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 |
|---|---|
| Canvelete canvelete/canvelete-mcp-server Enables programmatic design creation and manipulation on the Canvelete platform through AI assistants. Supports design management, canvas element manipulation, template application, asset management, and real-time synchronization with the d | |
| Open Legal Data MCP Server canvena/oldp-mcp Provides access to German court decisions and laws via MCP tools, enabling legal document search and retrieval. | |
| Proxmox MCP Server canvrno/proxmoxmcp A Python-based server enabling interaction with Proxmox hypervisors. It supports secure authentication and provides tools for managing nodes, VMs, clusters, and storage. | |
| Noteastic MCP canxinner/noteastic-mcp-public Enables local inspection and comparison of Noteastic backups, and exports pages or notebooks as PDF and PNG via MCP tools. | |
| tuya-bulb-mcp canyrtcn/tuya-bulb-mcp Enables an MCP-compatible AI client to locally control a compatible Tuya / Smart Life Wi-Fi bulb over the LAN, including status checks, power, color, brightness, and color temperature, without Tuya Cloud calls at runtime. | |
| graph-mcp cao-jacky/graph-mcp Exposes a Neo4j knowledge-graph index over personal markdown notes to LLM agents via MCP, enabling semantic search, tag navigation, and relationship discovery. | |
| knowledge-mcp cao-jacky/knowledge-mcp An MCP server that allows Claude to export knowledge and experience into a personal knowledge corpus of markdown files with YAML frontmatter, organized by category, with tools for saving, reading, searching, and listing entries. | |
| CAD-CAE-Agent SolidWorks MCP Server caoguanqiu1-alt/cad-cae-agent Enables AI clients to drive a real SOLIDWORKS 2020 installation through COM to build parametric models, add materials, loads and constraints, run static Simulation studies with mesh and pin-contact checks, and read back feature trees, studi | |
| QRadar MCP Server caohonghoa98/mcpsiem Bridges LLMs to IBM QRadar SIEM via 4 intelligent MCP tools covering 728 REST API endpoints, enabling natural language queries for offenses, assets, rules, and more. | |
| QRadar MCP Server caohonghoa98/qradar-mcp-server-docker MCP server for IBM QRadar SIEM that consolidates 728 REST API endpoints into 4 intelligent tools, enabling natural language interaction for security tasks like managing offenses, assets, rules, and reference data. | |
| vision-augment caomeiyouren/vision-augment Enables non-vision LLMs to understand images, extract text via OCR, and parse documents through a unified MCP interface, with local-first processing and optional OpenAI-compatible channels. | |
| CorelDRAW MCP caoshuo594/coreldraw-mcp Enables AI assistants on Windows to inspect, edit, and save CorelDRAW documents through COM, including template-driven batch generation from CSV/Excel data and post-save verification. | |
| mql5-help-mcp caoshuo594/mql5-help-mcp Provides AI coding assistants with local access to 4500+ MQL5 documentation files and supplementary ebooks via MCP, enabling efficient search, browsing, and error diagnosis for MQL5 development. | |
| NanoBanana MCP Server caoshuo594/nano_banana An MCP server that wraps the OpenRouter API, enabling users to access diverse language models like Google Gemini 3 Pro for chat and image tasks. It provides tools for generating completions and listing available models within MCP-compatible | |
| uacos caotiensinh/uacos Local-first code intelligence and safety layer for AI coding agents. MCP server exposes dependency graph, impact analysis, and AST-compressed repo context, backed by typed local memory, patch-scope safety gates, and git-independent transact | |
| Seeder MCP Server caoxuandungecom/seeder Enables AI assistants to read and edit projects, tasks, client requests, comments, and settings over the Model Context Protocol, deployed with the app and authenticated via read-only or read-write bearer tokens scoped to the creating user. | |
| mcp-macclean caozhaoliang/mcp-macclean Local multi-package manager cache cleaning MCP service that safely discovers, previews, and cleans caches for Maven, pnpm, npm, yarn, pip, uv, and Go. | |
| Capgo cap-go/capgo.app Capgo: push fixes to your Capacitor users in minutes, build signed iOS and Android apps without a Mac, and roll back in one click. | |
| Meraki MCP Server cap5192/meraki_mcp_server Enables management and monitoring of Cisco Meraki networks, including device operations, client policies, firewall rules, wireless settings, and camera configurations through the Meraki API. | |
| ContextForge capatinore/contextforge MCP orchestrator combining code knowledge graph and context compression into a single pipeline to reduce token usage by 60-99%. | |
| contextforge-mcp capatinore/contextforge-mcp Orchestrates codebase indexing, token compression, and spec-driven development into a single MCP pipeline for AI coding agents. | |
| WinTerm MCP capecoma/winterm-mcp A Model Context Protocol server that provides programmatic access to the Windows terminal, enabling AI models to interact with the Windows command line through standardized tools for writing commands, reading output, and sending control sig | |
| Cloudflare Remote MCP Server capeom28-png/remote-mcp-server-authless Deploy a stateless MCP server on Cloudflare Workers without authentication, supporting custom tool registration and compatibility with AI clients like Claude and Playground. | |
| clipboard-vision-mcp capetlevrai/clipboard-vision-mcp Enables text-only AI models to understand clipboard images by describing them through a vision model, eliminating manual file saving. | |
| Typst Web MCP caphefalumi/typst-web-mcp Enables AI agents to authenticate to typst.app cloud projects, list/create/delete projects, and read, write, surgically edit, rename, or delete Yjs CRDT-backed text files and binary assets over the native WebSocket and REST/GraphQL protocol | |
| pce-memory caphtech/pce-memory MCP server for context-aware memory and retrieval with hybrid search, dual-phase memory, and boundary-first security. | |
| Capital-com Public API MCP Server capital-com-sv/capital-mcp The Capital.com MCP Server lets your AI assistant talk to your trading account directly. Market data, position checks, trade previews – all in plain language, without leaving your AI tool. | |
| DFX Intelligence capital-w-holdings/dfx-private-credit-mcp Cited private credit research from SEC filings: who lends to a company, BDC holdings and marks, sponsor financing, LP commitments and adviser moves. Free, no key: https://exchange-production-9123.up.railway.app/mcp/core?c=glama | |
| kreports capitalparser/kreports-dart-mcp Enables investors and analysts to query Korean listed companies' financial health, accounting risks, and disclosure events using DART filings, accessible via natural language through Claude. | |
| Capital Press MCP capitalpressdev/mcp Lets MCP clients browse tokenized stock news presses, view AI audits and onchain votes, purchase full texts via x402 payments, and cast onchain votes. | |
| mcp-template capitan112/mcp_template Minimal MCP server template for quick setup with one tool, one resource, and one prompt, enabling easy integration with Claude Desktop. | |
| Edvibe School MCP capitanes/edvibe-school-mcp Enables MCP-based access to the Edvibe School API for supported Pro-plan schools, exposing 78 operations categorized by risk for read, write, high-risk, and sensitive actions. | |
| ebay-browse-mcp capitansuat/ebay-browse-mcp Minimal MCP server for searching eBay listings via the Browse API, enabling keyword search with filters, sorting, pagination, and retrieving full item details. | |
| Tax Client Intake & Appointment Optimization MCP Server capithan/tax-intake-mcp Streamlines tax professional workflows by automating conversational client intake and generating personalized document checklists based on specific tax situations. It includes tools for calculating case complexity and routing clients to app | |
| MD Vision caplandorlespan/md_vision MCP server that enables AI assistants to open files and highlight ranges in a read-only Markdown and code viewer. | |
| access-calibre caplin-adam/access-calibre MCP server enabling LLMs to query a local Calibre Content Server for ebook metadata, chapters, and content in HTML or Markdown. | |
| capline-mcp caplinehq/capline-mcp Enables AI agents to make payments with strict spending limits enforced by signed mandates, preventing unauthorized fund movement beyond predefined caps and allowlists. | |
| ao-config-mcp capnexus/ao-config-mcp MCP server for Aptos ONE configuration management, enabling schema intelligence, change set management, distribution workflows, and cross-environment comparison. | |
| OWM MCP Server capnkeith/one-world-montessori MCP server providing Google Workspace tools (e.g., Drive browsing/search) and a peer channel for presence and messaging. Enables natural-language interaction with these tools via MCP-compatible clients like Claude. | |
| HoudiniMCP capoom/houdini-mcp Connects Houdini to Claude AI through Model Context Protocol, enabling AI-assisted 3D modeling, scene creation, simulation setup, and rendering through natural language commands. | |
| Supabase MCP Server cappahccino/sb-mcp A Model Context Protocol server that enables Claude and other LLMs to perform database operations and invoke Edge Functions within Supabase through natural language. | |
| mcp-server-cappt cappt-team/mcp-server Enables generating outlines and presentations using Cappt. | |
| Article Writer MCP cappybara12/mcp-use Enables automated content creation pipeline: topic research, article writing, image sourcing, and GitHub PR submission for blogs. | |
| OpenXAI MCP Server cappybara12/mcpopenxai Provides tools for evaluating and benchmarking AI explanation methods through a standard interface that can be used with AI assistants and MCP-compatible applications. | |
| discord-mcp cappyeo/discord-mcp Exposes the Discord REST API to AI agents via the Model Context Protocol, enabling message sending and other Discord interactions. | |
| Recon cappyeo/recon Recon indexes your codebase into a knowledge graph and exposes it via 14 MCP tools. AI agents get dependency mapping, blast radius analysis, safe multi-file rename, execution flow tracing, Cypher queries, semantic search, and PR review with | |
| db-fahrplan capracoder/db-fahrplan-mcp Enables MCP clients to access live Deutsche Bahn timetable data, including connections, departure and arrival boards, platforms, delays, fares, and disruptions, by querying bahn.de directly with no API key. | |
| jianying-local-mcp capricornus-joe/jianying-local-mcp Enables AI to create and edit local Jianying/CapCut draft projects on macOS from videos, images, audio, and text, supporting editable subtitles, keyframes, motion presets, and batch operations via MCP tools. | |
| Clonst capritora/clonst Enables adversarial code review by connecting Claude Code to OpenAI Codex, iterating until consensus is reached between the two AI models. | |
| Dice Roller capsjs/mcp_server Provides dice rolling tools for tabletop RPGs, including standard dice, custom notation, D&D stat generation, and initiative ordering. |
36,701–36,750 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.