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 |
|---|---|
| excalidash-mcp asas276203s/excalidash-mcp MCP server that lets Claude (and other MCP clients) create, list, read, update, and delete drawings in ExcaliDash via its REST API. It allows users to create diagrams directly from natural language commands like 'draw a flowchart'. | |
| Claude Bridge asasds145/claude-bridge A remote MCP server that lets an AI assistant session and a separate agent exchange queued messages via tools like send_to_chief and wait_for_reply, waking the agent with webhooks and long-polling for its replies. | |
| sticker-mcp asashiki/sticker-mcp Enables AI to send expressive stickers based on conversation context, with a built-in UI for managing stickers. | |
| mcp-cocktail asavs/mcp-cocktail Provides a framework to benchmark, evaluate, and inject real-time guardrails across competing MCP servers, CLIs, and AI agent tools. It enables recursive self-improvement by mining failures and synthesizing weakest valid guardrails. | |
| Google Ads MCP Server asaya-01/google-ads-mcp Enables LLMs and AI agents to query Google Ads accounts and reporting data through the Google Ads API, including customer lookups, resource metadata inspection, and reference material on metrics, segments, and release notes. Tools and resou | |
| Context-Aware Personal Assistant MCP Server for Alexa+ asayamedia/amazon-alexa-mcp-hackathon Provides persistent memory, calendar integration, task management, and proactive assistance for Alexa+ through the Model Context Protocol. | |
| garmin-claude-mcp asayet44/garmin-claude-mcp Enables Claude to read recent Garmin training history and wellness data and to create, update, or remove structured workouts on an intervals.icu calendar so they sync to Garmin Connect and a watch. | |
| garmin-claude-mcp asayet44/garmin-claude-mcp-fiouf Enables Claude to read recent training activities and wellness signals such as sleep, HRV, and resting heart rate, then design structured workouts that are written to an intervals.icu calendar and synced onward to Garmin Connect and the use | |
| ShapeItUp asbis/shapeitup Enables AI agents to write TypeScript to create, render, verify, and export parametric 3D models using Replicad/OpenCascade CAD kernel, headlessly from terminal or MCP clients. | |
| GitHub MCP Server asbloom-py/mcp-servers Enables interaction with GitHub through the GitHub API, supporting file operations, repository management, advanced search, and issue tracking with comprehensive error handling and automatic branch creation. | |
| underindex-mcp ascaniounderindex/underindex-api Verified records on 60 niche fashion subcultures (years, key brands, iconic items, where to buy, price range, and a WARNING on what each must not be confused with). Catalog and a sample record are free; full records cost $0.01 each, paid ov | |
| avito-scraper ascard/mcp-avito MCP server for searching and retrieving details from Avito listings, enabling integration with Claude Desktop. | |
| superposition-wishstar asccccyn/superposition-wishstar Enables a human and an AI companion to exchange hidden and visible stars through private/shared bottles, including requesting, offering, accepting, and opening stars on special dates with equal permissions via MCP tools. | |
| forja asced1807/forja-mcp Enables any AI, even a small local model, to work on real and large projects without getting lost, by compactly reporting project structure, exactly what is broken, whether a change truly passes verification, and which errors were already f | |
| Hubble MCP Server ascentkorea/hubble_mcp A Python-based Model Context Protocol server that integrates with Claude Desktop, allowing users to connect to Hubble API services by configuring the server with their Hubble API key. | |
| 医学知识检索 MCP 服务器 aschenmo/termonline-mcp 基于 MCP 协议的专业医学信息查询工具，集成 MSD 手册、MeSH 主题词、医学编码、术语和药品查询等多个权威数据源，支持 Claude Desktop、Cursor 等 AI 应用。 | |
| comfygenmcp aschet/uncomfymcp MCP server that connects an AI assistant to a running ComfyUI instance, allowing it to fetch saved workflows, inject a prompt and seed, run generation, and return the image inline in chat. | |
| Grimoire aschlatweiler/grimoire-ue5 Read-only MCP server that gives Claude live access to your UE5 project state — Blueprints, interfaces, variables, functions, event graphs, materials, structs, and Data Assets. | |
| ScrapeGraph MCP Server aschneider39/scrapegraph-mcp Enables AI assistants to perform AI-powered web scraping, structured data extraction, search, multi-page crawling, JSON schema generation, and scheduled monitoring through the ScrapeGraph AI API. It also exposes account credit and history l | |
| annotation-mcp aschokinatgmail/annotation-mcp MCP server for image annotation, supporting bounding boxes, arrows, highlights, callouts, text, and circles, plus barcode and text detection with OCR. | |
| fcp-mcp-server aschulz70462/fcp-mcp-server Enables Claude to read, edit, and generate real Final Cut Pro timelines via FCPXML, including cut detection, markers, roles, transcript-based editing, keyframes, speed curves, cross-NLE export, and live pushes into a running Final Cut Pro. | |
| log-mcp ascii766164696d/log-mcp MCP server for log file analysis. Gives LLMs the ability to efficiently analyze large log files without loading them into context. | |
| HeatShield ascilch/heatshield-mcp HeatShield MCP server enables AI assistants with real-time spatial reasoning for urban heat wave safety. It provides tools for geocoding, weather/heat risk, air quality, finding cooling spots, and heat safety advice. | |
| SentinelMCP asctttt/sentinelmcp Stateless enterprise policy firewall & token-cost proxy for MCP. It enforces identity, policy, and budget on every tool call. | |
| Intervals.icu MCP Server ascuitando/intervals-mcp Connects to Intervals.icu to let users query training data, create workouts, manage calendar events, and coach athletes through natural language in Claude Desktop. | |
| AltSportsData MCP Server asd-git-master/altsportsdata-mcp MCP-compatible server that gives AI agents access to alternative sports data across 30+ leagues — odds, events, probabilities, settlement, and futures for prediction markets, DFS platforms, and sportsbooks. | |
| AltSportsLeagues MCP Server asd-git-master/altsportsleagues-mcp Enables AI agents and sportsbooks to discover, evaluate, and monitor alternative sports leagues with tools for discovery, valuation, fingerprinting, and market data. | |
| Memory Engine MCP Server asd-noor/agentmemory A high-performance MCP server providing long-term memory storage with semantic and keyword search capabilities, using SQLite and fastembed for sub-200ms queries. | |
| ProjectContext asd-noor/projectcontext A high-performance MCP server providing long-term memory storage with semantic and keyword search, along with a structured agenda engine for task management. | |
| db-query-mcp asd369932/db-query-mcp Enables AI assistants to safely run read-only SQL against SQLite databases through whitelist-validated queries, capped result sets, and confined file paths. It also exposes schema inspection so models can discover tables and columns before | |
| file-manager-mcp asd369932/file-manager-mcp Enables AI assistants to list directories, read, write, and search files within a locked root directory, using resolve-then-validate path checks, size caps, and binary detection to prevent sandbox escapes. | |
| Remote MCP Server (Authless) asdasgusdas/remote-mcp-server-authless A template for deploying an authentication-free MCP server on Cloudflare Workers. Provides a starting point for creating custom tools accessible via SSE from remote MCP clients like Claude Desktop or AI Playground. | |
| remote-mcp-server-authless asdasgusdas/remote-mcp-server-authless-test123 Deploy a remote MCP server on Cloudflare Workers without authentication, enabling custom tools and connection to AI Playground or Claude Desktop. | |
| Remote MCP Server (Authless) asdasgusdas/remote-mcp-server-authless-testabctest Enables deploying a remote MCP server on Cloudflare Workers without authentication, supporting custom tools and connection to AI Playground or Claude Desktop. | |
| Remote MCP Server (Authless) asdasgusdas/remote-mcp-server-authless3 A template for deploying an authentication-free MCP server on Cloudflare Workers. Allows users to create and customize remote MCP tools accessible from Claude Desktop or AI playgrounds via SSE endpoint. | |
| MAIN MCP asdener123/main-mcp-server MCP (Model Context Protocol) server for the MAIN DEX on Base.
Provides AI agents (Claude, Cursor, etc.) with tools to interact with the protocol: swap tokens, manage liquidity, enter/exit ALM strategies(10% APY), and more. | |
| markfetch-mcp asdfas988/markfetch-mcp Enables AI agents to fetch any web page as clean markdown or screenshot it, turning URLs into LLM-ready context. | |
| bl-mcp asedias/bl-mcp Enables an AI agent to drive a live Blender session, building, sculpting, measuring, checking, rigging, lighting, rendering and exporting 3D models through safe operations in world units. Every geometry-changing call reports achieved dimens | |
| shayari-mcp aseem-raspberry/shayaari Search and retrieve Devanagari Hindi shayari from an owner-authorized, provenance-tracked corpus, with audit and research-only inspection capabilities via stdio. | |
| sher-search aseem-raspberry/urdu-sher-mcp Enables local, auditable semantic search over a pinned subset of Mirza Ghalib's Urdu corpus, retrieving existing couplets with provenance and license evidence. | |
| MCP Security Framework aself101/mcp-secure-server Enables creation of secure-by-default MCP servers with 5-layer validation to protect against injection, path traversal, and other attack vectors. | |
| arcgis-portal-mcp asem-d/arcgis-portal-mcp Enables AI assistants to search, query, and manage ArcGIS Portal and Online content, feature layers, users, and groups via the Model Context Protocol. | |
| @kama/mcp-server asemanserver/kama-mcp-server MCP server that auto-discovers Kama CRM API endpoints from OpenAPI spec and exposes them as tools for AI agents to perform CRM operations via natural language. | |
| ignition-mcp asemenovarglass/ignition-mcp Enables AI assistants to manage and interact with Ignition Gateway 8.3+ through a curated set of tools covering gateway administration, projects, resources, tags, alarms, historian data, and script execution via the REST API. | |
| MCPedia asepharyana/mcpedia MCP server for a content-first knowledge base, enabling AI agents to search (full-text, semantic, hybrid) and retrieve Markdown documents, list content, and find related docs. | |
| MCP Aseps asepsafrudin/multiple-mcp-server-by-kimi A modular MCP server suite that provides core tools, long-term memory, knowledge RAG, skills registry, and external integrations for AI agents. | |
| Public Procurement MCP asept1977/public-procurement-mcp Neutral MCP server for researching public procurement notices from EU (TED) and German (DÖE) sources, offering tools to search, retrieve, and inspect notices without built-in business preferences. | |
| tender-documents-mcp asept1977/tender-documents-mcp Safely downloads and extracts public tender documents from PDFs, Office files, and ZIP archives into text with structured signals, while also supporting document comparison and base64 extraction. | |
| Jellyseerr MCP Server aserper/arrchestra Enables interaction with Jellyseerr media request systems through natural language. Supports searching for media, creating requests, checking request status, and managing your media library workflow. | |
| Etsy MCP Server aserper/etsy-mcp Provides full access to the Etsy Open API v3 for both buyer browsing and seller shop management through 37 specialized tools. It enables users to manage listings, process orders, handle shipping, and access inventory data via secure OAuth 2 |
31,001–31,050 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.