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 |
|---|---|
| Readedit abnersajr/mcp-readedit MCP server that combines Read+Edit file operations into single tool calls. 80-95% fewer tool calls formulti-file refactoring across Claude, Cursor, Windsurf, and more. | |
| Meta Ads MCP abnerzx/meta-ads-mcp MCP server for the Meta Marketing API with 118 typed tools across ads, insights, pixels/CAPI, pages, Instagram, WhatsApp, catalogs, audiences, leads, and billing, featuring secure token storage and a confirmation gate on destructive calls. | |
| wordpress-seo-mcp abnormal-yi/wordpress-seo-mcp Connects AI assistants to WordPress sites, enabling automated SEO analysis and fixes for meta tags, schema, content, images, and technical SEO via MCP tools. | |
| rutorrent-mcp abnormalend/rutorrent-mcp MCP server for controlling rTorrent through ruTorrent's httprpc plugin, enabling torrent management (list/add/remove/start/stop), label/priority management, data movement, and global throttle settings from any MCP client. | |
| web-gpt-file-save abo1016/web-gpt-file-save Enables ChatGPT to save conversation attachments, generated files, and images directly into a configured local macOS project directory with OAuth-secured MCP access. | |
| MCP Unity Editor abojad2026/mcpunityopenhands Enables AI assistants to interact with Unity Editor through the Model Context Protocol, allowing natural language control of Unity projects including scene manipulation, GameObject creation, component updates, package management, and test e | |
| telegram-mcp abol1644/telegram-mcp MCP server that enables AI agents to send messages, photos, polls, and receive replies via Telegram with persistence and rate limiting. | |
| Amazon Public Fetch MCP abomination81/amazon-public-fetch-mcp Enables local MCP clients to retrieve public Amazon product page details such as title, ASIN, visible price, and feature bullets using the host computer's network connection or a configured HTTP(S) proxy. | |
| hunyuan-workbench abooai/hunyuan3d-workbench Enables local CLI and MCP agents to drive Tencent Hunyuan 3D web workbench for multi-view uploads, model generation, background task monitoring, automatic downloads, and Blender asset handoff using the user's existing web login and quota. | |
| mcp-menesesdk aboodtt404/mcp-menese-sdk 19-chain DeFi gateway for AI assistants for Menese Protocol | |
| MCP LangChain Weather Agent aboomar26/mcp_waether A weather MCP server that geocodes city names and fetches live weather from Open-Meteo, enabling a LangGraph agent to answer weather queries. | |
| Alfresco MCP Chat aborroy/hyland-mcp-gen Turns hundreds of Alfresco MCP REST endpoints into a small set of tools for a local LLM, enabling natural language interaction with Alfresco while keeping everything local and secure. | |
| drawio-mcp abossard/drawio-mcp Enables AI assistants to create, read, and edit draw.io diagrams with live preview in VS Code. | |
| LedFX MCP Server abossard/ledfx-mcp Enables AI assistants to control a local LedFX instance through natural language, allowing management of LED devices, virtuals, effects, scenes, palettes, and playlists. | |
| prospecto-mcp aboudou-cto-bloko/prospecto-mcp MCP server for Prospecto that enables managing your prospection pipeline with AI, including prospects, campaigns, and scraping. | |
| pogo-tb buyer MCP bridge abovecolin-venture/pogo-tb-buyer-mcp-bridge Enables access to RDW vehicle and Dutch address data packs by automatically handling x402 payments using the buyer's own wallet key, running locally as a stdio MCP server. | |
| learn-mcp abp2204/learn-mcp An MCP server for agent-guided DSA practice that generates LeetCode-style problems and provides tutoring with escalating hints, concept explanations, and progress tracking. | |
| memory-mcp abpandey-dev/agent-memory-engine Enables Claude Code and other MCP-capable agents to turn conversations into structured long-term memories, deciding whether each extracted fact is new, an update, or already known while preserving superseded history. It also lets agents rec | |
| Lean MCP abr4xas/lean-mcp Enables WordPress plugins to expose their Abilities as MCP tools, prompts, and resources, letting MCP clients discover and call site capabilities over HTTP with application passwords or locally through WP-CLI over stdio. | |
| ThreatWatch MCP abraar02/threatwatch-mcp AI-powered threat intelligence server with real-time alert monitoring and multi-source IOC analysis, enabling security investigations directly in Claude Desktop. | |
| jira-kb abraganca-1977/jira-kb-mcp Enables MCP-capable AI assistants to search and retrieve past Jira issues, resolutions, and recurring topics from a fully local embedded knowledge base using hybrid semantic and keyword search. | |
| fpt-mcp abrahamadsk/fpt-mcp MCP server for Autodesk Flow Production Tracking (ShotGrid) enabling AI assistants to query, create, update, and delete entities via the ShotGrid API with built-in RAG anti-hallucination and safety layers. | |
| maya-mcp abrahamadsk/maya-mcp Enables control of Autodesk Maya using natural language via Claude and the Model Context Protocol, providing tools for modeling, animation, scene management, and RAG-powered documentation search. | |
| @meeseeks-sdk/mcp abrahamcasanova/meeseeks-mcp An MCP server that runs a quality gate on generated code, executing it in a sandbox and scoring it before returning the code to the user. | |
| MCP OSINT Server abrahamhl/mcp-osint-server Enables AI agents to run open-source intelligence workflows such as sanctions screening, prioritized vulnerability briefs, IOC searches, evidence-chain verification, and sun-position chronolocation. | |
| Trainner AI MCP Server abrahamhm00/trainner_ai Enables LLMs to access and analyze biometric and training data via MCP, supporting queries on sleep, performance, nutrition, and training load to generate adaptive training insights. | |
| GoHighLevel MCP Server abrahamshal/ghl-mcp Enables AI assistants to interact with GoHighLevel CRM through MCP tools, with support for OAuth 2.1 remote deployment and agency multi-sub-account mode. | |
| Obsidian MCP abrak98/obsidian-mcp Enables AI agents to manage Obsidian vaults through full CRUD operations, wikilink management, and section-level manipulation. It supports frontmatter editing, tag-based searching, and automated link updates to maintain vault integrity. | |
| RollDate MCP abramov-front-end/rolldate-mcp Helps AI agents install and integrate the RollDate vanilla JS scrolling date picker into projects. | |
| telegram-bot-mcp abramovmarketing88-byte/telegram-bot-mcp MCP server that enables interaction with the Telegram Bot API, allowing users to send messages, retrieve updates, and access chat information through natural language. | |
| Sailfish Devel MCP abranson/sailfish-devel-mcp Enables local MCP clients to run Sailfish OS device, SDK, OBS, and Android/AppSupport development workflows via typed tools for SSH access, screenshots, touch injection, builds, logs, services, and repository checks. | |
| Between abrar5510/between Enables each household's assistant to negotiate coverage for calendar commitments with other households, exchanging signed, schema-checked offers to arrange swaps or favours while keeping calendars, names, and locations private. Both sides | |
| Filesystem MCP Server abrarsavan123/mcp-integration-project Provides MCP tools for reading, listing, writing, searching, watching, and batch-processing files, enabling automated file management and resume matching workflows. | |
| WhatsApp MCP Server (Docker Edition) abrauser/whatsapp-mcp-docker Enables AI clients to interact with WhatsApp via MCP tools for searching contacts, sending/receiving messages, and managing chats, running in a Docker container with HTTP/SSE transport. | |
| Security Context MCP Server abreed05/cybersecurity-mcp Provides instant access to authoritative security documentation from organizations like OWASP, NIST, and major cloud providers through natural language semantic search. It enables users to retrieve security best practices, frameworks, and v | |
| Easy MCP Proxy abrookins/easy-mcp-proxy Enables aggregation, filtering, transformation, and composition of tools from multiple MCP servers through a single proxy with tool views. | |
| mcp-server-eia abrose1/mcp-server-eia Provides AI agents with structured access to the U.S. EIA Open Data API for energy data including power plants, operations, fuel prices, projections, and state CO2 emissions. | |
| MCP File Downloader abs222222/mcp-file-downloader Enables Claude Desktop to download files from web URLs with automatic browser fallback for JavaScript-heavy sites. Supports smart redirect handling, custom file naming, and cross-platform compatibility. | |
| Morpheus Inference absgrafx/morpheus-grok-mcp Enables chat completions, embeddings, and model listing through an OpenAI-compatible interface. Supports configurable public or custom Uplink endpoints, per-bot API keys, and MoE/fallback policies. | |
| MCP E-commerce Server abshekpat/mcp-ecommerce-crud Enables CRUD operations for e-commerce products with AI-generated descriptions, MySQL-backed search, inventory monitoring resources, and prompt templates over stdio or HTTP/SSE. | |
| Arrakis MCP Server abshkbh/arrakis-mcp-server Exposes Arrakis VM sandbox functionality to LLMs, enabling sandbox management and command execution. | |
| ABsmartly MCP Server absmartly/mcp Provides access to the ABsmartly experimentation platform with 230+ commands across 33 groups for experiment lifecycle, metrics, goals, teams, etc. | |
| @absolutejs/mcp absolutejs/mcp Enables serving a remote Model Context Protocol endpoint by exposing tools, prompts, and resources with customizable authorization and hooks, allowing AI models to interact with your application through a standardized JSON-RPC interface. | |
| claude-ask absolutemode/claude-ask Enables users to request a second opinion from a locally authenticated Claude Code model via MCP tools, supporting asynchronous jobs with restricted tools for safety. | |
| session-recall absolutemode/session-recall Provides local, agentic semantic recall over Claude Code session history, enabling the agent to search past discussions semantically, expand turns, and grep transcripts. | |
| circe-graph absterrg0/circe-graph Enables agents to route spoken requests to the right project on the right machine and to remember the outcome by reading and writing a FalkorDB graph, so learned aliases, clarification answers, and episodes carry over across sessions. Expos | |
| IBM AS400 ISeries MCP Server abstracta/ibm-as-400-iseries-mcp-server This project implements a customizable MCP server to execute RTE protocol.
The intention of this project is to be easily extensible. You can add your own MCP tools by using RteUtils class.
Also is needed to define the RTE connection param | |
| markdown-publish abstractwebunit/markdown-publish-plugin Enables AI to search, retrieve, list notes, and get backlinks from a published Markdown vault (Obsidian) via GitHub Pages. | |
| MCP Knowledge Viz abtpst/mcp-knowledge-viz Enables storage and semantic search of facts, and interactive 3D visualization of embeddings via MCP tools. | |
| mcp_slack abu-bakaryasir/my_slack_mcp fetch the latest channels messages chat |
23,251–23,300 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.