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 |
|---|---|
| LLM Pricing Scraper MCP Server alexis-htc/mcp Enables scraping and comparison of LLM inference pricing from multiple providers like Cloudrift, DeepInfra, Fireworks, and Groq, storing results in a SQLite database. | |
| Agentdocs alexis81790/python-mcp-server-client Enables users to search and retrieve current technical documentation for mainstream agent frameworks such as LangChain, LlamaIndex, AutoGen, Agno, OpenAI Agents SDK, MCP, Camel AI, and CrewAI through Google search and web scraping, using st | |
| hevy-mcp alexisb1988/hevy-mcp Enables AI assistants to read, analyze, create, and update Hevy workout data, including workouts, routines, exercises, and body measurements, through the Model Context Protocol. | |
| Cinema4D MCP Server alexisb39931/cinema4d-mcp Enables Claude to perform prompt-driven 3D modeling, scene creation, and manipulation in Cinema 4D, with tools for objects, materials, lighting, cameras, MoGraph, dynamics, and rendering. | |
| Roundtable AI MCP Server alexisbayrak023/roundtable Enables a primary AI coding assistant to delegate work in parallel to multiple specialized AI CLI tools (Gemini, Claude, Codex, Cursor) sharing the same project context, then aggregates their findings into a single synthesized response. Run | |
| fitness-mcp alexisdechiara/fitness-mcp Read-only MCP server aggregating Lyfta workouts, Yazio nutrition, and weight data. Exposes tools for querying workouts, nutrition summaries, and fitness analytics to AI clients. | |
| ScrapeGraph MCP Server alexisfujita78/scrapegraph-mcp Enables language models to perform AI-powered web scraping, structured extraction, web search, crawling, schema generation, and scheduled monitoring through an API integration. | |
| Gmail MCP Server alexisg1993/mcp_gmail Enables AI agents to search, read, and draft replies to Gmail messages and threads using least-privilege OAuth access, while never sending, deleting, labeling, or archiving mail. | |
| Task Board MCP Server alexisinwork/mcp A task-board MCP server that provides tools to search, create, and update tasks, resources for reading the board, and prompts for standup and triage workflows. | |
| Deep Code Reasoning MCP Server alexisivanov43287/deep-code-reasoning-mcp Enables Claude Code to escalate complex code analysis to Google's Gemini AI, supporting large-context debugging, execution-flow tracing, cross-system impact analysis, performance bottleneck detection, and hypothesis testing through multi-tu | |
| point-by-point alexisjamet/point-by-point Enables users to annotate individual sentences or selected passages of Claude's responses in an inline interface and send all their replies and questions back in a single message. Claude then answers each point in turn. | |
| ProxyPI alexislspk/proxypi-mcp Self-healing API proxy MCP that sends REST requests, diagnoses failures using Claude, patches requests, and retries. Successful fixes are remembered for instant reuse. | |
| HubSpot MCP Server alexism8877/mcp-hubspot Enables AI assistants to interact with HubSpot CRM data, including creating and searching contacts and companies, retrieving activity and conversations, and using vector storage for semantic search across prior interactions. | |
| DB2ST MCP alexismarasigan/db2st-mcp A horizontally scalable Model Context Protocol server for exposing shipment tracking (and other data sources) as authenticated MCP tools, starting with DB Schenker's public tracking endpoint. | |
| Oh My Cassette alexismulder51/oh-my-cassette A local MCP server that turns natural-language chat in Claude Code, Codex, Hermes, or OpenCode into finished montage video edits. It analyzes uploaded raw clips, performs shot selection, beat-synced cuts, music matching, subtitles, transiti | |
| Gate22 alexisokada98085/gate22 Enables teams to govern which tools agents can use by onboarding remote MCP servers with function-level allow-lists and org-shared or per-user credentials, then exposing permitted tools through a single unified endpoint with just search and | |
| Atrio MCP Server alexisvieto/atrio-mcp-sample A read-only Model Context Protocol server that lets an AI agent answer questions about unit balances, overdue fees and common-area bookings for the signed-in user. Row Level Security and a read-only database role scope every answer to that | |
| flompt alexiswatanabe66/flompt Enables users to decompose raw prompts into structured typed blocks and compile them into Claude-optimized XML prompts through MCP tools, with block type listing for manual crafting. | |
| LunchMoney MCP Server alexiswatanabe66/lunchmoney-mcp Enables AI assistants and other MCP clients to read and manage personal finance data through LunchMoney's API v2, covering transactions, categories, tags, budgets, recurring items, manual and Plaid accounts, crypto holdings, and balance his | |
| IDA Pro MCP Server alexisy5758/mcp-server-idapro Enables AI assistants to automate reverse engineering and binary analysis by running scripts, retrieving metadata, searching values, text, and byte sequences, and reading disassembly. | |
| my-kb alexiuhubhiu/my-kb Enables agents to search a local, fully offline personal document library (Markdown/txt/PDF/docx) via SQLite FTS5 trigram search with subject-terminology expansion, returning every hit with its domain, document title, section path, and page | |
| dify-mcp alexjiaguo/dify-mcp A comprehensive MCP server and CLI that exposes the entire Dify console API as 138 tools, enabling AI agents to programmatically build, test, and publish Dify workflows and manage all aspects of the Dify platform. | |
| gopro2cloud alexjiaguo/unicloud Enables AI assistants to discover connected GoPro cameras and stream or sync videos directly to cloud storage such as Google Drive, Dropbox, OneDrive, or S3 with zero local disk usage. | |
| receipts alexjpower74-create/receipts Enables any agent to query the same interview corpus as the UI over stdio, exposing tools to list transcripts, search quoted lines, retrieve verified themes with citations and dropped reasons, and fetch source lines. | |
| Synapse alexjsmith0115/synapps Synapse indexes C# codebases into a FalkorDB-backed graph to provide deep structural insights including inheritance, interface implementations, and call chains. It enables AI assistants to query code architecture and navigate symbol relatio | |
| publer-mcp-server alexkess/publer-mcp-server MCP server for Publer social media management API, enabling AI assistants to schedule posts, upload media, pull analytics, and manage accounts across 15+ social networks. | |
| bot2bot-mcp alexkirienko/bot2bot-chat MCP server for end-to-end encrypted multi-agent chat rooms, enabling turn-based hosts like Codex and Claude Code to claim, process, and acknowledge tasks. | |
| GitHub MCP Server alexkissijr/unreal-mcp-server Enables comprehensive interaction with the GitHub API, including file operations, repository management, issue tracking, pull request workflows, and advanced search functionality across code, issues, and users. | |
| NetBox MCP Server - Read & Write Edition alexkiwi1/netbox-mcp-rw Enables comprehensive interaction with NetBox infrastructure management through both read and write operations. Supports full CRUD operations for devices, IP addresses, sites, racks, and other NetBox objects through natural language command | |
| Guardia MCP Server alexlaguardia/guardia-mcp A production Model Context Protocol (MCP) server with 70+ tools, OAuth 2.1 authentication, and frame-based tool filtering. | |
| mcp-activecampaign alexlaguardia/mcp-activecampaign Enables AI assistants to manage ActiveCampaign CRM, marketing automation, and contact data via 33 tools including contacts, deals, tags, automations, pipelines, custom fields, campaigns, accounts, and webhooks. | |
| mcp-freshbooks alexlaguardia/mcp-freshbooks Production-grade MCP server for FreshBooks. 25 tools for invoices, clients, expenses, payments, time tracking, projects, estimates, and financial reports. OAuth2 with automatic token refresh. | |
| Mailchimp MCP Server alexlaguardia/mcp-mailchimp A production-grade MCP server that integrates with the Mailchimp Marketing API to manage campaigns, audiences, members, and reports. It provides 28 specialized tools for automating marketing tasks such as sending emails, managing subscriber | |
| WooCommerce MCP Server alexlaguardia/mcp-woocommerce A production-grade MCP server for the WooCommerce REST API, enabling AI assistants to manage products, orders, customers, and store settings. | |
| ToolBridge alexlaguardia/toolbridge-demo A governed MCP server for integrating AI agents with customer data, featuring role-based access control, field redaction, and human-in-the-loop approval for secure support operations. | |
| Vigil alexlaguardia/vigil MCPWatch: observability for MCP servers. One line instruments any Python MCP server (FastMCP and the low-level Server) and tracks per-tool latency (p50/p95/p99), error rates, silent failures (empty/null returns and isError), and call volume | |
| Warden alexlaguardia/warden A governed MCP server enforcing RBAC outside the model, with OpenTelemetry traces on every run and an LLM-as-judge eval suite proving the agent stays inside policy. | |
| Bots alexlayton/herdr-bots Lets coding agents running in herdr panes discover one another, exchange messages, and delegate tasks, with idle agents prompted automatically when work arrives. | |
| MarketIntel MCP Server alexlcortes/mcp-server-demo-marketintel Enables AI chat clients to perform market research and competitive intelligence by gathering company overviews, competitor lists, product portfolios, pricing snapshots, and recent news via live Tavily search. | |
| Concierge MCP Server alexlenk/ha-concierge-mcp Exposes a curated allowlist of Home Assistant entities to external clients over MCP with read-only list and get_state tools, using an isolated guest credential that cannot access other Home Assistant APIs. | |
| ha-dev-tools-mcp alexlenk/ha-dev-tools-mcp Comprehensive development tools for Home Assistant, enabling file management, template testing, entity/state management, service calls, log access, and system information retrieval through MCP. | |
| Marketo MCP Server alexleventer/marketo-mcp A Model Context Protocol server for interacting with the Marketo API that provides tools for managing Marketo forms, including listing, cloning, and approving forms. | |
| sionna-mcp alexli18/sionna-mcp Exposes NVIDIA Sionna RT ray-tracing as 15 structured tools for AI agents, enabling wireless channel simulation (scene loading, antenna array setup, ray tracing, CSI extraction) through MCP. | |
| arr-doctor alexliam83/arr-doctor Enables Claude and other MCP clients to query, troubleshoot, and manage Sonarr, Radarr, and Prowlarr, including guided diagnostics, safe maintenance, and bulk actions with good-practice guardrails. | |
| Smithsonian MCP Server alexlin1234/smithsonian-mcp-server Enables searching and exploring millions of items from the Smithsonian Institution's collections including artifacts, artworks, specimens, photographs, and more, using the Smithsonian Open Access API. | |
| Weather MCP alexliu13483/weather_mcp Enables weather data retrieval and visualization with support for geocoding, multi-day forecasts, historical weather queries, and natural language processing through LangChain integration. Supports both current and historical weather data w | |
| minimax-image-mcp alexlivre/minimax-image-mcp Enables image generation via MiniMax's API through MCP, supporting text-to-image, batch generation, aspect ratios, seed reproducibility, and image-to-image with character references. | |
| macOS MCP Server alexlock1/macos-mcp Enables interaction with macOS system features including file dialogs, clipboard management, Finder integration, and system notifications. It also provides tools for taking screenshots, processing images, managing PDFs, and interacting with | |
| MCP DSFR alexmacapple/mcp-playbook-dsfr Generates, validates, and audits French government DSFR components with RGAA 4.1 accessibility compliance, enabling seamless integration into Claude Desktop. | |
| pdf-reporter-mcp alexmakeev/pdf-reporter-mcp MCP server for rendering Mermaid diagrams to SVG and converting Markdown with callout blocks into styled PDF reports. |
26,301–26,350 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.