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 |
|---|---|
| Stash MCP Server donlothario/stash_mcp_server An MCP server for querying and analyzing a Stash instance with advanced filters, caching, and personalized recommendations. | |
| SQLite Database MCP Server with Google OAuth donlw/mcp-server-with-oauth Enables AI assistants to perform CRUD operations on a SQLite database, with all tools protected by Google OAuth 2.0 authentication. | |
| Google Workspace MCP Server donmrmango/google-workspace-mcp A comprehensive integration providing 114 tools to manage Google Drive, Docs, Sheets, Slides, Gmail, Calendar, and more through the Model Context Protocol. It enables seamless interaction with the full Google Workspace suite for file manage | |
| MCP Data Analyst donmul/mcp-data-analyst Enables natural language querying of SQL databases using AI, supporting multiple database types and automatic schema discovery. | |
| LAPRAS MCP Server donna1819/lapras-mcp-server Enables users to search job listings, view job details, and retrieve or update work experiences, job summaries, career goals, and technical skills through natural language. | |
| CanLII MCP Server donna49/canlii-mcp Enables AI assistants to search and retrieve Canadian court decisions, legislation, and case citation information through the CanLII API. | |
| PACER MCP Server donna49/pacer-mcp Enables live search of U.S. federal court cases and parties across district, bankruptcy, and appellate courts using your own PACER account, with filters for courts, filing dates, case types, nature of suit, and party roles. | |
| Yolfi MCP Server donna536/yolfi-agent Enables AI coding agents to add stablecoin checkout, payment links, payment status checks, and webhook verification to applications, plus webhook-based access logic after confirmed payments. | |
| data-gov-il-mcp donna634/data-gov-il-mcp Enables MCP-compatible clients to discover, inspect, and query Israeli Government Open Data from data.gov.il — datasets, resources, organizations, tags, and tabular datastore records — through the official CKAN API. Includes a bundled catal | |
| Sub-Agents MCP Server donnac15696/sub-agents-mcp Enables users to define reusable, task-specific agents in Markdown and run them from any MCP-compatible client using a chosen coding CLI. Supports shared backend and model configuration plus optional session continuity across calls. | |
| Juror Cloud MCP donnakarabacak/juror Enables users to list workspaces and inspect concise pull-request review findings and hosted run summaries, and to prepare then, after explicit confirmation, start or rerun an existing hosted review. It deliberately never exposes raw diffs, | |
| tradingview-chart-mcp donnal30446/tradingview-chart-mcp Enables fetching TradingView chart snapshots for any ticker and timeframe, returning direct image URLs or base64 data for AI analysis. Uses browser pooling and session-based authentication to handle several concurrent chart requests with su | |
| Smart Coding MCP donnali24415/smart-coding-mcp Enables AI coding assistants to search a local codebase semantically using AI embeddings, finding relevant code by meaning instead of exact keywords. It also provides package version lookup, manual reindexing, cache clearing, workspace swit | |
| Bitbucket MCP donnarao1616/bitbucket-mcp Enables AI assistants such as Cursor to work with Bitbucket Cloud and Server through its REST APIs, listing and retrieving repositories, fetching and creating pull requests, and reviewing pipeline data. Read-only by default, with destructiv | |
| Financial Modeling Prep MCP Server donnasanchez0415/financial-modeling-prep-mcp-server Enables AI assistants to access and analyze financial data, including stocks, ETFs, crypto, forex, commodities, economics, company fundamentals, and market insights through 250+ tools. Supports dynamic, static, or full toolset modes for fle | |
| Discogs MCP Server donnatto/discogs-mcp Enables AI assistants to search, manage, and analyze personal Discogs music collections with features like mood-based recommendations, advanced search, and collection analytics. | |
| Siri Shortcuts MCP Server donnatucker96230/mcp-server-siri-shortcuts Enables LLMs to list, open, and run shortcuts from the macOS Shortcuts app, including passing optional text or file input and exposing dynamically generated tools for available shortcuts. | |
| UART MCP Server donnel666/uart-mcp Enables AI assistants to communicate with serial port devices, supporting port management, data transmission in text/binary modes, interactive terminal sessions, and automatic reconnection. | |
| MCP Spine donnyb369/mcp-spine A local-first middleware proxy that proxies multiple MCP servers through a single entry with schema minification, semantic routing, security hardening, and state guard. | |
| LibreLink MCP Server donnycrash/librelink-mcp-http Enables secure access to continuous glucose monitoring data from FreeStyle Libre sensors, with tools for current readings, history, statistics, trends, and sensor info, plus an optional Streamable HTTP deployment behind bearer-token authent | |
| agent-utils-mcp donnywin85/agent-utils-mcp Provides six general-purpose utilities (geocoding, reverse geocoding, weather, web search, URL-to-Markdown, secure random) as paid MCP tools, with each call costing $0.01 USDC on Base mainnet. | |
| superops-mcp donoree/superops-mcp Enables interaction with the SuperOps.ai PSA/RMM platform via its GraphQL API, providing tools for managing clients, tickets, assets, technicians, and custom queries. | |
| deployctl donotwaitx/deployctl Enables AI coding agents and developers to perform secure, ultra-fast differential deployments over FTP, FTPS, and SFTP, inspect remote directory trees, test connectivity, and run dry-run diffs without exposing server credentials. | |
| wellulu-insight donoueken/wellulu-insight Enables automatic saving of insights from Claude conversations as GitHub Issues, with features to create, list, and search insights by category and keyword. | |
| Cloudflare Workshop MCP Server donovan-fournier/cloudflare-workshop-mcp-server Provides chess-related tools via the Model Context Protocol, integrating with the Chess.com API to fetch daily puzzles, live streamers, player information, and more for AI assistants. | |
| X-Ways MCP donovoi/x-ways-mcp Enables triage, installation validation, and controlled automation of X-Ways Forensics and related tools through structured MCP tools for agents. | |
| edstem_mcp donpham7/edstem_mcp An MCP server that allows AI assistants to access EdStem course discussion boards, including listing courses, fetching posts, searching, and retrieving thread details, with automated SSO login support for Georgia Tech. | |
| tauri-mcp donswayo/tauri-mcp A Tauri plugin that enables AI agents to interact with Tauri applications through screenshots, DOM inspection, and input simulation via the Model Context Protocol. It allows agents to perform actions like clicking, typing, and executing Jav | |
| UniFi Network MCP Server dontcrash/unifi-local-network-mcp Exposes the UniFi Network Integration API as MCP tools, dynamically loaded from JSON manifests, with read-only mode by default. | |
| mc9py MCP server dontforgetantaiku/mc9py Enables AI assistants to build and edit Micro-Cap 9 circuits, run analyses, sweeps, Monte Carlo and optimization, read numeric results, place cursors, and capture native MC9 screenshots through 33 tools. | |
| Claude Continuity MCP Server donthemannn/claude-continuity A Model Context Protocol server that provides persistent memory and conversation continuity for Claude Desktop and Claude Code, allowing users to save and restore project context when threads hit token limits. | |
| Solana Agent Kit MCP Server donutlabs-ai/mcp-solana-data An implementation that enables interaction with the Solana blockchain through the Model Context Protocol, supporting all actions from the Solana Agent Kit for standardized protocol operations. | |
| MCPlanManager donway19/mcplanmanager An AI agent task management system that provides structure and visualization for long-term task planning with support for the Model Context Protocol (MCP) standard. | |
| MCP Zephyr donyfs/mcp-zephyr Enables comprehensive test management in Zephyr Scale Cloud, including creating and managing test cases, executing tests with step-by-step results, organizing test cycles and plans, and performing advanced JQL searches. | |
| NetSpectre WebMCP Challenge Edition doobydev/netspectre-webmcp-challenge Enables human-led defensive cyber investigations by letting agents and people share visible case state, review synthetic evidence metadata, prioritize explainable signals, draft findings that require human approval, and generate incident su | |
| graph-memory doodle-lin/graph-memory Provides AI coding agents with a local knowledge-graph memory, enabling cross-project retrieval via PageRank diffusion and tools to retrieve, write, extract, update, and view recent knowledge over MCP. | |
| mcp.shop doodlydan/mcp An MCP-based web shop server that enables users to authenticate and order t-shirts through MCP tools. Features secure authentication with WorkOS AuthKit and admin functionality for viewing order details. | |
| ddb-mcp doogan1/ddb-mcp Enables MCP-compatible clients to read D&D Beyond characters, campaigns, and game reference data, with optional opt-in tools for session tracking and character building. | |
| AgentShield MCP Server doogie-bigmack/agentshield-mcp Exposes AgentShield security scanning tools to protect AI clients by detecting threats like prompt injections, PII leakage, and SSRF. It enables real-time monitoring of inputs, outputs, and tool definitions to ensure secure interactions wit | |
| Yahoo Mail MCP Server doohinkus/gemini-yahoo-mcp Enables LLMs to read, search, and send emails through Yahoo Mail using secure OAuth2 authentication. | |
| IACR MCP Server doomdagadiggiedahdah/iacr-mcp-server Enables programmatic access to the IACR Cryptology ePrint Archive, facilitating the search and retrieval of cryptographic research papers and metadata via a secure interface. | |
| harness-feed-mcp doominkim/harness-feed-mcp Fetches and searches structured JSON feeds from 7 tech sources including GeekNews, Hacker News, and arXiv. | |
| typeorm-docs-mcp doominkim/typeorm-docs-mcp Analyzes TypeORM entity source files offline to produce schema graphs, ERD diagrams, Markdown documentation, and missing-documentation audits. Enables AI clients to understand database schema without a database connection. | |
| moodle-mcp doomscrollsurvivor/moodle-mcp A Model Context Protocol (MCP) server that connects AI coding agents to your Moodle LMS. Fetch assignments, grades, deadlines, and sync everything to Obsidian automatically. | |
| Reaper MCP doomsdayxproductions/reaper-mcp Provides AI-powered undetectable browser automation for data harvesting, bypassing protections like Cloudflare, and intercepting network traffic, with 90 tools for element interaction, extraction, and network debugging. | |
| bili doomsgeats/dsh-bili-feed Enables models to look up Bilibili's trending videos, keyword search results, video details, and popular danmaku, returning compact plain-text summaries instead of bulky JSON. Works without login, cookies, or extra dependencies, and also ru | |
| Solarium doomsun-dev/solarium A knowledge base MCP server backed by Qdrant vector database with local embeddings for semantic search and document management. | |
| wecom-excel-mcp doone-skser/wecom-excel-mcp Enables AI assistants to read WeCom online spreadsheets (read-only) from a shared link, listing worksheets and data ranges, reading text, formatting, and cell images, and searching sheet contents using each caller's own login cookie. | |
| dooor-os-mcp dooor-ai/dooor-os-mcp Exposes Dooor OS workspace capabilities to MCP-compatible AI clients, enabling natural language querying of data sources, app and deployment inspection, agent and database management, and governance trace reading. | |
| mcp-gateway dooosp/mcp-gateway MCP server that exposes local agents as tools for Claude Code, enabling capabilities in quant, trading, news, reports, robotics, Notion, and FreeCAD. |
45,551–45,600 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.