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 |
|---|---|
| keyword-steroids-gold diklaaltman91-ux/keyword-gold Provides Hebrew-focused SEO keyword research and gap analysis, including Google Suggest expansion, related questions/PAA, keyword clustering, bulk gap scans, crawl audits, Search Console insights, Semrush competitor gaps, and content brief | |
| keyword-steroids-70 diklaaltman91-ux/keyword-steroids-70 Enables keyword research across 70 languages without API keys, providing Google Suggest autocomplete, People Also Ask, related searches, Jaccard clustering, and language-specific intent tags via MCP tools. | |
| obsidian-web-mcp dikoloko/obsidian-claude-server Gives Claude and other MCP clients remote, authenticated read/write access to a personal Obsidian vault over HTTPS — reading and atomically writing markdown, parsing YAML frontmatter, running indexed frontmatter queries and full-text search | |
| HotelRate MCP diksha-jindal/hotelrate Enables AI agents to retrieve and compare hotel offers across Trip.com, Booking.com, Agoda, and Google Hotels through a unified MCP interface, with demo mode, Playwright-backed live searches, and batch queries. | |
| MCP → Local MSSQL Server dikshadogra25/mcp Exposes SQL Server stored procedures as tools for LLM clients (Claude Desktop, VS Code, Cursor, etc.) enabling direct database interaction through natural language. | |
| DOS Growth MCP Server dikshu143644/dos-growth-mcp Connects a brokerage account to AI assistants, enabling portfolio queries, order management, and market data access through natural language. | |
| k6 MCP Server dil-anoojibettu/k6-mcp-server Enables running k6 load tests with customizable duration and virtual users via natural language, with real-time output and LLM-powered analysis. | |
| BRVM MCP Server dilane-kamga/brvm-mcp-server Enables AI agents to access live market data from the BRVM stock exchange, supporting queries on stock prices, indices, market summaries, and company information via the Model Context Protocol. | |
| Lexicon MCP dilanrg/lexicon-mcp A local-first multilingual dictionary, thesaurus, translation, lexical-relations, semantic-neighbour, and English wordplay server for the Model Context Protocol (MCP). It operates fully offline with read-only query access and no data mutati | |
| google-flow-mcp dilantha-wijesinghe/google-flow-mcp Lets AI agents generate images in Google Flow by driving the real web app in a Chrome window you sign into once, selecting the model, aspect ratio, and image count from a prompt. Results can be downloaded at 1K, 2K, or 4K, all without an AP | |
| Robinhood MCP dileepgaganr/robinhood-mcp Integrates with Robinhood API and LLMs like Perplexity to provide AI-powered portfolio rebalancing recommendations and trading analytics without executing trades directly. | |
| Upstox MCP Server dileepgaganr/upstox-mcp Enables AI-powered trading and portfolio management through Upstox API integration. Supports portfolio rebalancing strategies with LLM inference for automated trading decisions. | |
| CodeContext MCP dileepreddy27/codecontext-mcp Enables coding agents to search local repositories and retrieve bounded, cited source chunks, look up full indexed chunks, and inspect index statistics through read-only MCP tools over stdio. | |
| mcp-taiho-toyota-bearing-catalogue dileepwick/official-taiho-toyota-bearing-catalogue-mcp-server Authoritative Taiho Toyota Bearing Catalogue MCP server. Provides high-fidelity technical specs for Toyota engine bearings, monetized via X402. Optimized for automotive AI agents and procurement systems. | |
| ControlAPI-MCP dili414/controlapi-openapi2mcp An MCP server that dynamically converts any OpenAPI or REST API into MCP tools, allowing for real-time server switching and schema reloading. It supports variable substitution for headers and bodies, enabling seamless authentication and int | |
| jupyter-book-writer diligejy/jupyter-book-writer-mcp Automates Jupyter Book notebook creation by fixing common rendering issues (bold, math, markdown formatting) and provides tools for adding cells, validating notebooks, updating TOC, and deploying. | |
| MCP TypeScript SDK dilipbaviskar/mcp-server-sdk-typescript A TypeScript SDK for building MCP servers and clients, providing standardized context provision for LLMs through tools, resources, and prompts. | |
| Weather MCP Server dilipsc/weather-mcp Provides active weather alerts for U.S. states and 7-day forecasts for a given latitude and longitude. | |
| Dilix MCP dilix-ai/mcp Open-source MCP server providing real estate regulatory intelligence (zoning, permits, entitlements, deal scoring) for US properties, enabling AI agents to access 10 callable tools. | |
| NotebookLM Retrieval MCP dillettante/notebooklm-readonly-mcp Enables users to connect their own account to AI clients to list notebooks and sources, fetch complete indexed source text and summaries, and ask grounded questions that return citation-to-source mappings, without creating, renaming, upload | |
| power-plan-db dillettante/power-plan-db MCP server for Korean government power/energy statutory plans. Enables AI agents to search and retrieve public power plan documents. | |
| MCP Development Server dillip285/mcp-dev-server A Model Context Protocol server that enables Claude to manage software development projects with complete context awareness and code execution through Docker environments. | |
| MCP Terminal Server dillip285/mcp-terminal A secure server for executing terminal commands within predefined paths, allowing safe interaction by Large Language Models with operating system environments. | |
| obsidian-mcp dillonpcousins/obsidian-mcp An MCP server that gives AI agents read and write access to a folder of Markdown notes, supporting full-text search, reading, listing, and writing notes. It is deliberately small, with no dependencies beyond the MCP SDK, and includes proper | |
| Iron Cannon dillonrich/iron_cannon An MCP-powered compliance copilot for SaaS stacks, enabling structured audit workflows including stack detection, module wiremapping, implementation directives, code verification, and security/infrastructure/legal readiness gates. | |
| Formly Agent Contracts dills122/formly-contract Enables agents to query precompiled, versioned Angular Formly contracts to generate deterministic typed end-to-end test intents without evaluating arbitrary application code. | |
| MCP Weather Server dilmurodmak/mcpweather Provides real-time weather information for any location using FastMCP. | |
| codebase-memory-mcp diloper/codebase-memory-mcp A Docker-based MCP server providing codebase memory and search tools. It enables storing/retrieving memories, regex search of code, and file summarization for AI assistants. | |
| docmost-community-mcp dilruwanm/docmost-community-mcp Enables AI assistants to search, read, write, and organize content in self-hosted Docmost Community Edition wikis through MCP clients like Cursor and Claude. | |
| MCP-Server dilshankavishka/mcp-server Enables querying a structured CV and sending test emails via Ethereal through a backend API. | |
| Enterprise Data MCP Server diluksha-upeka/mcp MCP server providing natural-language tools for managing and querying an employee database, including user CRUD, search, and statistics. | |
| NeuroSpace MCP Server diluksha-upeka/neurospace-mcp-server Exposes a Neo4j knowledge graph to AI assistants via MCP, enabling entity search, neighbor traversal, and read-only Cypher queries. | |
| MCP Yandex Voice dimaanj/mcp-yandex-voice MCP server for Cursor that generates text responses via Yandex GPT and converts them to speech using Yandex SpeechKit TTS, enabling voice replies to user messages. | |
| Telegram MCP server dimajolkin/mcp-telegram Connects AI assistants to Telegram through the MTProto API, enabling them to list dialogs and messages, send, edit, forward, and delete messages, create groups, manage folders, and mute, archive, or leave chats. | |
| etoro-mcp dimakudr/etoro-mcp This server exposes read-only eToro portfolio data, including positions, P&L, balances, watchlists, and closed trade history, as tools that can be registered as a custom connector in Claude.ai for natural-language portfolio queries. | |
| AIWorkers MCP dimaneuron/aiworkers-mcp An MCP server that lets coding agents like Cursor and Claude manage neural employees (AI assistants) across channels such as Telegram, WhatsApp, and web widgets. It provides tools for surveys, tasks, worker card management, Telegram bot con | |
| ai-trading-kit dimas-100/ai-trading-kit Enables AI assistants to connect to brokerage accounts in read-only mode so users can inspect balances, positions, and orders, and provides a local lab for backtesting strategies and simulated trading with pretend money. | |
| Claude Desktop Extension dimascior/claude_automation Adds automation capabilities to Claude Desktop through MCP and enables Claude Desktop to act as a model gateway for Claude Code, solving WSL-Windows integration challenges through file-based bidirectional communication. | |
| knitto-mcp-server-channel dimasknitto/knitto-mcp-server-channel A Node.js server that runs a WebSocket relay and AI bridges (Cursor and OpenRouter) to integrate Figma with MCP agents. | |
| m365-radar dimavasilenko-intune/m365-radar An MCP server that provides offline searchable Microsoft 365 roadmap data and live Azure status, enabling AI agents to answer questions about upcoming features, roadmap changes, and Azure incidents. | |
| mcp-brreg dimavasilenko-intune/mcp-brreg MCP server for the Norwegian Central Coordinating Register for Legal Entities (Enhetsregisteret), providing tools to search companies, get full register records, list recent registrations, and retrieve registered roles. | |
| awesome-awesome dimdoremy/awesome-awesome MCP server that helps discover and rank libraries from awesome lists by tech stack and category, using a state-machine workflow to find relevant sections and present ranked repos. | |
| brain-graph dimedatacloud/brain-graph Lets Claude or any MCP client query a Neo4j index of a markdown vault, answering what is connected to a note and how far, how two notes relate, which notes are orphans or dangling links, and running read-only Cypher. | |
| SAP Datasphere MCP Server dimidr/sap-datasphere-mcp Model Context Protocol server that lets AI assistants explore and query SAP Datasphere — metadata discovery, catalog search, OData and SQL queries, ETL extraction, data lineage and column profiling — with built-in config-driven PII masking. | |
| college-career-agent-poc dimipilo92/college-career-agent-poc Enables a conversational goal-setting flow for college and career coaching, exposing tools to save and retrieve goals and open a goal planner, with recommendations sourced from Career Coach MCP. | |
| mcp-server-python dimitrearaujo/mcp-server-python A Python MCP server providing AI agents with tools for local knowledge base search, business context retrieval, and text summarization prompt generation. | |
| @0n1x/rhinogent dimitrilaouanis-tech/rhinogent-mcp Provides AI agents with a self-custody identity and MCP server for verifying counterparties, signing facts, and carrying portable reputation within the 0n1x trust ecosystem. | |
| Engram dimitriou28217/engram Enables AI coding agents to query a locally indexed structural code graph — source entities, callers/callees, Git relationships and recorded mistakes — so they retrieve focused, token-bounded context instead of reading entire files. It runs | |
| Semantic Scholar MCP Server dimitriou79336/semantic-scholar-fastmcp-mcp-server Enables searching and retrieving academic paper data, author profiles, and citation networks through the Semantic Scholar API, including paper and author search, batch lookups, citation and reference tracking, snippet search, and paper reco | |
| CamoFox MCP dimitris22952/camofox-mcp Enables AI agents to navigate, interact with, search, extract from, and automate the web using anti-detection browser tools, with multi-tab workflows, session persistence, downloads, and batch operations. |
44,701–44,750 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.