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 |
|---|---|
| Salesmate MCP Server arnav-chauhan-kgpian/salesmate-mcp A production-ready MCP server that exposes the Salesmate CRM to Claude Desktop, enabling search, update, and creation of contacts, deals, tasks, notes, and activities. | |
| Fringe arnav020/fringe Enables an existing agent to turn a one-line caregiver note into a working AAC communication board of picture buttons grounded in Qloo's taste graph, and to build a board tailored to a specific conversation partner from two people's shared | |
| Memex arnavbee/memex A local-first, privacy-first MCP server that passively indexes personal digital activity (screenshots, clipboard, notes, downloads, links) into a local database, enabling LLMs like Claude to access your context without cloud storage. | |
| edgar-mcp arnavdsp/edgar-mcp Enables AI agents to query US public company financial data from SEC filings, with tools for resolving tickers, listing filings, retrieving financial concepts, comparing companies, extracting filing sections, and full-text search. It surfac | |
| mcp-enterprise-agent arnavhazra/mcp-enterprise-agent An enterprise-grade MCP server that enables LLM agents to securely interact with PostgreSQL databases and the local file system under absolute sandbox boundaries. | |
| Notion MCP Bridge arnavk800/notion-mcp-bridge Enables secure natural language querying of Notion CRM databases, allowing AI agents to retrieve client health, ARR, and deployment roadblocks through a custom MCP middleware. | |
| fitbit-mcp arnavsankhe/fitbit-mcp Enables Claude and other MCP clients to query your Fitbit/Pixel Watch health data via the Google Health API, including sleep, heart rate, activity, workouts, and trends with read-only access. | |
| hearth-mcp arnavshah22/hearth Enables families to care for an aging parent by voice, handling medication check-ins, appointments, daily summaries, missed-dose escalation, and parent-controlled sharing. Writes are tiered and confirmed by the user through MCP elicitation, | |
| indstocks-mcp arnavshah22/indstocks-mcp Read-only MCP server for INDmoney portfolio and Indian market data, using official REST and WebSocket APIs. Provides tools for account info, quotes, holdings, mutual funds, CAS parsing, and analytics. | |
| Dynamo Diff arnavsharma2/dynamo-diff Enables comparing two recorded PyTorch Dynamo runs and inspecting compiler evidence behind differences via CLI, MCP tools, and a VS Code extension. | |
| screenshot-mcp arnavv-guptaa/screenshot-mcp An AI-powered screenshot tool for Cursor IDE that enables agents to capture and analyze web pages, handling authentication, dynamic content, and element-specific capture. | |
| DroidPilot arnavvs/droidpilot Lets a laptop hand whole goals, or single tool calls, to an LLM agent running on an Android phone, and then track, stop, reply to, or inspect the resulting background tasks. Read-only operations are annotated so clients can auto-approve the | |
| MobileAgentMCP arnavvs/mobileagentmcp Enables an agent to control a real Android phone by reading structured UI elements and performing actions such as tapping, swiping, typing, and extracting fields from known app screens. | |
| Remote MCP Server (Authless) arnegrondahl/argrtest00-remote-mcp-server-authless Template to deploy a remote MCP server on Cloudflare Workers without authentication, enabling connection to AI playground and Claude Desktop. | |
| Nanonets MCP Server arnejanning/nanonets-mcp Converts images, PDFs, Word documents, and Excel spreadsheets to structured markdown using Nanonets OCR, with support for tables, LaTeX equations, and complex layouts. | |
| Backforms MCP arneld18/backforms-mcp Official Model Context Protocol (MCP) server for Backforms[ https://backforms.com]. Connect serverless forms, anti-spam shields, and lead telemetry directly to Cursor, Windsurf, Claude Code, and Claude Desktop. | |
| EchoProbe arneuralx/echoprobe An MCP server that audits voice-assistant tools for prompt injection, tool poisoning, privacy leaks and speech-unfriendly answers. It exposes scanning, PII/link checks, voice rewriting and server-audit tools so users can test whether MCP to | |
| MCP All-in-One Server arnie936/agentic-mcp A versatile MCP server providing tools for arithmetic operations, n8n webhook integration, and access to a customer support playbook resource. It also includes specialized prompt templates for converting webinar transcripts into engaging bl | |
| arabic-dict-mcp arnizamani/arabic-dict-mcp MCP server that provides grounded Arabic dictionary lookup, enabling AI agents to search word roots, inflections, and meanings from real dictionary data. | |
| xflow-timesheet arno-vel-bept/sap-fiori-timesheet-mcp Lets humans and AI agents drive an SAP Fiori timesheet portal through CLI or MCP, handling SSO login with 2FA and enabling tasks such as filling days, managing favorites, staffing plans, and multiproject allocation. | |
| Perplexity Search MCP arnochenfx/perplexity-search-mcp Enables AI-powered search capabilities through Perplexity AI's continuously refreshed index. Supports web, academic, and SEC search modes with advanced filtering options including geographic location and customizable result limits. | |
| shelfkeeper-mcp-server arnold-commits/shelfkeeper-mcp-server MCP server for Amazon FBA sellers providing tools for profit calculation, inventory health analysis, COGS breakdown, tax deduction guidance, reorder point calculation, and FBA fee reference. | |
| image-finder arnoldkouya/image-finder Enables searching multiple royalty-free image sources (Openverse, Wikimedia Commons, NASA, and optionally Pexels/Unsplash/Pixabay) with license, orientation, and size filtering, then inspecting URLs and safely downloading chosen images with | |
| AtlasRepo MCP arnon-hs/atlasrepo-mcp Enables read-only access to the AtlasRepo decision catalog, allowing users to search for evidence-backed projects, tools, and repository decision records without loading the full catalog. | |
| Behance MCP Server arnonfr/behance-mcp-server A powerful Model Context Protocol (MCP) server for scraping Behance.net. Extract projects, user profiles, images, and job listings from Behance's creative community without any API keys or subscriptions. | |
| facebook-mcp-video-reels arnost55/facebook-mcp-video-reels Enables authentication with Facebook and provides tools to list pages, post text/images, upload videos, and create Reels on Facebook Pages. | |
| mcp-server-qnap-qvs arnstarn/mcp-server-qnap-qvs Manages QNAP Virtualization Station (VMs, snapshots, disks, ISOs) via the QVS REST API, enabling VM lifecycle operations and resource monitoring through natural language. | |
| mcp-server-splunk-oncall arnstarn/mcp-server-splunk-oncall MCP server for the Splunk On-Call (VictorOps) API providing comprehensive incident management, on-call schedules, team administration, and alert reporting through natural language. | |
| Agent Owl MCP Server arnwaldn/agent-owl Agent Owl provides cryptographic file integrity monitoring, OWL/RDF semantic knowledge graphing with SPARQL queries, and EU AI Act compliance tracking for Claude Code via 15 MCP tools covering file verification, compliance management, and p | |
| deepseek-web arnyigor/deepseek-local-server Enables MCP clients to ask questions and continue conversations with DeepSeek's web interface, with Expert mode and DeepThink reasoning enabled, without needing an official API key. | |
| WebdriverIO MCP Server arociris/webdriverio-mcp-server A Model Context Protocol server that acts as a bridge, allowing LLMs and AI agents to control a web browser using WebdriverIO. | |
| Signal K MCP arodus/signalk-mcp Enables clients to discover and read authorized vessel telemetry, state snapshots, and historical data, and to inspect and invoke approved read-only core or plugin operations over Streamable HTTP. It reuses the existing Signal K bearer toke | |
| moneybags aroesec/moneybags Lets you query your personal finances in plain language, log expenses, and correct transaction categories through a secure MCP endpoint. | |
| Garmin MCP Server arohiabhilasha/garmin-mcp-server A local, read-only MCP server that allows Claude Desktop to access Garmin Connect data such as activities and recovery metrics, enabling AI-assisted running plan creation and adjustment. | |
| VulnPilot arojit/vulnpilot-mcp An MCP server that gives AI assistants the ability to check open-source packages for vulnerabilities, enrich findings with real-world exploit intelligence, and statically analyse whether vulnerable code is actually reachable in your project | |
| Context Catalog MCP arokianisha/shopsense_agent-mcp Exposes schema, lineage, and data-quality trust signals from a SQLite-backed catalog as MCP tools, enabling AI agents to answer grounded questions about datasets without hallucinating. | |
| tempo-mcp arome3/tempo-mcp MCP server for Tempo blockchain stablecoin payments, enabling AI agents to autonomously execute real-world payments. | |
| mcp-ecom-agent-layer arone011-creator/mcp-ecom-agent-layer Enables AI agents to search products, manage carts, and cancel orders on the mcp-ecom storefront via HTTP, with server-enforced approval tokens for high-risk actions. | |
| fansly-mcp aronjesusfj-lang/mcp-fansly MCP server for Fansly account analytics using your own session, storing metrics in local SQLite. Provides tools for profile metrics, post performance, top fans, churn, and more. | |
| MCP Image Validator aronmav/mcp-image-validator Enables Claude and other MCP clients to analyze and describe images using the Qwen3-VL vision model (235B parameters) through Ollama Cloud API, supporting multiple image formats without requiring local GPU. | |
| zoom-mcp aronroyca/zoom-mcp Provides AI agents with structured access to Zoom recorded meetings, enabling search, summarization, and action item extraction. | |
| weather_mcp aronsoldok/checking_weather_mcp Provides a weather forecast tool that accepts a city name (in Russian or English) and returns a 7-day forecast with temperature, precipitation, and wind data via the Open-Meteo API. | |
| cad-mcp arookie127/cad-mcp Enables an LLM to design parametric 3D parts in pure NumPy and verify they are actually printable before exporting them. Provides topology checks (watertightness, genus, shell count, wall thickness), self-rendered views, and gated STL/OBJ e | |
| A2RG Obsidian MCP arosentiehl24/a2rg.obsidianmcp Enables MCP clients to read, write, append, delete, search, list, and inspect linked or active files in a local Obsidian vault, using a desktop bridge when Obsidian is running and a filesystem fallback otherwise. | |
| omp-mcp arosyihuddin/omp-mcp Wraps Oh My Pi built-in tools (read, write, edit, bash, grep, etc.) as MCP tools, enabling file operations, shell commands, web search, and agent coordination. | |
| mcp-teamline aroy314/mcp-teamline Enables MCP hosts to call the Teamline API for user authentication, task listing, creation, completion, and webhook management. | |
| kreta arpadtamasi/uzenofuzet Enables Claude to query your KRÉTA student data locally and read-only, including timetables, homework, grades, tests, and absences, using your own credentials via OAuth/PKCE. | |
| sql-copilot arpan018/sql-copilot Enables AI assistants to inspect PostgreSQL schemas and table metadata, preview SELECT queries with capped rows, and receive write or DDL statements for manual review without execution. | |
| Agent World arpan1221/agent-world Provides a local, vendor-agnostic control room where coding agents can be assigned tasks, exchange scoped messages, submit claims, and have work reviewed across different models, with a voxel-world interface for inspecting sessions and evid | |
| claudex arpan1221/claudex Enables Claude Code and Codex to exchange messages through a shared local file-based mailbox, allowing them to hand off tasks and report back without a server or tokens. |
30,551–30,600 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.