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 |
|---|---|
| atxp-mcp autonsol/atxp-mcp Access 5+ ATXP agent tools via MCP: web search, AI image generation, email, and music generation. Free tier with pay-per-use Pro tier via x402 micropayments (USDC on Base mainnet). | |
| recall-mcp autonsol/recall-mcp Persistent memory MCP server for AI coding agents. Stores, searches, and retrieves context across sessions using SQLite and FTS5. | |
| MCP Logic autonull/mcplogic Enables first-order logic reasoning including theorem proving, model finding, counterexample detection, and category theory diagram verification using pure TypeScript with no external dependencies. | |
| merchant-mcp autopaylab/merchant-mcp A universal MCP server that provides a single merchant interface for AI agents across multiple protocols, enabling catalog browsing, checkout creation, and transaction status queries. | |
| Autopilot Browser MCP Server autopilotbrowser/mcp-server Enables AI agents to search for and execute automated browser workflows through Autopilot Browser's API, allowing web scraping, data extraction, and other browser automation tasks via natural language commands. | |
| Evidenceline autopilotyourworkflow/evidenceline Enables environmental scientists to tidy PFAS lab files, screen results against two drinking-water guideline sets side by side, search public guidance with page-level citations, and check report text so every number traces back to its lab r | |
| ARM MCP Server autorabit-ai/arm-mcp-server MCP server for AutoRABIT ARM APIs, covering CI Jobs v1 endpoints, Deployment Reporting v1 endpoints, and SIEM Audit Logs. | |
| copyq-mcp autoralabs/copyq-mcp Provide AI agents with read and search access to CopyQ clipboard history, plus tab listing, with optional Windows dictation routing to separate tabs. | |
| AutoRev MCP Server autorevai/autorev-mcp Enables AI clients to manage field service operations through natural language, including call handling, job dispatch, estimates, invoicing, and reporting via the AutoRev platform. | |
| pubdata-mcp autosha-blip/pubdata-mcp Seven keyless Earth-data tools for AI agents: live USGS earthquakes with time-window and magnitude filters, ISS position, current weather, Base gas price, and live-data postcards. One optional paid tool behind a fail-closed spend cap. | |
| autotuesday-kb-mcp autotuesday/autotuesday-kb-mcp Enables secure access to an organizational knowledge base via Supabase (RLS), providing tools for search, retrieval, writing, version history, and change tracking. | |
| autousers autousers-ai/mcp Evaluate UX with AI personas and human raters directly from MCP-aware clients like Claude and ChatGPT. | |
| AutoVault autoworks-ai/autovault AutoVault is an MCP server that provides a local-first vault for AI agent skills, enabling validation, signing, and serving of SKILL.md files to agents through stdio or HTTP. | |
| GDA-MCP-Server autozw/gda-mcp-server Enables Android APK static analysis in Cursor/Claude via GDA CLI Server, supporting reconnaissance, attack surface scanning, and code decompilation through natural language. | |
| LW MCP Agents autumn-ais/lw-mcp-agents A lightweight framework for building and orchestrating AI agents through the Model Context Protocol, enabling users to create scalable multi-agent systems using only configuration files. | |
| Project Context MCP autumn-hh/project_context_mcp Enables coding agents to incrementally index project text and code, persist decisions and constraints with clear sources, and assemble focused project context across sessions via MCP. | |
| Schematron MCP Server autumnsgrove/schematronmcp Enables AI agents to extract structured JSON from HTML using a local ML model (Schematron-3B) via MLX, based on custom JSON schemas. | |
| dsh-timem-memory auuduu/dsh-timem-memory Bridges TiMEM's cloud MCP server with DeepSeek Harness to provide long-term memory tools and automatic memory skills for AI models, enabling persistent context and learned behaviors across conversations. | |
| soundcloud-mcp auxa-m45/soundcloud-mcp Enables MCP clients to search SoundCloud and retrieve tracks, playlists, and users, as well as perform authenticated actions such as likes, reposts, follows, comments, playlist editing, and uploads with multi-account OAuth support. | |
| Hello World MCP Server auxin-io/demo-mcp-server-smithery A simple MCP server that provides a basic greeting tool for saying hello with customizable names. Serves as a boilerplate template for developers to quickly create and deploy new MCP servers. | |
| Hello World MCP Server auxin-io/demo-not-friendly-mcp A simple boilerplate MCP server that provides a basic greeting tool for demonstration purposes. Serves as a starting template for developers to quickly create and deploy custom MCP servers. | |
| archery-mcp-2fa auxior/archery-mcp-2fa MCP server that adds TOTP two-factor authentication support to Archery MCP, enabling secure login for Archery accounts with 2FA enabled. | |
| AdventedHUD av151318/adventedhud Turns an LLM agent into a personal planner by providing atomic context (roles, goals, decision matrix) and routing classified items to Obsidian, with optional projection to Google Calendar and Tasks. | |
| mssql-mcp av1choudharyy/mssql-mcp An MCP server that enables interaction with Microsoft SQL Server instances using Windows or SQL Server authentication via native ODBC drivers. It allows users to execute SQL queries, list tables, and inspect schemas across multiple configur | |
| 1C MCP Sales Analyst av75057/1c-mcp-sales-analyst Enables natural language queries about warehouse stock and sales data from 1C accounting system using DeepSeek AI and MCP tools. | |
| media-mcp ava-hip/mcp-media-stack Enables users to manage Sonarr and Radarr instances through natural language, allowing search, addition, deletion, and monitoring of TV series and movies. | |
| DEM Terrain Analysis ava11235/terrain-analysis-mcp AI-powered terrain analysis for any location on Earth. Uses super-resolution and computes environmental risk metrics including erosion, water flow, and a composite Site Intelligence Score. | |
| Qdrant RAG Build avaazquezz/rag-build Enables users to build and manage a complete retrieval-augmented generation pipeline through conversation, including file ingestion, collection management, hybrid search, reranking, citations, and a guided setup wizard. | |
| mimo-free-api-mcp avac22/mimo-free-api-mcp OpenAI-compatible gateway and native MCP server for Xiaomi MiMo models, enabling search and vision capabilities in clients like Claude and Cursor. | |
| Tavily MCP Server avac22/tavily-mcp Provides AI assistants with real-time web search, intelligent data extraction from web pages, website mapping, and web crawling capabilities through Tavily's API. Enables comprehensive web research and content analysis through natural langu | |
| wikikit avalancheai-labs/agent-wiki-kit Enables agents to search, list, and read pages from a curated Markdown wiki via MCP, with live updates and tools for targeted section access. | |
| mammo-triage avalderrama/ai-mammogram-triage Analyzes mammogram CC/MLO views and sorts each breast into a BI-RADS group with a priority level (high_priority, review, or no_suspicious_findings), so physicians can see which women look most worrying and reach a radiologist first. It mask | |
| RunComfy MCP Server avalla/mcp-runcomfy Enables generation of AI videos and images using RunComfy APIs. Supports multiple models for text-to-video, image-to-video, text-to-image, and image-to-image workflows with customizable parameters like aspect ratio, duration, and seed. | |
| JAOT MCP Server avallavall/jaot Exposes optimization solver tools to AI agents via the Model Context Protocol, enabling natural language problem solving. | |
| circe-mcp avalynn-circe/circe-mcp Enables deterministic, LLM-free checking of text against a prose editorial standard, returning violations with rule IDs, locations, severity, confidence, and suggested fixes, while also supporting safe fixes and writing measurements. | |
| Math MCP Server avanishd-3/math-mcp Enables basic arithmetic operations (addition, subtraction, multiplication, division) with 64-bit precision and matrix multiplication capabilities. Provides mathematical computation tools for AI assistants through the Model Context Protocol | |
| MCP Server for macOS avanomme/mcp_mac A modern, extensible server that provides a unified interface to control and interact with various macOS applications through plugins. | |
| odouche-mcp avanserv/odouche A Model Context Protocol server that lets development agents work with Odoo.sh from their development environment, listing branches, watching builds, and streaming logs. It sits on top of the odouche Python library's public interface. | |
| Avanti Fellows PostgreSQL MCP Server avantifellows/mcp-postgres Read-only MCP server that enables AI tools like Claude and Cursor to query the Avanti Fellows PostgreSQL database, providing schema inspection, data sampling, and SELECT query execution capabilities. | |
| Billing Explainer avantiketkar-lab/billing-explainer Enables users to ask natural-language questions about why an account's bill changed and receive ranked, evidence-linked explanations grounded in computed SQL diffs, with enforced per-session authorization so agents cannot access unauthorize | |
| cockpit-mcp avanxo-technology/cockpit-mcp A read-only MCP server for Cockpit CMS that lets AI agents explore content models, fields, and items via tools, without mutating data. | |
| Typesense MCP Server avarant/typesense-mcp-server A server that enables vector and keyword search capabilities in Typesense databases through the Model Context Protocol, providing tools for collection management, document operations, and search functionality. | |
| MCP Frigate Optimizer avargas2026/mcp-frigate-0.17 Enables AI agents to audit, manage, and optimize Frigate NVR configurations, including LPR tuning and recording management. | |
| Airmail MCP avatar-arts/airmail-mcp Enables AI clients to read, search, compose, organize, and act on emails, plus manage calendars, contacts, reminders, folders, rules, signatures, aliases, and account preferences through a local bridge. | |
| Ecosystem Intelligence MCP avatar-arts/my-mcp-creator Provides bounded, read-only analysis of local project directories, enabling inventory, marker detection, and safe file reads without executing code. | |
| MinerU Document to Markdown MCP Server avatarganymede/mineru-mcp Converts documents (PDF, Word, PPT, images, HTML) to Markdown via MinerU API. Supports URL and local file inputs with OCR, formula/table recognition, and automatic large file handling. | |
| UnrealMCP avatarganymede/ue5.7-mcp A native MCP server for Unreal Engine 5.7 that lets AI assistants inspect and control an open Unreal Editor through a single 'unreal' tool, supporting Python/console command execution and async tasks. | |
| OpenXE MCP Server avatarsia/openxe-mcp-server Connects OpenXE ERP with AI assistants via MCP, enabling natural language queries to read and write ERP data locally. | |
| StructureAI MCP Server avatrix1/structureai-mcp Extracts structured JSON data from unstructured text using predefined schemas for receipts, invoices, resumes, and emails. It allows users to transform messy text into organized data through built-in or custom-defined fields. | |
| LandingAI ADE MCP Server avaxia8/landingai-ade-mcp Enables extraction of text, tables, and structured data from PDFs, images, and office documents using LandingAI's Agentic Document Extraction API. Supports both direct parsing and background job processing for large files with privacy-focus |
31,851–31,900 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.