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 |
|---|---|
| finanze-mcp adriadam10/finanze-mcp Enables AI assistants to read and query a Finanze self-hosted portfolio manager using natural language, including net worth, positions, and financial calculations. | |
| woolies-mcp adrian-baker/woolies-mcp Enables browsing and searching the Woolworths New Zealand grocery catalogue, retrieving product details, checking specials, and managing a shopping trolley with optional account sign-in. | |
| omnidaw-agent-mcp adrian-cancio/omnidaw-agent-mcp Enables policy-gated interaction with OMNi DAW through preview-and-apply workflows for composing, arranging, inspecting, measuring, and exporting audio, with domain filtering and job/file safety checks. | |
| Harvest Natural Language Time Entry MCP Server adrian-dotco/harvest-mcp-server Enables natural language time tracking and reporting for Harvest, including automatic leave requests, project/task matching, and date parsing. | |
| ucc_question_bank adrian-maa/ucc-question-bank-mcp Enables MCP-compatible AI clients to read and work with the UCC question bank on ucc.sziscloud.com, including listing question libraries, starting exercises, fetching questions with answers, and submitting answers, via a local bridge that s | |
| Android Source Explorer MCP Server adrian09990/android-source-explorer-mcp Enables on-demand access to AOSP and AndroidX source code, letting AI tools search classes, inspect methods, trace inheritance, and resolve definitions and references across Android framework and Jetpack libraries. | |
| MCP Jenkins adrian8211/mcp-jenkins Enables AI assistants to securely interact with Jenkins through its API, exposing tools for inspecting items, nodes, views, queues, and builds, reading console output, test reports, and artifacts, managing plugins, and triggering, stopping, | |
| edge-history-mcp adrianba/edge-browser-mcp A Model Context Protocol server that exposes Microsoft Edge browsing history across multiple profiles, allowing listing profiles and fetching history for a given day. | |
| Nemotron Transcribe MCP adrianbindc/nemo-transcribe-mcp Enables transcription of local audio files and YouTube links in over 40 languages, including translation between supported languages and English, by calling an already-running Nemotron 3.5 Transcribe endpoint. Long recordings are automatica | |
| obsidian-rag-mcp adrianbodrug/obsidian-rag-mcp Provides local hybrid search over an Obsidian vault via the Model Context Protocol. It enables Claude Code to retrieve relevant notes with citations, using on-device embeddings and BM25 rank fusion. | |
| fabric-docs-mcp adriancalavie/fabric-docs-mcp MCP server that provides LLM coding agents with version-pinned Fabric modding documentation, including search, page reading, and a curated built-ins index to encourage idiomatic code. | |
| Microsoft SQL Server MCP adriancy/mssql-mcp Enables interaction with Microsoft SQL Server databases through T-SQL query execution, table exploration, and schema inspection. Supports configurable write protection and row limiting for safe database operations. | |
| airflow-mcp-server adriandecode/mcp-server-for-airflow A Model Context Protocol server for controlling Airflow 3 via Airflow APIs. | |
| notability-mcp adriandlam/notability-mcp Enables MCP clients to search and read Notability notes, including handwritten pages via OCR-based fuzzy search and page images rendered as PNGs. Runs entirely against a local synced index, so queries never touch the network. | |
| FRED MCP Server adriangonzalez4947/fred-mcp-server Enables users to browse, search, and retrieve 800,000+ economic time series, including categories, releases, sources, tags, date ranges, frequency aggregation, and data transformations. | |
| DocFiller adriangonzaleziabd/mcp-server Enables generating PDFs from DOCX/ODT templates using MCP with support for OpenAI or local Ollama models. | |
| Advanced Trello MCP Server adriangrahldev/advanced-trello-mcp-server An enhanced Model Context Protocol server providing comprehensive integration between Trello and Cursor AI with 40+ tools covering multiple Trello API categories for complete project management. | |
| todo-mcp adrianhardy/todo-mcp Enables managing tasks in a structured TODO.md file through MCP tools for listing, adding, updating, setting status, logging notes, searching, and removing tasks while preserving hand-authored formatting. | |
| Codex Control Plane MCP adrianhunt04/codex-control-plane-mcp Enables MCP clients and local orchestrators to drive Codex Desktop and codex-app-server as a durable async worker: submit a task or Plan Mode workflow, immediately receive an operationId or workflowId, then poll status, answer approvals, an | |
| VMware MCP Server adrianlizman/vmware-mcp-server Enables management of VMware vCenter and ESXi environments, including VM operations, resource management, and automation with Ollama AI and n8n workflows. | |
| JakartaMigration adrianmikula/jakartamigrationmcp A Model Context Protocol (MCP) server that provides AI coding assistants with specialized tools for analyzing and migrating Java applications from Java EE 8 (javax.) to Jakarta EE 9+ (jakarta.). | |
| job-helper adrianmnd/job-helper-mcp Enables natural language management of job applications through MCP-compatible clients, including searching real job offers, creating and deleting applications, generating CVs or cover letters, and retrieving application metrics. | |
| Korean DART MCP adriannovaes27/korean-dart-mcp Enables AI assistants to query Korean DART corporate disclosures, financials, equity filings, and XBRL statements through 15 consolidated tools, including insider-trading cluster signals, accounting-risk scoring, Buffett-style quality check | |
| Nexus Intelligence MCP adriano2bx/arcturian-lattice Enables AI agents to perform company due diligence, OSINT, competitive, SEO, market, finance and regulatory research through a single MCP endpoint exposing 45 tools that draw on official public APIs, local D1 mirrors, and optional self-host | |
| pixel-mcp adrianoamaral/pixel-mcp An MCP server that enables AI coding agents to create pixel art programmatically by providing canvas manipulation tools and PNG export. | |
| opencloud-mcp adrianofoschi/opencloud-mcp Enables AI assistants to search and read the files a user can access, including full-text matches inside PDFs and office documents, through read-only MCP tools. | |
| project-bridge adrianohsnegrao/project-bridge Enables AI clients to read structured project context and propose task changes that require explicit human approval, with scoped permissions, idempotency, and a full audit trail. | |
| akahu-mcp adrianparker/akahu-mcp An MCP server exposing the Akahu banking API as tools to list accounts, get balances, and fetch transactions. | |
| SetlistMCP adrianparker/setlistmcp Enables AI assistants to search for and retrieve concert setlists from setlist.fm by artist, city, and date, and to view full setlists with songs, sets, and encores. | |
| Wisnu MCP adrianpdm/wisnu-mcp A travel booking server that enables searching for flights, hotels, and destination recommendations based on user interests and budget. It provides additional tools for calculating total trip costs and retrieving destination-specific travel | |
| Ollama MCP Server adrianpuiu/ollama-mcp-server Bridges Ollama's capabilities with MCP-compatible clients, enabling web search and content fetching to provide real-time information and reduce hallucinations. | |
| Weather-Open-Meteo-MCP adrianr84/weather-open-meteo-mcp Provides hourly and daily weather forecasts using the free Open-Meteo API without requiring an API key. | |
| Tripletex MCP Server adriantr/tripletex-mcp Enables AI assistants to interact with the Tripletex accounting API to manage time tracking, projects, and timesheet approvals through natural language. It also supports searching and managing outgoing invoices and processing supplier invoi | |
| obsidian-pkm adrianv101/obsidian-pkm-plugin This MCP server enables Claude to interact with an Obsidian vault for persistent, structured memory, providing tools for note creation, semantic search, graph traversal, and session memory. | |
| cross_yapper adrianvalentim/cross-yapper Enables Codex agents to discover projects, read existing conversation histories, and send messages to specific conversations across trusted machines using a lightweight local bridge over SSH. | |
| RLM-MCP adrianwedd/rlm-mcp Implements the Recursive Language Model pattern, enabling LLMs to process arbitrarily long contexts through session-based document management, on-demand chunking, BM25 search, and artifact storage. | |
| MCP-Discord adrianzakharov61/mcp-discord Enables AI assistants to operate a Discord bot and manage Discord servers, channels, forums, messages, reactions, webhooks, roles, and members. | |
| Taiga MCP Server adriapedralbes/mcptaiga Enables natural language interaction with Taiga project management tool to list projects, view details, and create user stories. | |
| Hiking MCP Server adriapt/hiking-mcp Allows you to search for hiking routes on Wikiloc using geographic and textual queries. | |
| JLCPCB Parts MCP Server adrie-coder/jlcpcb-parts-mcp A server that assists users in finding electronic components compatible with JLCPCB PCBA services through a searchable interface with filtering capabilities. | |
| MCP Server: Weather & Upnify Integration adrielisa/mcp Provides tools to check weather information for any city and manage prospects in Upnify CRM with dynamic authentication, eliminating the need for pre-configured credentials. | |
| Sélecteur de Codes CHATGPT adriencommery/selecteur-codes-chatgpt Provides access to 1000 ready-to-use French ChatGPT commands with keyword search, category filters, customization, and direct launch, plus OpenAI-powered image generation from a reference image with configurable roles, aspect ratios, and cr | |
| mcp-strava adrienlupo/mcp-strava Minimalist Strava integration for Claude with 7 focused tools for querying athlete stats, activities, zones, and segment analysis. | |
| ga4-viz adriennevermorel/mcp-ga4-viz Enables interactive Google Analytics 4 visualizations inside Claude conversations, supporting ad-hoc queries with line, bar, pie charts and data tables. | |
| SailPoint MCP Server (Authless) adrienricoux/sailpoint-mcp-server-authless Provides a template for deploying a remote MCP server on Cloudflare Workers without authentication, allowing customization of tools and connection to AI Playground or Claude Desktop. | |
| Obsidian MCP Server adrienthebo/obsidian-mcp Enables AI assistants to interact with local Obsidian vaults through direct filesystem access for reading, creating, and managing notes. It features high-performance SQLite indexing for fast searches, regex support, and tools for organizing | |
| Tool Box MCP Server adriftnote/tool-box-mcp Central registry for AI tools with vector search and knowledge graph, enabling intelligent tool discovery, chaining, and execution via MCP. | |
| Domoticz MCP Server adrighem/domoticz-mcp Integrates AI assistants with the Domoticz home automation system to monitor and control smart home devices, scenes, and variables. It enables users to manage device states, room configurations, and system logs through the Model Context Pro | |
| lupa11y adriiiii24/lupa11y Enables agentic accessibility auditing of a URL through a tool that runs axe-core, zoom and WCAG text-spacing checks, a keyboard-focus agent, and visual analysis, returning fixes as Markdown plus structured results. Keeps Chromium warm betw | |
| MCP Pentest adriyansyah-mf/mcp-pentest An automated penetration testing framework that enables intelligent security assessments through reconnaissance, vulnerability scanning, and controlled exploitation. Features AI-driven workflow management with comprehensive reporting for au |
23,951–24,000 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.