-owned models, including annual daylight, compliance metrics, renders, glare analysis and electric lighting studies, with reproducible exported scripts. | |
| ollama-websearch-mcp akopper/ollama-websearch-mcp Enables performing web searches and fetching web page content via Ollama's hosted APIs, providing search results and raw page data. | |
| mcp-server-stdio akoskm/create-mcp-server-stdio A starter MCP server using StdioServerTransport, providing example tools to check which app runs on a port (macOS) and add two numbers. | |
| mcp-switchboard akospapp/mcp-switchboard Enables running local MCP servers on machines behind NAT and accessing their tools from anywhere through a single Streamable HTTP endpoint, without opening any inbound ports. | |
| ultramem-mcp akpughe/ultramem-mcp Give any MCP client durable, cross-session memory by exposing an UltraMem deployment's memory layer. | |
| Shaky akquisio-dev/shaky-mcp Gives your AI a live picture of your home bar's spirits, liqueurs, juices, garnishes, equipment and glassware, so it can suggest cocktails you can actually make right now, propose substitutes, help use up open bottles before they turn, and | |
| claude-whatsapp-mcp akram-atassi/claude-whatsapp-mcp Enables Claude Desktop to read, search, send, and broadcast WhatsApp messages and files, and manage groups and communities through a linked personal WhatsApp account. | |
| Notebook MCP akram-side-projects/notebook-mcp Provides AI assistants with deep semantic and runtime understanding of Jupyter notebooks. | |
| PayPal MCP Server akramiot/paypal_mcp_server A Python implementation that enables Large Language Models to interact with PayPal's APIs through function calling, supporting features like invoices, orders, products, subscriptions, and transactions. | |
| Zero Trust Access AI Agent - MCP Server akramiot/zta_mcp_server Zero Trust Access AI Agent - MCP Server | |
| cairnos akramlam/cairnos Local MCP server for CairnOS, a local-first productivity app. Exposes 13 tools that let Claude read and write the same local SQLite "brain" the app uses — create and update
tasks, projects, reminders, ideas, and notes; classify natural-lang |
25,601–25,650 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.