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 |
|---|---|
| dwolla-mcp dwolla/dwolla-mcp Enables AI agents to retrieve and analyze Dwolla payment platform data using natural language, with read-only access to accounts, transfers, customers, and compliance information. | |
| QA MCP Server dwonng/qa-mcp-server An AI-powered QA automation server that integrates Jira, GitHub, Jenkins, AWS, and Webex into a unified interface for QA engineers. | |
| fantasypros-mcp dwooods/fantasypros-mcp Enables MCP clients to access FantasyPros data through tools for injury news, player lookup, consensus rankings, and projections. | |
| Skylight MCP Server dwooods/skylight-mcp Enables MCP clients to query and manage a family calendar, chores, grocery and task lists, meals, family members, and rewards through a private Skylight account, with local or hosted deployment. | |
| omdb-mcp dworf/omdb-mcp MCP server for the OMDb API - search movies, series, and episodes from any MCP-compatible client. | |
| AutoDocBot-V2 dwprov/autodocbot-v2 MCP server that converts natural language process descriptions into structured Confluence process articles with SVG diagrams and publishes them under the authenticated user's Atlassian identity. | |
| WING Rack MCP dwrightii/wing-mcp Enables Claude to discover and connect to Behringer digital mixers over OSC, read and write parameters, dump subtrees to show files, and push edited files back to the desk. | |
| MCP Gateway dwsitproject-hub/mcp-gateway Enables authorized Energi-Up staff to query KLIP data in natural language through Claude, strictly read-only, without opening the application. | |
| @dwsm/changelog-mcp dwsmorg/changelog_mcp Enables safe changelog management for AI assistants with append-only entries, automatic versioning, and backups to prevent accidental deletion or formatting inconsistencies. | |
| EndpointSecureOps-MCP dwsnttdata/endpointsecureops Enables AI assistants to perform read/write management of Microsoft Intune and Entra ID across devices, apps, users, groups, Conditional Access, Cloud PC, compliance, and reports via Microsoft Graph. | |
| Magic-API MCP Server dwsy/magic-api-mcp-server Provides comprehensive development tools for Magic-API including documentation lookup, API testing, resource management, debugging with breakpoints, backup operations, and code search capabilities. Enables developers to efficiently build, t | |
| mcp-feedback-enhanced dwsy/mcp-feedback-enhanced MCP server providing feedback-oriented development workflows with a Web UI and desktop application for interactive user confirmation, session tracking, and smart prompt management. | |
| Ombre Brain dwwwpfquct/ombre-brain Enables Claude to keep persistent cross-conversation memory by storing each memory as an Obsidian-compatible Markdown bucket tagged with Russell valence/arousal coordinates, then decaying, merging, and proactively surfacing memories by emot | |
| anysite-mcp dwytmcl/anysite-mcp Enables AI agents to operate real signed-in Chrome sessions per site, interact with any website through accessibility roles and names, and save successful workflows as reusable shortcut tools. | |
| gemini-mcp dwytmcl/gemini-mcp Enables Claude or any MCP client to use the Google Gemini web app through a real Chrome browser with a normal Google account and no API key, including sending prompts, managing chats, uploading files, downloading results, and inspecting or | |
| notebooklm-mcp dwytmcl/notebooklm-mcp Enables MCP clients such as Claude to drive the real Google NotebookLM/Gemini Notebook website using a free Google account, including listing and creating notebooks, adding sources, asking questions with citations, and generating Studio con | |
| Deep Code Reasoning MCP Server dx-corp/deep-code-reasoning-mcp Pairs Claude Code with Google's Gemini AI for complementary code analysis, enabling intelligent routing where Claude handles local-context operations while Gemini leverages its 1M token context for distributed system debugging and long-trac | |
| Shared Memory MCP Server dx-corp/shared-memory-mcp Provides a shared context layer for AI agent teams to improve token efficiency through context deduplication and incremental state sharing. It enables multiple agents to coordinate tasks, share real-time discoveries, and manage dependencies | |
| Secure Local Workspace MCP dxawdc/chatgpt-workspace-mcp Enables ChatGPT and Codex to safely work with explicitly authorized local project folders through MCP, providing constrained file reading, searching, patch editing, Git inspection, and whitelisted tasks without exposing arbitrary shell, del | |
| PostgreSQL MCP Server dxc-lab-linkage/postgres-mcp-server Enables interaction with PostgreSQL databases through both HTTP and Stdio transports, supporting read-only SQL queries, table listing, and schema inspection. Features stateful session management for HTTP transport and flexible deployment op | |
| Quack MCP Server dxc-lab-linkage/quack-mcp-server A continuous integration server that automates Python code analysis, providing linting and static type checking tools for quality assurance. | |
| ABAP MCP Server dxchowardb/abap-mcp-server Provides unified ABAP and RAP documentation search, document retrieval, and ABAP feature matrix lookups. It also enables local ABAP linting to streamline development and documentation workflows via the Model Context Protocol. | |
| mcp-server-jsxgraph dxd214/mcp-server-jsxgraph Enables creating interactive mathematical visualizations like function graphs, geometry diagrams, and parametric curves using JSXGraph. | |
| Capyra dxeledx/capyra Enables ChatGPT and other MCP clients to browse, search, edit and upload files, run commands and interactive terminals, inspect Git history and worktrees, dispatch coding agents, and install composable plugins within locally registered work | |
| EchoBrain Local dxer/obsidian-echobrain Enables AI agents such as WorkBuddy, Cursor, and Claude Desktop to search, understand, and traverse the links of a local Obsidian vault as long-term memory, combining keyword, semantic, and graph-based retrieval. Also lets agents safely sav | |
| mcp-servers dxheroes/mcp-servers Enables deploying standalone MCP connectors, discovering them through a validated catalog, and running an optional trusted polyglot runtime for the DX Heroes MCP Gateway. | |
| autocad-mcp dxlary/autocad-mcp Enables MCP clients to connect to and automate AutoCAD on Windows via COM, exposing tools to inspect drawings and layers, create geometry and text, manage system variables, run commands, and save or open drawings. Requires full AutoCAD runn | |
| Windows MCP Server dxn-crsis/windows-mcp An enterprise-grade automation server that enables AI assistants to control Windows PCs through intelligent UI element detection, window management, and system-level commands. It leverages the Windows UI Automation tree for reliable interac | |
| DXN1-AUDIO-AI-TOOL dxn1-termux/dxn1-daw-ai-tool AI-powered music production toolkit enabling AI agents to generate, remix, separate stems, master tracks, and control DAWs via MCP. | |
| Garmin Claude MCP dxnielcr/garmin-claude-mcp Lets Claude read a runner's recent activities and wellness signals — sleep, HRV, resting heart rate — and then design, schedule, edit, or delete structured workouts. Planned sessions are written to an intervals.icu calendar that syncs throu | |
| Spotify MCP Server dxtintx/spotify-mcp2host Enables AI assistants to control Spotify playback, manage playlists, and search music via the Model Context Protocol. | |
| agent-eval-gate dxwss/agent-eval-gate Serves MCP tools to inspect agent trace JSONL files and evaluate them against golden-case constraints, returning structured metrics and gate results. | |
| gephi-3d dxy624/gephi-and-codex Enables Codex to control a Gephi 3D network view through natural language, including network generation, 3D layout, node focus and neighbor highlighting, layered views, and PNG/PDF export. | |
| wd-mycloud-mcp dy-le/wd-mycloud-mcp Enables AI assistants to browse, read, write, move, copy, and delete files on WD MyCloud Home devices, supporting local SMB and remote REST API connections with automatic token refresh. | |
| incident-mcp dyakonovalex/incident-mcp An incident management MCP server for on-call engineers, providing tools to search incidents, review deploys, query logs, analyze latency metrics, and acknowledge or summarize incidents. | |
| Spec Kit Memory Hub dyangalih/spec-kit-memory-hub Repository-native, Git-reviewable memory extension for AI coding assistants to persist project context across features, using SQLite caching for up to 10x token reduction. | |
| asana-mcp dyanko89/asana-mcp Enables to interact with Asana through Claude, with read and write tools for tasks, projects, tags, and custom fields, with no destructive operations. | |
| central-brain dycandx/devbrain Enables AI coding assistants to access a local Obsidian vault as a unified knowledge base, with hybrid semantic search, project context retrieval, agent session logging, and reusable skill loading. | |
| MindGraph dycm8009/mindgraph Enables AI agents to query and analyze code across multiple repositories through a unified knowledge graph, with tools for symbol search, impact analysis, and graph algorithms. | |
| QCViz-MCP dydtkddl/qcviz-mcp An MCP server for quantum chemistry that enables LLMs to perform electronic structure analysis, parse calculation outputs, and generate 3D orbital visualizations. It integrates tools like PySCF, cclib, and py3Dmol to facilitate molecular st | |
| nostr-auth dyegolara/nostr-auth-agents Enables LLM coding agents to sign in with Nostr by generating NIP-07 signatures and exposing public keys, without requiring a wallet or browser extension. | |
| Clerk MCP Server Template dyeoman2/clerk-mcp-template A production-ready template for building Model Context Protocol servers with Clerk authentication on Cloudflare Workers, allowing AI assistants to securely access user data and business logic in Clerk-authenticated applications. | |
| WhatsApp MCP dyfintie/whatsapp-mcp Enables AI agents to search and read locally stored chat history, look up contacts, send messages and attachments, and retrieve media through a self-hosted local daemon with encrypted SQLite storage. | |
| agent-guard-mcp dygogogo/agent-guard-mcp MCP Guard Server - Budget control, approval workflows and audit logging for AI agents (Claude Code, Cursor, ChatGPT) | |
| chromectx dyingg/chromectx Search and retrieve content from all open Chrome tabs, and provide them as context for AI tools via MCP. | |
| McProxy dykstrasound/mcproxy A local, multi-tenant MCP server framework for macOS that consolidates multiple third-party services behind a single MCP endpoint, with a browser-based connection manager. It provides a secure, extensible foundation for adding custom connec | |
| FreeCrawl MCP Server dylan-gluck/freecrawl-mcp Enables web scraping and document processing with JavaScript execution, anti-detection measures, batch processing, and structured data extraction. Supports multiple formats including markdown, HTML, screenshots, and handles PDFs with OCR ca | |
| LocalDocs MCP dylan-gluck/localdocs-mcp Creates a local database of indexed technical documentation from web crawls and local files, enabling AI agents to efficiently search and retrieve documentation through MCP tools. | |
| MCP Background Job Server dylan-gluck/mcp-background-job An MCP server that enables coding agents to execute and manage long-running shell commands asynchronously with capabilities for process monitoring, interaction, and lifecycle management. | |
| Motion MCP Server dylan948/motion-mcp-server Enables LLM clients to manage tasks, projects, workspaces, schedules, comments, custom fields, recurring tasks, and statuses through natural conversation by bridging Motion's API via the Model Context Protocol. |
46,551–46,600 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.