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 |
|---|---|
| Pommel Horse Aesthetics MCP Server dmarsters/pommel-horse-aesthetics-mcp Analyzes pommel horse gymnastics routines using a categorical aesthetics framework that evaluates element groups, spatial patterns, temporal qualities, and form with 85% deterministic taxonomy and 15% LLM synthesis. | |
| Quantum ZX-Calculus MCP Server dmarsters/quantum-zx-calculus-mcp Converts quantum circuits into ZX-diagrams using categorical quantum mechanics, enabling circuit visualization, analysis, and optimization through deterministic gate mapping and rewrite rules. | |
| Shadow Complement Integration MCP dmarsters/shadow-complement-mcp Applies Jungian shadow complement to unified composition parameters, creating psychological depth through systematic visual opposition after multi-domain blending. | |
| String Diagram Generator MCP Server dmarsters/string-diagram-mcp Generates formal string diagram visualizations of Lushy brick compositions, enabling zero-cost diagram generation and recursive self-documentation based on category theory. | |
| Wine Tasting Visual Vocabulary MCP Server dmarsters/wine_tasting_mcp Translates wine tasting vocabulary (varietal, terroir, balance, aging) into visual parameters for AI image generation, enabling sommeliers to describe wines in their native sensory language and get corresponding visual attributes for creati | |
| mcp-gateway-mcp dmartinol/mcp-gateway-mcp Admin MCP server that exposes Kubernetes CRD state and live broker status as MCP tools and a browser-renderable UI resource, enabling platform engineers to manage the mcp-gateway without kubectl. | |
| Harvest MCP Server dmarttinen/harvestmcp Integrates with Harvest time tracking to allow AI assistants to log time, view projects, manage tasks, and track work hours, with optional Azure DevOps integration for automated time logging from work items. | |
| mcflux dmayan-ss/mcp-influx1 Read-only MCP server for InfluxDB v1 that lets Claude query and explore time-series data using InfluxQL. | |
| mcp-opensearch dmayan-ss/mcp-opensearch Read-only MCP server for exploring and searching OpenSearch clusters, enabling log analysis, index exploration, and query execution. | |
| mcp-prtg dmayan-ss/mcp-prtg Enables querying sensors, devices, groups, channels, historical data, and system status from a PRTG Network Monitor instance via the classic PRTG HTTP API. | |
| Cloud.ru Sales Report MCP dmayudin/cloudru-sales-report-mcp Enables an agent to guide secure onboarding, provision required Cloud.ru resources through APIs, stage and import sales CSV data into ClickHouse, and publish and verify revenue and contribution-margin dashboards in Managed BI with cost appr | |
| BrowserCat MCP Server dmaznest/browsercat-mcp-server Provides cloud-based browser automation capabilities that allow LLMs to interact with web pages, capture screenshots, and execute JavaScript. It eliminates the need for local browser installations by leveraging BrowserCat's API for navigati | |
| ya-direct-mcp dmburov/ya-direct-mcp MCP-сервер для управления кампаниями, группами, объявлениями, ключевыми фразами и статистикой Яндекс.Директ через Claude. | |
| RHACS MCP Server dmc5179/redhat-advanced-cluster-security-mcp MCP server for the Red Hat Advanced Cluster Security for Kubernetes API, providing LLM access to all 69 API services and 361 endpoints through six meta-tools for discovery, inspection, and direct API calls. | |
| rhdp-blog-search dmc5179/redhat-blog-mcp Enables searching Red Hat Developer content such as blogs, articles, and learning paths with filters for content type, product, and topic, plus fetching full article text as clean markdown. | |
| Red Hat Security Data API MCP Server dmc5179/redhat-security-data-api-mcp Enables querying Red Hat security data including CSAF advisories, CVEs, and OVAL streams through natural language. | |
| claude-desktop-mcp dmccaffery/claude-desktop-mcp A fake MCP server with 108 themed tools for testing Claude Desktop's handling of large toolsets and Amazon Bedrock AgentCore Gateway integration. | |
| perch-agent dmcconnect/perch-agent-mcp Lets orchestrators like Claude Code and opencode hand off coding tasks to an autonomous Perch AI worker that does the work and returns verifiable evidence. Supports async job handoff with status polling and cancellation, thread continuation | |
| PasNavigator MCP dmchet/pasnavigator_mcp Enables semantic navigation and symbol lookup in Delphi/Pascal codebases, providing ranked symbol search, hierarchy exploration, and source retrieval. | |
| uv-mcp dmclain/uv-mcp Enables LLMs to manage Python environments and dependencies via uv, supporting package inspection, installation, and requirement management. | |
| dmc-sql-saglik dmcteknoloji/dmc-sql-saglik Provides read-only SQL Server health diagnostics (server health, blocking queries, missing indexes) via MCP, with a GUI installer that automatically configures AI clients like Claude Desktop. | |
| mssql-health-mcp dmcteknoloji/mssql-health-mcp Provides read-only SQL Server health and diagnostic tools using DMVs, enabling users to query server health, active queries with blocking, and missing indexes through natural language. | |
| ignitionLLens dmdufresne/ignitionllens A multi-target MCP server that gives AI clients read and, when permitted, write access to Ignition 8.3 gateways across configuration, project exports, live runtime values, and an offline Ignition reference corpus. It enables browsing, expla | |
| QuestLLens dmdufresne/questllens Gives AI agents read-only access to any QuestDB instance, enabling schema discovery, time-series querying, and monitoring of partitions, WAL state, symbols, and ingestion health through MCP. | |
| URLhaus Security Checker dmdund/dmdund-cloudflare-mcp-authless-urlhaus MCP server that checks URLs against the URLhaus malware database to identify malicious URLs. | |
| Google Sheets MCP Server dmegabyte/google-sheets-mcp Enables Claude to read, write, append, and clear data in Google Sheets directly using a Google Cloud Service Account. It provides tools for real-time spreadsheet interaction, including fetching sheet metadata and managing cell ranges throug | |
| nextdns-mcp dmeiser/nextdns-mcp Enables AI assistants to manage NextDNS profiles, settings, logs, analytics, and security configurations through 70+ operations via the Model Context Protocol. | |
| tesserae-mcp dmellok/tesserae-mcp Enables AI agents to build freeform dashboards for e-ink panels by listing widgets and devices, laying out a canvas, rendering a preview, and pushing to the panel. | |
| PlayCanvas Editor MCP Server dmendoza9395/editor-mcp-server Enables AI agents to automate the PlayCanvas Editor across projects, entities, assets, scripts, scenes, builds, and runtime operations, including launching scenes to verify they actually run via screenshots and logs. | |
| lexoffice-mcp dmesh-io/lexoffice-mcp Enables users to create draft or finalized invoices in Lexware Office, look up contacts, and retrieve invoice details through natural language, with support for line items, tax types, payment terms, and deep links. | |
| DM Faster MCP Server dmfaster/agents Exposes seven read-only tools for sales engagement data from DM Faster, enabling agents to query workspace briefings, campaigns, sendings, replies, pipelines, and company timelines. | |
| Mother MCP Skills dmgrok/mcp_mother_skills Automatically discovers and installs AI skills for your project's tech stack, supporting Claude, Copilot, Codex, and other MCP-compatible agents. | |
| tezos-mcp dmichael/tezos-mcp RAG-powered MCP server that indexes and searches Tezos protocol specs, TZIPs, and Octez source code, enabling semantic search and expert guidance on Tezos topics. | |
| usb-relay dmikushin/attiny_relay2 MCP server for controlling ATtiny85 USB relay devices via serial break signals. Enables listing, turning on/off, and renaming relays. | |
| orca-slicer-mcp dmikushin/orca-slicer-mcp An MCP server that drives OrcaSlicer headlessly on a virtual display, enabling an agent to import 3D models, slice them, and export G-code without a physical screen or GUI automation. | |
| swiss-qr-bill-mcp dmikushin/swiss_qr_payment Enables AI agents to generate, validate, decode, and verify Swiss QR payment slips, with all file writes confined to a specified output directory. | |
| OCP Viewer MCP Server dmilad/ocp-viewer-mcp Enables AI assistants to capture screenshots from the OCP CAD Viewer, allowing visual analysis and feedback on 3D CAD models created with CadQuery or Build123d. | |
| Amazon Leadership Principles MCP Server dminhk/amazon-lp-mcp-server Serves as a Model Context Protocol server that provides tools to look up Amazon Leadership Principles and access video transcripts for integration with Amazon Q CLI. | |
| Dmint MCP Proxy dmint-app/dmint-mcp Enables developers to wrap existing MCP servers with a deterministic policy enforcement gate that intercepts tool discovery and tools/call requests over stdio, allowing only authorized calls to reach the downstream server. It supports dynam | |
| Firefly III MCP Server dmitos/firefly-iii-mcp Enables interaction with Firefly III personal finance management instances via the Firefly III API, deployed as a Cloudflare Worker. It allows AI tools to manage transactions, accounts, budgets, and reporting through natural language. | |
| telegram-mcp-server dmitrii-ive/claude-telegram-mcp A read-only MCP server that lets AI agents read personal Telegram chats from an allowlist of folders, with no send/edit/delete capability. | |
| article-scraper-mcp dmitriiweb/article-scraper-mcp Enables fetching and parsing news articles from URLs, extracting title, text, author, and publication date. | |
| mcp-db-analyzer dmitriusan/mcp-db-analyzer A Model Context Protocol (MCP) server that gives AI assistants deep visibility into databases, inspecting schemas, detecting index problems, analyzing table bloat, and explaining query plans across PostgreSQL, MySQL, and SQLite. | |
| MCP Java Backend Suite dmitriusan/mcp-java-backend-suite A comprehensive MCP toolkit for Java backend developers, providing 35 tools across 5 servers for database analysis, JVM diagnostics, migration assistance, Spring Boot monitoring, and Redis diagnostics. | |
| mcp-jvm-diagnostics dmitriusan/mcp-jvm-diagnostics Enables AI assistants to analyze JVM thread dumps and GC logs, detecting deadlocks, lock contention, and GC pressure, without requiring a JVM runtime. | |
| MCP Migration Advisor dmitriusan/mcp-migration-advisor Analyzes database migrations for risks like lock contention and data loss before they run. Supports Flyway and Liquibase formats, providing risk scores and rollback generation. | |
| mcp-redis-diagnostics dmitriusan/mcp-redis-diagnostics A lightweight npm MCP server for deep Redis diagnostics, offering tools for memory, slowlog, clients, keyspace, latency, and config analysis with AI-powered recommendations. | |
| mcp-youtube-intelligence dmitriusan/mcp-youtube-intelligence MCP server for extracting structured intelligence from YouTube channels and videos — transcripts, topics, and competitive signals for AI-powered research workflows. | |
| MCP Vault dmitriy-lyakhov/termix-plugin-mcp-vault Turns a Termix server into a remote MCP endpoint where Claude Desktop and other clients can sign in with an API key to access hosts, a vault of logins, passwords, API keys, notes, TOTP codes, and integrations with monitoring, ticketing, and | |
| Sales Analysis MCP Server dmitriy-shtefan/fast-mcp-demo Enables sales data analysis from CSV files using MCP tools, resources, and prompts, including metrics like revenue, profit, top products, and monthly trends. |
45,151–45,200 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.