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 |
|---|---|
| mealplan-mcp evcraddock/mealplan-mcp MCP server for meal planning and grocery list generation, enabling recipe storage, meal plan creation, and automated grocery lists with ignored ingredients. | |
| Apple App Store Revenue MCP Server evekeen/appstore-revenue-mcp Fetches revenue and download data for Apple App Store apps using the Sensor Tower API. | |
| applemusic-mcp evelyn24594/applemusic-mcp Enables MCP clients to control Apple Music playlists, library, catalog, discovery, playback, and the Up Next queue across macOS, Windows, and Linux using native app, Apple Music API, Safari, or Chrome engines. | |
| AutoCAD MCP Pro evelyndogan/autocad-mcp Enables AI agents to automate AutoCAD drafting, drawing understanding, and quantity takeoffs either through a live COM connection on Windows or headlessly via ezdxf on any platform. It covers P&ID, mechanical, and architectural workflows wi | |
| Pentest MCP evelynkonstantinou48223/pentest-mcp Enables professional penetration testers to orchestrate reconnaissance, scanning, brute-force checks, traffic capture, privilege-escalation auditing, and reporting workflows through MCP transports. It integrates tools including nmap, GoBust | |
| MCP Image Generator evelynozdemir1695/mcp-image Enables users to generate and edit images from any MCP client by automatically enriching short requests with composition, lighting, and camera details before sending them to Gemini, OpenAI, or BytePlus Seedream. Supports quality presets, as | |
| MCP Memory evenfuture/mcp-memory Enables MCP clients such as Cursor, Claude, and Windsurf to store and recall user preferences, behaviors, and other text-based information across conversations, using vector similarity search so conceptually related items are found even whe | |
| pramana-mcp evenindividual04/pramana Enables citation-audited deep research with tools for web-grounded answers, source conflict detection, and per-claim citation auditing. | |
| File Operations MCP Server evenli01/fileops-server Provides tools for common file processing operations including reading files, listing directories, searching across files, getting file info, and counting lines with built-in security features like path traversal protection. | |
| EventCatalog MCP Server event-catalog/mcp-server A server that connects MCP clients (Claude, Cursor, Windsurf, etc.) to EventCatalog instances, allowing users to ask questions about their event-driven architecture and get insights about domains, services, and message schemas directly with | |
| agent-memory event4u-app/agent-memory A persistent, trust-scored project memory for AI coding agents, backed by PostgreSQL + pgvector, providing durable memory of architecture decisions, bug patterns, and coding conventions. | |
| newsapi-mcp eventregistry/newsapi-mcp A Model Context Protocol (MCP) server that provides real-time news intelligence using NewsAPI.ai. This server enables LLMs to search articles, track events, and analyze news through natural conversation. | |
| local-image-search eventual-inc/local-image-search Privacy-first MCP server for macOS that allows AI agents to search local images using natural language descriptions, leveraging MLX CLIP embeddings and LanceDB for fast, fully offline search. | |
| Met Research MCP evenwestvang/met-mcp Enables read-only collection research through six snapshot-backed tools for capabilities, facets, typed selection, ranking, bounded object metadata hydration, and evidence resolution. | |
| mcp-mistral-ocr everaldo/mcp-mistral-ocr OCR images or pdfs, locally or by URLs by using Mistral OCR API (paid) | |
| Splunkbase MCP Server everdrediidx/splunkbase-mcp A Machine Control Protocol server providing programmatic access to Splunkbase functionality, allowing users to search, download, and manage Splunkbase apps through a standardized interface. | |
| Context Mode everflow-utilities/context-mode Context Mode is an MCP server that reduces context window waste by sandboxing data-heavy tools, tracking session state in SQLite, and promoting code-based analysis over raw data reads, achieving up to 98% context savings. | |
| Fetcher MCP everford/fetcher-mcp A server that allows fetching web page content using Playwright headless browser with AI-powered capabilities for efficient information extraction. | |
| evergreen-mcp-server evergreen-ci/evergreen-mcp-server MCP server for MongoDB's Evergreen CI/CD platform, enabling AI assistants to manage projects, analyze builds, and troubleshoot failures via natural language. | |
| Crawlmind everhard/crawlmind Enables AI clients to crawl websites and run technical SEO audits, including broken-link detection, internal-link suggestions with anchors, template-based speed measurement, crawl diffs, and report export through MCP tools and prompts. | |
| chatgpt-local-coding-agent everlastingqaq/chatgpt-local-coding-agent Enables ChatGPT web to interact with local Windows/WSL shell and code workspaces via an MCP server, providing file access, shell execution, and snapshot-based workspace management with per-command authorization. | |
| ACC.MCP eversedevelopment/aps.mcp An MCP server that exposes Autodesk Platform Services (APS) as tools for AI assistants to interact with the APS Data Management API. It enables users to authenticate and manage hubs, projects, and folders through a standardized interface. | |
| Eversince MCP Server eversince-ai/mcp A creative agent that plans and executes across image, video, and audio. Uses 30+ tools, orchestrates 20+ AI models, and does agentic timeline editing. | |
| SharedContext eversmile12/sharedcontext Provides encrypted, portable memory for AI agents via MCP, allowing fact storage, conversation recall, and cross-machine sync using Arweave. | |
| Garmin Health MCP Server eversonl/garmin-health-mcp-server Enables Claude Desktop to access and analyze Garmin wearable health data including sleep, HRV, Body Battery, and activity metrics. Users can query their health trends, track recovery, and generate interactive HTML dashboards using natural l | |
| MCP - Model Context Protocol eversonpereira/mcp A conversational application server that integrates LLM capabilities via Ollama with vector memory context, supporting multiple users, sessions, automatic history summarization, and a plugin system for executing real actions. | |
| Kali MCP Server eversonwbm/kali-mcp-server Provides AI-assisted web penetration testing tools built on Kali Linux Docker container, with proper input sanitization and formatted output. | |
| TaskPad evert-vh/taskpad A Windows system-tray task manager with MCP server integration, enabling Claude Code, Claude Desktop, and claude.ai to read and write tasks via stdio or SSE. | |
| vault-search-mcp everton-dgn/vault-search-mcp Enables local hybrid search over Obsidian and Markdown vaults via MCP, combining vector retrieval, full-text search, reranking, graph navigation, and safe CRUD while keeping data local. | |
| Stream MCP Server evertrust/stream-mcp An MCP server for Evertrust Stream, a PKI platform, allowing LLM clients to manage certificate authorities, issue/revoke X.509 and SSH certificates, and operate PKI infrastructure through natural language. | |
| torch-datadog-mcp everwise/torch-datadog-mcp A FastMCP server that provides DataDog log search and monitoring with service-aware filtering, preview-execute workflow, and response size safeguards. | |
| distillory everyai-com/distillory Local-first memory engine that synthesizes entity profiles at ingestion. Enables persistent, reasoning memory for AI agents via MCP tools like add, search, and profile. | |
| Pulse everyai-com/pulse A read-only analytics MCP server that enables AI assistants to query site traffic, revenue attribution, breakdowns, timeseries, pages, realtime visitors, lifetime value, MCP tool usage, funnels, and visitor journeys across projects. | |
| relationship-manager everyai-com/relationship-manager Enables agents to query and reason over a unified graph of a person's real relationships, resolved across email, WhatsApp, calendar, and calls, with evidence-backed facts and deterministic briefs. | |
| google-workspace-mcp-server everyinc/google-workspace-mcp-server MCP server for Google Workspace APIs - Docs, Sheets, Drive, Gmail, and Calendar. Enables reading, creating, and editing Google Docs and Sheets, managing comments, reading emails, and viewing calendar events. | |
| Sparkle MCP Server everyinc/sparkle-mcp-server Provides secure file access and clipboard history management for Claude AI and other MCP-compatible clients, with sandboxed file operations and search capabilities. | |
| tiergrader everyinc/tiergrader Enables agents to create tier-grading collections, upload files or text items, generate per-person ranking links, and read back individual and averaged S/A/B/C/D/F placements and results over a stateless streamable HTTP endpoint. | |
| Scintilla MCP everymanjames/scintilla-mcp-server Gives AI assistants read-only, natural-language access to a supplier's Walmart Scintilla BI Link BigQuery share, exposing tools for listing and describing views, running guarded SELECT queries, and summarizing sales, inventory, in-stock, ou | |
| AutoCAD MCP Server everymethod/autocad Enables natural-language control of AutoCAD LT for automation and headless DXF generation, supporting drawing, entity, layer, block, annotation, P&ID, and system operations via an MCP interface. | |
| evex-agent-messaging evexu2/evex-agent-messaging Provider-neutral MCP transport for Parent Main, Child Main, and Role Child conversation operations, enabling agents to create child conversations, send results, request user decisions, and manage missions via HMAC-signed capabilities withou | |
| timeweb-mcp evgeninho69/timeweb-mcp Local MCP server for Timeweb Cloud that enables running any twc CLI command and provides shortcuts for managing servers, apps, and account. | |
| clinicmarketiq-public-data evgeniy-yudin/clinicmarketiq-data Enables read-only access to public U.S. healthcare market-intelligence datasets, including catalogs, schemas, metadata, checksums, and artifact URLs. It supports CMOs, analysts, researchers, and AI agents in discovering and consuming govern | |
| lira-sapr-mcp evgenver/lira-sapr-mcp Enables AI agents to drive LIRA-SAPR/LIRA-FEM on Windows through its COM API, including creating and editing models, running analyses, and reading results with full tables exportable to CSV or Excel. | |
| @relbase/mcp evgeny-tc/relbase-mcp Enables MCP clients like Cursor to manage RelBase diagrams and projects through the RelBase REST API, including listing, retrieving, creating, updating, and deleting diagrams. | |
| Zettelkasten MCP Server evgeny9478/zettelkasten-mcp Enables users to create, link, explore, and synthesize atomic notes through Claude and other MCP-compatible clients, with markdown storage, tags, search, and semantic link types. | |
| AutoCAD MCP Pro evgenyfontana48122/autocad-mcp Enables AI agents to draft, read back, validate and take off real CAD drawings — mechanical parts and sheets, architectural plans with measured room areas, and P&IDs — through a typed tool contract covering ISO GD&T, dimension tolerances, I | |
| R2R MCP Server evgenygurin/fastmcp-r2r-openapi-integration A FastMCP-based MCP server for the R2R API, enabling integration with document management, knowledge graphs, and RAG systems through automatically generated tools and resources. | |
| MCProxy evgenygurin/mcproxy An MCP server that gives AI agents on-demand access to proxies from the world's leading and Russian/CIS proxy providers — through a single, unified interface. | |
| R2R FastMCP Server evgenygurin/r2r-rag-search-agent Integrates R2R (Retrieval-Augmented Generation) with Claude Desktop, enabling semantic search across knowledge bases and RAG-based question answering with support for vector, graph, web, and document search. | |
| Vercel MCP Memory evgenygurin/vercel-mcp-memory Enables semantic memory storage and retrieval with natural language queries, deployed on Vercel with PostgreSQL pgvector and OpenAI embeddings. |
48,951–49,000 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.