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 |
|---|---|
| Yahoo Fantasy MCP andy78644/yahoo-fantasy-mcp Enables Claude to interact with Yahoo Fantasy Baseball and Basketball leagues, allowing roster analysis, matchup tracking, free agent browsing, and player stats retrieval via natural language. | |
| yuque andy8663/yuque-mcp-tool Enables reading Yuque documents, listing knowledge base docs, and converting source content to Markdown via MCP. Supports session cookie authentication and optional Playwright rendering. | |
| Read Image MCP Server andyanh174/read-image-mcp MCP server using Google Gemini to read and describe image content, supporting single or multiple images and custom prompts. | |
| brreg-mcp-server andyarntsen-alt/brreg-mcp-server Enables AI agents to search and retrieve Norwegian company data from the Brønnøysund Register Centre's open API, including company details, roles, and subunits. | |
| repo-memory-mcp andyast/repo-memory-mcp MCP server for sharing source-backed engineering memory across AI coding clients like Cursor and VS Code. | |
| Lumar MCP Server andyc00ps/lumar-mcp-server An MCP server that enables conversational access to Lumar SEO crawl data via its GraphQL API. It allows users to query projects, inspect crawl metrics, pull URL-level SEO data, and generate reports using natural language. | |
| SelfHostDesktopMCP andyching168/selfhostdesktopmcp Enables MCP clients to securely reach and invoke tools on self-hosted machines through a remote gateway, using outbound-only device connections, OAuth or bearer authentication, per-device policies, and audit logging. | |
| db-query-mcp andychinghk01/db-query-mcp MCP server for running read-only SQL queries across MySQL and PostgreSQL databases with safety guardrails, credentials stored outside source, and support for multiple databases. | |
| Strapi MCP Server andychoi/mcp-strapi Provides AI agents with full access to Strapi 5.x CMS for managing content types, entries, media, and schemas. It supports full CRUD operations, relation management, and secure authentication for comprehensive content administration. | |
| skylight-mcp-remote andychongyz/skylight-mcp-remote Remote MCP deployment scaffold for Skylight's MCP server, hosted on Cloudflare Workers and Containers, enabling HTTP access to the stdio-based Ruby MCP server. | |
| google-appscript-mcp-server andyconley/google-appscript-mcp-server MCP server for managing Google Apps Script projects, deployments, versions, and executions via OAuth 2.0. Provides 16 tools for full API coverage with secure token storage and auto-refresh. | |
| Portero andycufari/portero A self-hosted MCP gateway that aggregates multiple servers into a single endpoint with features for data anonymization and granular permission policies. It integrates a Telegram bot for real-time 2FA approvals of sensitive operations and se | |
| MCP-Flowise andydukes/mcp-flowise A Python package that implements a Model Context Protocol server for integrating with Flowise API, allowing users to list chatflows, create predictions, and dynamically register tools for Flowise chatflows or assistants. | |
| ssh2mcp andyernotfound/ssh2mcp Exposes a single SSH-reachable host as MCP tools for running and backgrounding remote commands, resumable verified file transfers, and read-only file comparison, stat, hashing, listing and reading. Runs on loopback with per-request Bearer a | |
| OpenProject MCP Server andyeverything/openproject-mcp-server Enables LLM applications to interact with OpenProject for project management, work package tracking, and task creation. | |
| CouchDB MCP Server andyfe76/couchdb_mcp Provides tools for interacting with CouchDB databases, enabling document management, Mango search queries, and database administration. It allows Claude Code and other MCP clients to perform CRUD operations and manage indexes on local or re | |
| SoupNet-oss andyforest/soupnet SoupNet gives your AI agents one shared memory of how you think — across Claude, Cursor, and ChatGPT. Each checks your past decisions as searchable “recipes” and acts on your real judgment. Share it, and your team’s agents inherit that judg | |
| iCloud Connect MCP andyg1128/icloud-connect-mcp Enables users to connect a self-hosted MCP server to their own personal iCloud mail and calendars, supporting folder discovery, search, message and attachment reading, sending and replying, verified moves and flag changes, plus calendar rec | |
| oms-client-agent-mcp andygruening/oms-client-mcp Exposes the 0xSequence OMS wallet client as a local MCP server, enabling email-based wallet authentication, message signing, balance queries, and transaction sending on supported networks like Polygon, Base, and Sepolia. | |
| Slack Message MCP andygruening/slack-mcp Enables posting messages to a Slack channel using a bot token, with support for stdio and HTTP modes. | |
| gong-nl-db-mcp andyhorvitz/gong-nl-db-mcp Enables read-only querying of the gong-nl-db Postgres database through natural language via Claude Desktop. | |
| imessage-send-mcp andyjianzhou/imessage-send-mcp Enables sending iMessages or SMS messages via the macOS Messages app using osascript. No Full Disk Access required, and never reads your message history. | |
| 蓝湖 Design Schema MCP andyjin5/lanhu-schema-mcp A read-only MCP server for reading and analyzing Lanhu (Blue Lake) design projects, providing tools to retrieve design lists, previews, node trees, schemas, and exportable resources. | |
| Chosun MCP andyjusa/chosunmcp MCP server for querying Chosun University portal, CLC/e-Class, and OJ systems, providing tools to access academic information, timetables, notices, and more. | |
| netdisk-organizer-mcp andykair55-byte/baidunetdisk-mcp Enables intelligent organization and retrieval of Baidu Netdisk files through semantic scanning, event clustering, and structured queries. Adds safety with protected moves, undo history, and customizable profiles, building on the official B | |
| Cisco MCP Network Discovery andykumeda/cisco-mcp-discovery Enables users to start from a seed host, traverse CDP/LLDP neighbor evidence and device information over SSH, and produce an editable Draw.io topology diagram plus supporting evidence for engineer review. It supports explicit host/CIDR scop | |
| Google Cloud MCP Server andyl25/gcp-mcp A Model Context Protocol server that connects to Google Cloud services, allowing users to query logs, interact with Spanner databases, and analyze monitoring metrics through natural language. | |
| Google Cloud MCP Server andyl25/googlecloud-mcp An MCP server that enables querying and interacting with Google Cloud services including Logging, Spanner, Monitoring, and Cloud Trace through natural language. | |
| Math-Physics-ML MCP System andylbrummer/math-mcp Provides GPU-accelerated scientific computing capabilities including symbolic mathematics, quantum wave mechanics simulations, molecular dynamics, and neural network training through four specialized MCP servers. | |
| MCP Replicate FLUX andylee20014/mcp-replicate-flux A Model Context Protocol server that generates images using Replicate's FLUX model and stores them in Cloudflare R2, allowing users to create images through simple prompts and retrieve accessible URLs. | |
| jimeng-ai-mcp andyleimc-source/jimeng-ai-mcp Wraps Jimeng AI's image and video generation APIs for AI assistants to create and edit visual content via natural language. | |
| mdymcp andyleimc-source/mdymcp Unified MCP server for Mingdao platform, providing 98 tools for collaboration APIs (v1) and HAP gateway. Enables AI IDEs to interact with Mingdao's features like schedules, workflows, knowledge bases, etc. | |
| Tencent Ad MCP Server andyleimc-source/tencent-ad-mcp Wraps all Tencent Ads Marketing API v3.0 endpoints as MCP tools, enabling AI assistants to directly manage ads, creatives, reports, and more via natural language. | |
| wecom-crm-mcp andyleimc-source/wecom-crm-mcp MCP server for WeCom customer contact API, enabling LLMs to manage customers, tags, group chats, moments, and mass-send messages. | |
| Supermemory andylin-hao/antigravity-supermemory Gives Google Antigravity persistent memory by automatically recalling profile and project context before model calls and saving new conversation turns at turn boundaries. Exposes MCP tools to add, search, list, profile, and forget memories, | |
| HWCA MCP Server andyliner13/hwca-mcp Enables AI assistants to automate context-management tasks for the Horizon Worlds editor by executing system commands, reading/writing files, and managing processes. | |
| ts-mcp-server andyliner13/ts-mcp-server A lightweight MCP server that provides 40 tools for TypeScript/JavaScript refactoring and code intelligence, directly mapping to TypeScript's tsserver protocol commands for accurate structural changes and workspace analysis. | |
| RusyaSearch andylopeslindao-art/rusyasearch Enables AI agents to perform stealth web searches, browse pages with anti-bot bypass, and extract clean Markdown content, supporting direct image URLs and deep research. | |
| ai-image-gpt-mcp andyluu98/ai-image-gpt-mcp Standalone MCP server and CLI for generating images via ChatGPT backend, with reliable exact file paths and multi-account login support. | |
| vn-autocad-claude andyluu98/vn-autocad-claude Enables Claude to control AutoCAD—draw, edit, query, layers, blocks, annotations, screenshots, plot to PDF—using plain language. | |
| VN MCP Blender andyluu98/vn-mcp-blender Enables AI to construct 3D building models in Blender from Vietnamese architectural data, including walls, floors, columns, beams, stairs, and roofs, while reading DXF floor plans from AutoCAD and extracting quantities from the model. | |
| vn-revit-mcp andyluu98/vn-revit-mcp Enables Claude and other MCP clients to query an open Autodesk Revit model through pyRevit 7 — counting doors and rooms, taking off wall, slab and structural quantities, detecting missing parameters, and exporting results to Excel. It runs | |
| vn-sketchup-mcp andyluu98/vn-sketchup-mcp Enables controlling SketchUp from MCP-compatible clients via a stdio Python server that bridges to a Ruby plugin, supporting component operations, material assignment, scene export, arbitrary Ruby evaluation, and wood joinery tools. | |
| Promptzilla andymccutcheon/silverquill Exposes five prompt-engineering skills as MCP tools, prompts and resources so a connected AI client can itself prepare and execute task, system-prompt, evaluation and rewrite work. It also provides a durable, resumable pipeline that tracks | |
| mcp-cliniko andymillar84-cyber/mcp-cliniko Provides integration with the Cliniko API for healthcare practice management, enabling patient, appointment, invoice, and payment operations via natural language. | |
| Agentic Travel Recommendations MCP Server andypnguyen11-gif/agentic-travel-recommendations-api Enables an AI agent to fetch member profiles and generate deterministic, partner-rule-compliant travel recommendations on a multi-tenant white-label platform. | |
| Trello MCP Server andypost/mcp-server-ts-trello Enables interaction with Trello boards, lists, and cards through Model Context Protocol (MCP) tools, leveraging TypeScript for type safety and asynchronous operations. | |
| org-mcp andyreagan/org-mcp A Python-based MCP server that provides access to local Org mode files, enabling querying and management of org notes, agenda, and TODOs through natural language. | |
| Crest Counterparty Intelligence andysalvo/crest-counterparty-intelligence Enables agents to assess counterparty risk, token danger, and wallet creditworthiness on Base by analyzing contract powers and controlling wallet reputation. | |
| crest-verify andysalvo/crest-verify-mcp Verify x402 endpoints before your agent spends. Three tools: verify (SPEND/CAUTION/INVESTIGATE/DO NOT SPEND backed by 50K+ services), passport (full trust identity), risk_check (deep assessment). No API keys, no signup. |
28,901–28,950 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.