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 |
|---|---|
| swissdevjobs dhernandez175/swissdevjobs-cli Enables AI agents to search salary-transparent tech job postings across nine boards and eight countries, filter them by pay, remote work, tech stack, level, and language, and retrieve apply URLs or track applications. All commands are JSON- | |
| Spec3 MCP Server dhevenb/dheven-spec3-mcp-server A demonstration MCP server for local development and testing with Claude Desktop on WSL. Provides basic utility tools including greeting messages, echo functionality, and server information retrieval. | |
| APRS.fi MCP Server dhhuston/aprsfi-mcp-server A Model Context Protocol server that provides access to APRS.fi API for ham radio position tracking and balloon chase operations, enabling AI-powered APRS data analysis through Claude Code. | |
| codex-web-search-mcp dhicoc/codex-web-search-mcp Zero-dependency MCP server that wraps OpenAI Codex's standalone search endpoint into codex_web_search and codex_web_research tools for Claude Code, enabling real-time web search and multi-step deep research independent of the underlying mod | |
| localsend-mcp dhinalata21-ctrl/localsend-mcp Enables sending files to LocalSend devices on the local network by scanning for devices and sending files using the LocalSend v2 protocol. | |
| HackBridge dhineshkumar272005/hackbridge An MCP server that connects AI clients to a Linux terminal for real-time automated penetration testing and CTF challenge solving. It enables AI models to execute terminal commands and interact with offensive security tools like Nmap, SQLMap | |
| TypeScript MCP Server Template dhinojosac/calendar-mcp A comprehensive template for building MCP servers with TypeScript, Fastify, and Docker support. Includes tools for calculations and weather data, resources for server information, and prompts for greetings with full development tooling. | |
| Azure DevOps MCP Server dhippley/ado_mcp Enables interaction with Azure DevOps through Cursor chat, providing tools to manage builds, pipelines, work items, sprints, and board operations. Supports secure authentication via Personal Access Tokens and allows natural language-driven | |
| Azure Topology Graph MCP Server dhippley/azure_mcp_graph Enables exploration and analysis of Azure infrastructure by querying Azure Resource Graph, ARM, and Network Watcher APIs to create interactive topology maps. Provides tools for searching resources, discovering relationships, finding connect | |
| mssql-mcp dhipskind253/mssql-mcp Read-only MCP server for Microsoft SQL Server that retrieves connection details from AWS Secrets Manager, enabling database exploration and querying via natural language. | |
| Trilium MCP Server dhiraj-ydv/trilium-mcp Enables users to manage Trilium Notes through natural language commands in the terminal. Provides full ETAPI integration for creating, searching, moving, and editing notes, along with an autonomous agent for complex organizational tasks. | |
| MCP Boilerplate dhiraja474-star/mcp_agents_test Deploys a remote MCP server to Google Cloud with authentication, enabling tool invocation via FastMCP and local testing with uv. | |
| VidMCP dhirajlochib/vidmcp MCP server for video editing with text-prompt subject segmentation and compositing effects behind subjects. Enables agent-driven video creation and education animations. | |
| ShadowVault MCP Proxy dhirajparihar/shadow-vault Enables AI agents and MCP clients to keep sensitive data out of model context by substituting format-preserving synthetic tokens, restoring real values at local tool boundaries, and re-masking tool outputs before they return to the model. | |
| MarketIntel MCP Server dhirajpatra/mcp-n8n A minimal MCP server for market research using FastMCP and the Tavily API, with n8n automation, enabling company overview, competitor analysis, product portfolio, pricing snapshot, and recent news queries. | |
| GitHub MCP Server dhirendra1729/git_mcp MCP server exposing tools to fetch GitHub repository details, issues, and commits, enabling AI agents to query and summarize GitHub data via local LLMs. | |
| Coros MCP Server dhivakarkd/corus-mcp Enables AI assistants to access and analyze Coros watch data including activities, fitness metrics, training zones, and more through unofficial Coros API endpoints. | |
| walletwallet-mcp dhk/walletwallet-mcp Exposes the WalletWallet pass API as MCP tools for creating and updating digital passes, supporting Google Wallet links and usage checks. | |
| Anki MCP Server dhkim0124/anki-mcp-server A Model Context Protocol server that bridges Claude AI with Anki flashcard app, allowing users to create and manage flashcards using natural language commands. | |
| Cyphers MCP Server dhkim327/cyphersmcpserver An MCP server that integrates the Neople Cyphers Open API with AI assistants for searching players, match histories, and rankings. It provides tools for retrieving character info, game items, and real-time statistics directly through natura | |
| NHN Server MCP dhks77/gw-ssh Enables secure SSH access to servers through a gateway with Kerberos authentication, allowing execution of whitelisted commands with pattern-based security controls and server information retrieval. | |
| Sequential Story MCP Server dhkts1/sequentialstory Provides tools for structuring complex problems through narrative-based sequential story elements or systematic sequential thinking, helping make complex problems more memorable and easier to understand. | |
| localvibecode dhluong90/localvibecode Enables IDE and terminal agents to query an offline AST graph, inspect a file’s one-hop impact, verify changes with zero-token checks and tests, and run Plan-Execute-Verify coding cycles using a local Ollama model. | |
| mcp-neo4j-query-optimizer dhodapkarsoham/mcp-neo4j-query-optimizer Extracts structured operator data from Neo4j query plans and provides rich context for MCP clients to deliver intelligent optimization recommendations. | |
| Kontomanager MCP Server dhofer/mcp-server-kontomanager Enables programmatic access to Austrian mobile carriers (yesss!, Georg, XOXO) account management. Allows users to check usage, download bills, manage SIM settings, and configure call forwarding through natural language interactions. | |
| MCP ComfyUI Flux dhofheinz/mcp-comfyui-flux Enables AI image generation using FLUX models through ComfyUI with GPU acceleration, supporting image generation, 4x upscaling, and background removal with optimized Docker deployment. | |
| search-journal dhogenson/journal-search Enables semantic search over personal Markdown journal entries by indexing them with Ollama embeddings into a SQLite vector store and exposing retrieval through a Streamable HTTP MCP endpoint at /mcp. | |
| blacksmith-usage-mcp dholliday3/blacksmith-usage-mcp A local MCP server that exposes Blacksmith.sh's usage and cost data, enabling queries for CI spend through agents, alerts, or dashboards. | |
| coros-training-mcp dholliday3/coros-training-mcp Running-first MCP server for COROS that allows authoring, editing, and scheduling running workouts, plus accessing sleep, HRV, training load, and activity exports. | |
| ci-context-mcp dholman7/ci-context-mcp Enables AI coding assistants to inspect GitHub Actions CI runs, diagnose failures with failed-step summaries and filtered job logs, read per-job coverage, and view pull request checks through read-only, allowlisted access. | |
| supergateway-pro dhomane/supergateway-pro Provides a centralized MCP gateway with connection pooling, real-time observability dashboard, and macOS menu bar integration, enabling efficient resource usage for AI coding clients. | |
| MCP Verdict MCP Server dhoomlegeche/mcpverdict-mcp Enables AI assistants to search independent, source-reviewed evaluations of MCP servers and retrieve full reviews or individual sections covering capabilities, setup, security, permissions, token costs, and maintenance status, along with se | |
| officient-mcp dhrpieterjan/officient-mcp An MCP server that provides typed tools for AI assistants to read and write data from the Officient HR API, including people, calendars, contracts, expenses, and more. | |
| Google Workspace MCP Server dhrubajyoti-giri/google-workspace-mcp Enables AI assistants to access and manage Google Workspace services such as Gmail, Drive, Docs, Sheets, Calendar, and Slides through the MCP protocol, with built-in OAuth 2.0 authentication and read/write tool support. | |
| letta-appserver-mcp dhrubajyoti-giri/letta-mcp Enables callers to manage Letta App Server agents and long-term memory through granular Streamable HTTP tools, including agent CRUD, health checks, and memory save/search/get/update/delete operations. | |
| seafile-mcp dhrubajyoti-giri/seafile-mcp Enables AI assistants to manage Seafile files, folders, and libraries through MCP, with multi-user credential storage and dual token-based authentication. | |
| Expense Tracker MCP Server dhruta25/mcp Enables users to track and manage daily expenses through SQLite storage, supporting operations like adding, updating, deleting expenses, calculating totals by category, and filtering expenses by date range or category. | |
| reasoning-traces dhruv-corethink/reasoning-traces Adds a deep_reasoning tool that consults stronger reasoning models (e.g., DeepSeek R1) to produce full reasoning traces for complex problems, helping the agent shape and cross-check its answers. | |
| MCP Project Manager dhruv-vootkuri/mcp-project-manager Enables task management (create, list, update tasks with priority and status) using SQLite storage via MCP tools. | |
| mcp-tool-router dhruv1n30/mcp-tool-router Enables agents to send only the handful of tool definitions relevant to each question, ranking a large catalog by keywords and optional embeddings to cut context cost and wrong-tool picks. It can also run in front of any mcpServers config a | |
| LakeHouse_MCP dhruv2816/lakehouse_mcp Enables Claude to interact with a local DuckDB lakehouse by inspecting Gold table schemas, running read-only SQL queries, and checking dbt pipeline health. | |
| weather dhruvagarwal29/us-weather-mcp Provides weather forecasts, current conditions, and alerts for US locations using the National Weather Service API. | |
| smart-bug-triage dhruvdubey17/smart-bug-triage MCP server that triages GitHub issues by classifying, ranking priority, and assigning an engineer using a local LLM (Ollama) with full traceability. | |
| mcp-crypto dhruvil05/mcp-crypto Provides real-time cryptocurrency data from CoinGecko, including prices, market data, historical data, and coin search. | |
| Excel MCP Server dhruvimahale08/excel_mcp Enables AI-powered employee data management in Excel files, automatically classifying employees by department, designation, and salary band based on experience and role, with automatic data validation and backup capabilities. | |
| SJSINGLE_AI SQL Server MCP dhruvipatel712/dhruvi_mcp_server MCP server for Microsoft SQL Server enabling safe read-only queries, schema discovery, and natural-language query via LangChain. | |
| SQL Server MCP Server (Diamond Inventory) dhruvipatel712/mcp_server Enables safe, read-only querying and schema exploration for Microsoft SQL Server databases with preconfigured Diamond Inventory support, multiple database management, and optional HTTP API. | |
| MCP Dev Suite dhruvkej9/mcp-dev-suite A unified set of developer tools including file search/replace, SQLite queries, HTTP requests, port inspection, system monitoring, and Git status, accessible via natural language in MCP-compatible clients. | |
| RCP-1 dhruvmahendrapatel/abap-mcp-rcp-v1 RCP-1 is an enterprise-ready MCP server that connects AI assistants to SAP ABAP systems via the ADT REST API, with built-in security, access controls, and deployment options for BTP or on-premise. | |
| better-fetch dhruvparmar372/better-fetch An MCP server that gives AI tools a reliable way to fetch content from the web, handling anti-bot protection and JavaScript-rendered pages. |
44,401–44,450 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.