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 |
|---|---|
| Heroku MCP Tool Search Server dsouza-anush/mcp-tool-search Enables dynamic tool discovery and loading for Claude using BM25, regex, and semantic search algorithms. It supports managing a catalog of over 10,000 tools with minimal context overhead and provides a REST API for tool management. | |
| Zendesk MCP Server for Heroku dsouza-anush/mcp-zendesk Enables interaction with Zendesk Support for managing tickets, comments, and filtering via the Model Context Protocol. It allows LLMs to perform actions like creating, updating, and listing support tickets through natural language in a Hero | |
| Playwright MCP (Heroku) dsouza-anush/playwright-mcp-heroku Enables AI models to interact with web pages through structured accessibility snapshots using Playwright. Deployable on Heroku for easy cloud hosting. | |
| Zapmail MCP Server dsouzaalan/zapmail-mcp Enables AI assistants to interact with the Zapmail API through natural language commands for domain management, mailbox operations, and exports to third-party platforms like Reachinbox and Instantly. Provides complete coverage of 46+ Zapmai | |
| datacloud-code-mcp dsouzaanush/datacloud-code-mcp A Salesforce Data Cloud MCP server using Cloudflare Code Mode, enabling agents to discover and execute Data Cloud operations via a two-step search-and-execute loop with JavaScript code. | |
| MuleSoft Code MCP dsouzaanush/mulesoft-code-mcp Remote MCP server for MuleSoft APIs that enables agents to discover operations and execute validated API calls with a fixed low-context tool surface. | |
| slack-code-mcp dsouzaanush/slack-code-mcp A focused remote MCP server that enables LLMs to search and execute Slack Web API operations with OAuth and write guardrails. | |
| Auth0 MCP Server dsoziev1/deepseek-cli-day-16 MCP server that provides access to Auth0 Management API v2, offering read-only tools grouped by categories for querying Auth0 resources. | |
| Auth0 MCP Server dsoziev1/deepseek-cli-day-17 An MCP server that provides tools to read and modify Auth0 configurations via the Auth0 Management API v2, including write instruments for creation and updates but no deletion. | |
| Auth0 User Monitor MCP Server dsoziev1/deepseek-cli-day-18 Enables monitoring Auth0 users by collecting summaries, storing reports in SQLite, and auto-blocking suspicious admins, all through MCP tools without an LLM. | |
| Auth0 User Monitor dsoziev1/deepseek-cli-day-18-1 A scheduled MCP server that monitors Auth0 users by periodically collecting summaries, detecting suspicious admins, and auto-blocking them; it provides instant reports via SQLite and exposes tools for on-demand collection and configuration. | |
| Ticket Support MCP Server dsoziev1/deepseek-cli-day-33 Enables retrieval of support tickets and user data from a JSON store or ServiceNow via MCP tools, providing context for AI-powered support responses. | |
| steam dsp/mcp-server-steam Provide information about the games you played and how long you played them for to an LLM | |
| openapi2mcp dspachos/openapi2mcp An MCP server that exposes any OpenAPI REST API via two tools: search for discovering endpoints and execute for making API calls. It uses Code Mode to keep token footprint low and runs user-written JavaScript in a sandbox. | |
| MCP Chat dspenard/claude_mcp_chat_cli MCP Chat is a CLI application that enables interactive chat with AI models via the Anthropic API, supporting document retrieval, command-based prompts, and extensible MCP tool integrations. | |
| Lanhu MCP Server dsphper/lanhu-mcp Connects AI assistants to Lanhu design collaboration platform for analyzing Axure prototypes, downloading UI designs, and enabling team knowledge sharing through a collaborative message board that breaks AI IDE silos. | |
| claude-halopsa-mcp dspray/claude-halopsa-mcp Enables Claude to interact with HaloPSA by authenticating via Azure CLI and fetching OAuth secrets from Azure Key Vault at runtime. | |
| bizdata-mcp dsr-cyber/mcp-business-data Enables Claude to answer questions about a small business's own data by providing predefined sales, customer, refund, and inventory tools, plus a guarded read-only SQL query tool with audit logging. | |
| Dsrupt After Effects MCP dsrupt-technologies/dsrupt-after-effects-mcp Enables AI agents to connect to Adobe After Effects locally, inspecting projects, comps, and layers, discovering and executing a catalog of operations, rendering frames, and saving projects, with on-demand skill-based guidance. | |
| invoice-ninja-mcp dss-ai/invoice-ninja-mcp Enables MCP clients like Claude Desktop to interact with Invoice Ninja v5, providing tools to read and write contacts, customers, quotes, projects, products, and optionally invoices, with configurable permissions. | |
| Obsidian Tasks MCP Server dss99911/obsidian-tasks-mcp Enables AI assistants to manage Obsidian tasks with full CRUD operations, querying, and date-based filtering via MCP. | |
| Gemini Bridge dssbdev/gemini-bridge Enables Claude clients to delegate tasks such as web research with sources, reading PDFs, audio, video, images and web pages, image generation, and second opinions to Gemini running under a Google AI Pro subscription via the official Antigr | |
| whoop-mcp-resilient dssolutions-mx/whoop-mcp-resilient Enables read-only access to WHOOP health data through MCP clients, including recovery, HRV, sleep, strain, workouts, cycles, trends, and period comparisons, with resilient handling of outages, token refresh, and natural-language dates. | |
| Game Boy MCP Player dst0rtr/pokemon-ai-player Lets AI agents play Game Boy games via PyBoy with efficient button scripts, high-level Pokémon helpers, and automatic benchmark metrics. | |
| KNMI MCP Server dstotijn/knmi-mcp Provides access to Dutch weather data (current conditions, forecasts, alerts, and historical data) via the KNMI API, with automatic location name resolution for Dutch cities. | |
| ms-sentinel-mcp-server dstreefkerk/ms-sentinel-mcp-server MCP server for Microsoft Sentinel. Enables access to Sentinel logs, incidents, analytics, and Entra ID data via a modular, queryable interface. Strictly non-production. Designed for use with Claude and other LLMs. | |
| cs20-lidar dstrout/cs20-lidar-mcp Enables an LLM to take its own depth measurements from a Synexens CS20 solid-state ToF lidar, returning false-color images, point clouds, distance readings, settings control, and per-capture quality verdicts. | |
| weeek-mcp dsudomoin/weeek-mcp Enables Claude Code and OpenAI Codex to interact with the Weeek task tracker through natural language, covering task creation, searching, updating, moving, completing, commenting, and file attachments via thirteen curated tools. | |
| loci dsundberg272/loci Enables AI clients to search and ask questions across local notes and docs with hybrid retrieval, section-level citations, and shared durable memory; also exposes note resources and prompts for briefing, study planning, and contradiction ch | |
| NetSuite MCP Server dsvantien/netsuite-mcp-server A Model Context Protocol (MCP) server providing access to NetSuite data through OAuth 2.0 with PKCE authentication. Works seamlessly with any MCP-compatible client including Claude Code, Cursor IDE, and Gemini CLI. | |
| tif-score-mcp dsvxmedia/tif-score-mcp An MCP server that exposes three tools to analyze call transcripts for business intelligence, score leads 0-100 with hot/warm/cold classification, and diagnose n8n workflow errors with root cause analysis and proposed fixes. | |
| warden dsvxmedia/warden A sandboxed MCP server that executes shell commands inside ephemeral, locked-down Docker containers with no network by default, dropped capabilities, and an audit log, enabling secure agent-driven command execution. | |
| Digital Brain MCP dswillden/digital-brain-mcp A persistent long-term memory system that enables AI clients to store and recall notes, code, and research via semantic search. It utilizes Google Gemini embeddings and Supabase pgvector to provide a secure, searchable 'Second Brain' for MC | |
| LLM Python Code Sandbox dsxiangli/simple_sandbox Enables LLMs to execute Python code in isolated sandboxes with file operations and MCP integration, supporting multi-round execution and plot capture. | |
| pi-controller-mcp dsyorkd/pi-controller-mcp MCP server for managing Raspberry Pi K3s clusters via AI assistants like Claude Code. | |
| Project Manager MCP dtannen/pm Enables AI agents to manage projects, epics, and tasks with atomic locking, real-time dashboard, and multi-agent coordination. | |
| gmail-multi-mcp dtaveeva/gmail-multi-mcp MCP server that gives an AI assistant simultaneous access to multiple Gmail accounts with per-account read-only, draft, or send tiers, two-phase write confirmation, and safeguards for handling untrusted email content. | |
| OAuth 2.1 MCP Server dteam-top/mcp-oauth A Next.js-based MCP server template that implements OAuth 2.1 authentication with support for both SSE and Streamable HTTP transports. Provides a reference implementation for building authenticated MCP servers that work with Claude, Cursor, | |
| brain2 dtehan/second-brain A database-first personal knowledge management system powered by a local MCP server, providing 29 tools to manage and search structured knowledge (meetings, emails, people, accounts, projects, todos, etc.) via a single SQLite file. | |
| dtelecom-stt dtelecom/stt-mcp Enables AI assistants to transcribe audio files using dTelecom's real-time speech-to-text with pay-per-use USDC micropayments, no API keys required. | |
| infra-mcp dtg404/infra-mcp MCP server that gives Claude Code real-time visibility into local infrastructure — Docker containers and system health. | |
| nexus-mcp dtg404/nexus-mcp MCP server that wraps the nexus CLI, giving AI agents cross-session memory, semantic search, preference learning, and smart context injection. | |
| ollama-mcp dtg404/ollama-mcp A VRAM-aware MCP server that offloads token-heavy development tasks to local Ollama models, saving API tokens for complex reasoning. | |
| crtsh-mcp dthen/crtsh-mcp Enables certificate transparency log search via crt.sh, allowing users to query SSL/TLS certificates, enumerate subdomains, and retrieve certificate details with no API key required. | |
| iFixit MCP Server dthen/ifixit-mcp Provides read-only access to iFixit repair guides, device information, repairability scores, categories, search, media, and contributor profiles via MCP tools. | |
| internet-archive-mcp dthen/internet-archive-mcp Full-coverage MCP server for Internet Archive, enabling search, metadata lookup, collection browsing, and Wayback Machine snapshot retrieval via 13 tools. | |
| listenbrainz-mcp dthen/listenbrainz-mcp Enables interaction with the full public ListenBrainz API, exposing 37 tools for listens, stats, playlists, radio, social, and cover art over stdio. | |
| Nager.Date MCP Server dthen/nager-date-mcp Provides public holidays, long weekends, and country data for 202 countries via the Nager.Date API, with client-side filtering and timezone-aware checks. | |
| trove-scot-mcp dthen/trove-scot-mcp MCP server for Scotland's historic environment, providing tools to search, filter, count, and locate heritage sites, listed buildings, scheduled monuments, and properties in care using Historic Environment Scotland's open ArcGIS API. Suppor | |
| xhs-image-mcp dthinkr/xhs-image-mcp Converts text or markdown into Xiaohongshu (Little Red Book) style image cards with AI cover generation, supporting multiple themes and aspect ratios. |
46,201–46,250 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.