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 |
|---|---|
| Clockify MCP Server dustinestes/clockify-agent-plugin Unofficial MCP server for Clockify time tracking. Enables starting/stopping timers, mapping coding work to projects, and summarizing sessions in Cursor and other MCP hosts. | |
| Alexa+ AWS Bedrock Orchestrator MCP dustingibson-jpg/alexa-plus-bedrock-mcp Enables Alexa+ voice intents to be evaluated and orchestrated through AWS Bedrock Claude 3.5 Sonnet, coordinating multi-surface actions across Ring, Fire TV, and Wearable AI devices via MCP tools, prompts, and resources. | |
| mcp-memory-server dustinspace217/mcp-memory-server A knowledge-graph-based persistent memory server for the Model Context Protocol, storing entities, observations, and relations in SQLite with semantic vector search and temporal versioning. | |
| Local Image Search (Japanese) MCP Server duston/search-image-mcp Enables searching local images using natural Japanese queries, leveraging a Japanese-specific CLIP model for similarity search and providing efficient caching and fast retrieval via MCP and HTTP endpoints. | |
| yoga-store dustynotesai/yoga-agent-store Enables AI agents to browse a yoga apparel catalog and complete purchases through authenticated JSON/MCP checkout, with identity, mandate, budget, and payment gates. | |
| GitHub Stars MCP Server dustyposa/github-stars-mcp-server A high-performance server for analyzing GitHub user starred repositories, providing insights into development trends, technology adoption patterns, and timeline tracking. | |
| qdrant-mcp dutchakdev/qdrant-mcp MCP server that gives AI coding agents persistent, semantic memory via Qdrant vector search, enabling workspace-aware codebase, documentation, and decision search. | |
| brainstormform dutchbase/brainstormform Enables AI agents to create local web forms with unlimited brainstorming questions and retrieve user answers as JSON, including support for file uploads. | |
| img-convert MCP Server dutchbase/img-converter Provides AI agents with tools to convert images between formats and inspect image metadata, enabling seamless image processing within agent workflows. | |
| Confluence MCP Server dutta-piyush/custom-confluence-mcp Enables GitHub Copilot to read, write, search, and manage Confluence pages, spaces, attachments, and diagrams through MCP tools. | |
| Outlook MCP dutta-piyush/custom-outlook-mcp Enables AI agents to manage Microsoft Outlook emails through the Microsoft Graph API, supporting operations like listing, reading, sending, and moving emails. | |
| web-fetch-mcp dutta-sd/web-fetch-mcp A web-fetch MCP server for LLM agents that fetches pages with an escalation ladder through different engines, raising FetchBlocked instead of returning blocked content. | |
| MCP Server Demo duttaayush/mcp A demonstration server that provides tools for analyzing project structures and automatically generating comprehensive README files. | |
| iMCP duvaragesh/imcp A universal bridge that turns legacy backend services and modern APIs into AI-accessible tools without requiring code rewrites. It dynamically generates tool definitions from WSDL, OpenAPI, or custom JSON specs to enable AI assistants to in | |
| CUA MCP Server duvoai/cua-mcp-server Enables autonomous desktop automation by delegating tasks to vision-based agents operating within cloud-based virtual machine sandboxes. It allows users to manage VMs, execute complex computer tasks, and receive text-based screen summaries | |
| MCP-WEATHER duwancontacto/mcp-weather Provides weather information for any city using the Open-Meteo API, deployed via Vercel for easy integration with MCP clients. | |
| mysql-query duxiaoben/mcp-mysql A read-only MySQL query service that allows SELECT operations, listing tables, and viewing schemas via MCP protocol. | |
| WorldQuant MCP duy0699cat/worldquant-brain-mcp Automates WorldQuant BRAIN alpha research workflows, including simulation, reference search, and alpha submission through MCP tools. | |
| cf-mcp-bridge duya7019/cf-mcp-bridge Provides read-only inspection of Cloudflare account resources, including zones, DNS records, Workers, Pages projects, R2 buckets, and Tunnels, via a secure MCP endpoint. | |
| Owl Watch Simulator MCP duyatuan/owl-watch-simulator-mcp Enables AI agents to build, launch, inspect and drive Garmin Connect IQ apps in the macOS Connect IQ simulator, returning screenshots paired with recognised on-screen text and tap-ready coordinates. It runs whole interaction flows—including | |
| Duyet MCP Server duyet/duyet-mcp-server An experimental Model Context Protocol server that enables AI assistants to access information about Duyet, including his CV, blog posts, and GitHub activity through natural language queries. | |
| McpGemini2Antigravity duykhanhbv-bit/mcpgemini2antigravity Enables users to connect Google Gemini 4 High (Argon Extended Thinking) from Gemini Web into Google Antigravity via MCP tools, a /kg4 slash command, and an OpenAI-compatible proxy for chat completions. | |
| ImageRouter duylamneuuu/imagerouter Local MCP server that routes image-generation requests to xAI/Grok, Antigravity, and OpenAI Codex with ordered fallback, a local Playground, and an OpenAI-compatible image endpoint. | |
| PG Connection Pool Query Gateway duylongpro99/db-query-mcp Enables agents to run SQL queries against PostgreSQL databases through MCP with connection pooling, tenant isolation, and read-only guardrails. Supports introspection of schemas, tables, and columns. | |
| n8n-custom-mcp duynghien/n8n-custom-mcp A full-power MCP server for n8n that enables AI agents to create, read, update, delete, and test workflows and credentials, including webhook testing, validation, and backup/versioning. | |
| karate-graph-mcp duyngo91/karate-graph-mcp Enables analysis of Karate framework feature files, extracting dependencies and generating interactive dependency graphs. | |
| AccessBell MCP Server duynguyendang/aws-access-bell Enables Alexa+ and other agents to query door events, expected visitor context, quick replies, escalation controls, and accessibility preferences, turning Ring doorbell signals into grounded, consent-aware intelligence for voice and TV inte | |
| clockify-mcp duynhannguyen/clockify-mcp A local MCP server that lets Claude start, stop, and log Clockify time entries. | |
| codebaxing duysolo/codebaxing MCP server for semantic code search that indexes your codebase and allows AI editors to search using natural language queries. | |
| agoda-mcp duythien0912/agoda-mcp Enables searching Agoda hotel deals and evaluating room freshness using Vision ML, with Playwright stealth to bypass bot detection. | |
| @duytnb79/asana-mcp duytnb26/asana-mcp-server A local MCP server for Asana that uses a personal access token to read and manage Asana projects, tasks, sections, and comments via the standard Asana REST API. | |
| @duytnb79/asana-mcp duytnb79/asana-mcp-server A local MCP server that lets you interact with Asana using a personal access token, providing tools to list projects and tasks, search tasks, create and update tasks, and add comments via the Asana REST API. | |
| Backlog MCP Server duytnb79/backlog-mcp A read-only MCP server that enables users to retrieve and interact with Backlog projects, issues, pull requests, and notifications. It provides a secure way to query Backlog data through natural language using tools like Claude Desktop. | |
| VN AI Content Kit duytruyenthong/vn-ai-content-kit Enables local Vietnamese ecommerce copy preparation, source-grounded RAG retrieval, offline voice previews, correction-memory feedback, hook review, and fine-tuning dataset preparation without publishing posts or approving audio. | |
| ARES Explorer duzidavid/ares-explorer-mcp MCP server that turns the Czech business register (ARES) into an interactive force-directed graph of company management and ownership ties, allowing users to explore and expand the graph live within Claude. | |
| guardian-policy-mcp dv-labs-co/guardian_agent_ai Enables context-aware household safety workflows to coordinate smart-home events, household context, policies, risk, and safe actions through auditable MCP tools for status, event evaluation, wellness checks, rule creation, and action reque | |
| wave-mcp dv365lab/dv365-wave-mcp Enables LLMs and code agents to debug RTL waveforms through MCP by reading FST files and RTL netlists, converting VCD/FSDB/SHM/VWDB to FST, exploring hierarchy and signals, analyzing drivers, tracing values and X states, comparing waveforms | |
| elysiajs-mcp dvaji/elysiajs-mcp An MCP server plugin for the Elysia web framework, enabling AI clients to connect via Streamable HTTP transport with stateful or stateless sessions and authentication. | |
| Web Search MCP Server (Authless) dvc890/web-search-mcp-server-authless Deployable remote MCP server on Cloudflare Workers without authentication, enabling custom tool integration with AI Playground and Claude Desktop. | |
| Devonthink MCP Server dvcrn/mcp-server-devonthink This MCP server provides access to DEVONthink functionality via the Model Context Protocol (MCP). It enables listing, searching, creating, modifying, and managing records and databases in DEVONthink Pro on macOS. | |
| Linear MCP Server dvcrn/mcp-server-linear Enables AI tools like Cline to manage Linear issues, projects, and teams via the Linear API. | |
| mcp-server-memrise dvcrn/mcp-server-memrise MCP server to manage Memrise courses, levels, and words, enabling course creation and teaching workflows through natural language. | |
| Siri Shortcuts MCP Server dvcrn/mcp-server-siri-shortcuts Enables interaction with macOS Siri Shortcuts via the Model Context Protocol, allowing users to list, open, and run shortcuts dynamically with optional inputs. | |
| mcp-server-subagent dvcrn/mcp-server-subagent An MCP server that allows a planning agent to delegate tasks to executor agents (e.g., Claude Code, Aider) with bi-directional communication and real-time log streaming. | |
| mcp-server-tripit dvcrn/mcp-server-tripit Enables interaction with TripIt travel planning service, allowing users to manage trips, hotel reservations, flights, transport, activities, and documents via natural language. | |
| Kapa MCP Server dvdksn/kapa-mcp-docker Enables querying Kapa.ai's documentation and Q&A capabilities for any project enrolled with Kapa, with tools for asking questions and searching sources. | |
| douyin-mcp-server dvdxfv/douyin-mcp-server MCP server for parsing Douyin links to fetch video info/download links, transcribing audio locally, and organizing transcripts into polished spoken copy. | |
| MCP Media Generator dvejsada/mcp_media_generator A Model Context Protocol server that enables AI assistants to create images and videos using Amazon Nova Canvas and Nova Reel models. | |
| mealie-mcp dvejsada/mealie-mcp A read-only MCP server for Mealie that enables searching recipes, managing shopping lists, meal plans, and retrieving household/instance info via tools. Supports secure per-user authentication and multiple Mealie instances. | |
| google-search-console dveresov/dv-gsc-mcp Enables users to query Google Search Console data interactively from Claude Desktop and via CLI, providing search analytics, period comparisons, branded split, indexing status, sitemaps, and full CSV exports. |
46,451–46,500 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.