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 |
|---|---|
| ADT Security MCP Server cavanaugh-design-studio/adt-security-mcp Enables control and monitoring of an ADT Control / Alarm.com security system from MCP-compatible hosts, including checking system and device state, reviewing activity, and safely arming, disarming, locking, or adjusting devices through conf | |
| REA cavanaugh-design-studio/rea-mcp-app Enables agents to reverse-engineer software across native binaries, managed code, Electron apps, websites, and live runtime behavior, returning findings linked to the evidence and limitations behind each conclusion. It also maintains a dura | |
| RhymeBook cavanaughdesign/rhymebook-mcp-server An AI-powered creative studio for writing lyrics, finding beats, and tracking recording sessions, integrating with AI assistants via the Model Context Protocol. | |
| doorvault-mcp cavasotti/doorvault-mcp Enables AI assistants to analyze rental property deals using DoorVault IDEAL Scoring v2.0, including Section 8 FMR lookup, tax deduction checklists, and rental metrics calculations. | |
| ableton-mcp cavi-ai/ableton-mcp Enables local-first Ableton Live control for MCP clients, with guarded confirm-to-execute mutations. | |
| TallyPrime MCP cavishal04/tallyprime-mcp Read-only MCP server that lets AI assistants query a locally running TallyPrime installation through its HTTP-XML gateway, exposing companies, ledgers, vouchers, trial balance, P&L, balance sheet, receivables, payables, and stock reports as | |
| mcp-uk-tools cavitnation/mcp-uk-tools Enables MCP-compatible AI clients to look up UK postcode details, find nearest postcodes by coordinates, and retrieve upcoming bank holidays through keyless public APIs. | |
| Jules MCP Server cavuminfundo/julius-hub Provides an enterprise-ready bridge for AI agents to inspect, mentor, plan, and automate Google Jules AI execution sessions via HTTP, SSE, or Stdio transport. | |
| ax-mcp cawa0505/ax-mcp MCP server for remote web scraping, providing a scrape_web tool that fetches pages and extracts content as markdown or JSON, supporting CSS selectors. | |
| WHOOP MCP Server caxtmann/whoop-mcp A multi-user MCP server that exposes WHOOP fitness data (recovery, sleep, workouts, cycles, profile, body measurements) to AI clients. Each user connects their own WHOOP account via OAuth and only sees their own data, which is fetched live | |
| service-bridge-mcp cayde-6/service-bridge-mcp Enables agents to read, create, and modify invitations for calendar events through a deny-by-default broker that validates OAuth bearer tokens and intersects server-owned per-subject, per-calendar grants with token scopes. Access is limited | |
| Gerrit Review MCP Server cayirtepeomer/gerrit-code-review-mcp Provides integration with Gerrit code review system, allowing AI assistants to fetch change details and compare patchset differences for code reviews. | |
| HWP-MCP cayson-choi/hwp-mcp An MCP server that enables AI models to control Hancom Office Hanword (HWP) documents on Windows. It allows for the automated creation, editing, and management of Korean word processor files, including text formatting and table manipulation | |
| Twisted Nail MCP Server cba70118/twistednail-mcp Enables AI assistants to query Twisted Nail's services, materials, service area, and FAQs for aggregate supply and hauling. | |
| Nextcloud MCP Server cbcoutinho/nextcloud-mcp-server Connects AI assistants to Nextcloud instances with 90+ tools for managing notes, calendars, contacts, files, recipes, and more through natural language conversations. Supports semantic search and multiple deployment options. | |
| Whoop MCP Server cbellbell-spin/whoop-mcp Exposes Whoop fitness data (recovery, sleep, strain, workouts) to Claude for use as a daily training coach, enabling natural language queries about your health metrics and training readiness. | |
| Ascend MCP Server cben0ist/ascend-mcp Connects Claude to Ascend job search data, providing read-only access to job applications, resume, dashboard stats, and analytics. | |
| talos-mcp-server cbepx/talos-mcp-server MCP server that enables interaction with Talos Linux clusters via gRPC API, supporting cluster management, monitoring, configuration, and resource inspection. | |
| rtl-mcp-agent cbfaf/rtl-mcp-agent Enables AI assistants to analyze RTL simulation and synthesis logs through deterministic tools for compile-log summaries, signal tie-off safety checks, and regression result statistics. | |
| stardew-mcp cbhl/farming-game-mcp Exposes the Stardew Valley Wiki as structured data via MCP tools for keyword/semantic search, page retrieval, and entity listings. | |
| paperless-mcp-go cbinckly/paperless-mcp-go Search, read, (bulk) edit the documents and metadata in your Paperless NGX instance. | |
| CB Insights MCP Server cbinsights/cbi-mcp-server An interface that allows developers to interact with ChatCBI LLM through AI Agents, providing access to CB Insights' conversational AI capabilities. | |
| local-policy-mcp cbjworld/local-policy-mcp Enables users to search Korean local government project, plan, and budget documents through AI apps, compare cases across municipalities, and check planning, budget, and support conditions against original-source citations. | |
| twingate-mcp cblack34/twingate-mcp Enables MCP clients to query a Twingate network in read-only fashion for users, groups, resources, remote networks, connectors, devices, and access relationships. | |
| Chris MCP cblanquera/mcp A context provider that serves as an AI version of Chris's programming knowledge and practices. Enables AI utilities like Claude and Cline to search and access coding guidelines, rules, and context for JavaScript, TypeScript, React, and var | |
| US Government Data cblu2005/us-govdata-mcp Search official US government data from any MCP client: building permits from 10 city open-data portals, federal contract opportunities from SAM.gov with contracting-officer contacts, and the CMS NPI healthcare-provider registry. Open-sourc | |
| life-agent-mcp cbolden15/life-agent-mcp Enables turning any personal-assistant REST backend into Claude-ready tools via a single MCP server, providing 38 tools for communications, finance, health, and more. | |
| Hevy MCP Pro cbotworks/mcp-hevy-pro A production-ready MCP server for the Hevy fitness API that exposes 27 tools for reading, writing, and analyzing workout data, enabling LLM-driven personal trainer workflows. | |
| constructionclock-mcp cbourgeois-design/constructionclock-mcp Enables Claude Desktop to add and edit ConstructionClock time entries directly through the ConstructionClock REST API. | |
| Statamic MCP Server cboxdk/statamic-mcp Enables AI assistants to manage Statamic CMS content, including blueprints, entries, assets, users, and system operations, through a secure, router-based MCP endpoint. | |
| FS_MCP_thin cbreland-dlr/fs_mcp_thin A read-only MCP server that connects AI assistants to Freshservice Service Desk for ticket triage, asset analysis, and support history summarization. | |
| 20i MCP Server cbrown35/20i-mcp Enables natural language management of 20i web hosting services, including domains, databases, email, WordPress, and more, through AI assistants like Claude and ChatGPT. | |
| Mautic MCP Server cbrown35/mantic-mcp Enables comprehensive integration with Mautic marketing automation platform, providing contact management, campaign automation, email operations, form management, analytics, and content management through natural language commands. | |
| MCP Tasks Organizer cbruyndoncx/mcp-tasks-organizer Converts Cursor agent plans into structured markdown task lists and organizes them in your repository. | |
| ThirdBrain skills-mcp cbruyndoncx/thirdbrain-skills-mcp Enables MCP hosts to discover, browse, and load Agent Skills from one or many SKILL.md libraries over the Model Context Protocol, with namespaced libraries, search/list/get tools, progressive disclosure, and a digest-verified pull client fo | |
| paperless-ngx-mcp cbsmiley/paperless-ngx-mcp-server Enables Claude AI to interact with Paperless-NGX document management through natural language, offering 50 tools for full CRUD operations and management. | |
| gigai-tools-mcp cbsshekhawat18-lab/gigai-tools-mcp Enables AI agents to perform file operations through the GigAI Tools API, such as merging PDFs, converting and compressing images, extracting PDF text, and generating QR codes, with results saved locally and tools synced from the live API c | |
| qdrant-loader-mcp-server cbtw-apac/qdrant-loader Enables AI development tools to perform semantic search and document relationship analysis on vectorized content stored in Qdrant databases. | |
| Frank MCP Server cbuckley-code/frank-mcp-server An MCP server that provides typed, audited, least-privilege tools for monitoring AWS infrastructure and GitHub pipelines, including instance health, service status, logs, deployment status, CI workflow runs, failed jobs, and PR checks. | |
| Quotations MCP Server cbunny-2005/mcp_drivetech A read-only MCP server that provides conversational querying of quotations data (counts, values, lookups) via tools like quotation_stats, search_quotations, and find_by_number. | |
| Kiro MCP Memory cbunting99/enhanced-mcp-memory An enhanced MCP server that provides intelligent memory and task management for AI assistants, featuring semantic search, automatic task extraction, and knowledge graphs to help manage development workflows. | |
| MCP Code Analysis & Quality Server cbunting99/mcp-code-analysis-server Provides comprehensive code analysis through three MCP servers: static analysis for code quality and security, dependency analysis for package management and vulnerabilities, and complexity analysis for maintainability assessment across mul | |
| Claude Memory MCP Server cbuntingde/claude-memory Enterprise-grade MCP server for persistent, intelligent memory management across Claude Code sessions. | |
| CodeWiki MCP Server cbuntingde/codewiki-mcp-server Integrates with Google CodeWiki to search, fetch, and cache documentation for GitHub repositories, enabling easy access to repository documentation through natural language queries. | |
| enhanced-mcp-memory cbuntingde/enhanced-mcp-memory An MCP server for intelligent memory and task management with semantic search, automatic task extraction, and knowledge graphs, enabling AI assistants to maintain context and learn project conventions. | |
| enhx-memory cbuntingde/enhx-memory A persistent, project-scoped memory layer for AI coding agents, providing 39 tools for capturing, searching, deduplicating, relating, and maintaining memory records across long-running coding sessions. | |
| kimi-memory cbuntingde/kimi-memory Provides a local-first persistent memory layer for coding assistants, enabling cross-project user preferences, per-project durable and working memory, session archives, and reflective recommendations through MCP tools. | |
| leak-secure-mcp cbuntingde/leak-secure-mcp Enterprise-grade MCP (Model Context Protocol) server for detecting secrets and sensitive information in GitHub repositories. Scans for 35+ types of secrets including API keys, passwords, tokens, and credentials with production-ready reliabi | |
| Magic MCP Local cbuntingde/magic-mcp-local A local-first MCP server for generating production-ready React UI components entirely offline without requiring API keys or configuration. It provides tools to search, list, and create over 30 types of components including buttons, forms, a | |
| Memory MCP Server cbuntingde/memory-mcp-server Enables agents to maintain persistent memory through three-tiered architecture: short-term session context with TTL, long-term user profiles and preferences, and searchable episodic event history with sentiment analysis. Provides comprehens |
37,151–37,200 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.