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 |
|---|---|
| mcp-grounding alxnhfr-bit/mcp-grounding An MCP server that exposes a verify_place tool for verifying places via Google Places API, along with a rubric resource and classify_post prompt for grounding-based classification tasks. | |
| Grove alxshelepenok/grove A machine-enforced workflow protocol for AI coding agents that eliminates false progress. Tasks require verifiable evidence to close, while decisions, assumptions, and open questions persist in a versioned reasoning graph for seamless agent | |
| AI Meta MCP Server alxspiker/ai-meta-mcp-server Enables AI models to dynamically create and execute their own custom tools through a meta-function architecture, supporting JavaScript, Python, and Shell runtimes with sandboxed security and human approval flows. | |
| MCP Server for FTP Access alxspiker/mcp-server-ftp Enables Claude to interact with FTP servers through natural language commands, allowing users to list directories, download/upload files, create directories, and delete files/directories on FTP servers. | |
| Windows Command Line MCP Server alxspiker/windows-command-line-mcp-server A secure Model Context Protocol server that allows AI models to safely interact with Windows command-line functionality, enabling controlled execution of system commands, project creation, and system information retrieval. | |
| Hostinger API MCP Server alxubuntu/america-hostinger-mcp Enables management of Hostinger services, allowing users to deploy WordPress sites, themes, and plugins, as well as manage JavaScript and static website deployments. It also provides tools for retrieving billing catalog items and monitoring | |
| NECTARIN Intelligence MCP Server alxvasilevvv/nectarin-intelligence-worker MCP server for AI-powered marketing intelligence and automation for the RU/CIS market, offering tools for media planning, benchmarks, competitor analysis, and funnel conversion. | |
| TokenFluid MCP Server alyanjamalkhan-create/tokenfluid-mcp Enables AI assistants to safely interact with local code repositories through MCP tools for search, context building, and workspace management, while keeping all operations local and human-controlled for patch approval. | |
| Conduit alyhnte/conduit Connects MCP clients to radare2, x64dbg, cdb, and Frida for disassembly, control-flow graphs, cross-references, strings, and live debugging over stdio or HTTP. | |
| MCP SQL Server alyiox/mcp-mssql A read-only-by-default Model Context Protocol (MCP) server for Microsoft SQL Server with schema discovery, SELECT-only queries, execution-plan analysis, and opt-in writes per profile. Profile-based configuration serves multiple databases an | |
| mcp-samsclub-ads alyiox/mcp-samsclub-ads Deprecated. This server has merged into mcp-walmart-ads (>= 0.2.0), which serves the same 28 Walmart Marketplace domains alongside Walmart Connect Ads and Sam's Club Sponsored Ads. | |
| mcp-walmart-marketplace alyiox/mcp-walmart-marketplace Deprecated. This server has merged into mcp-walmart-ads (>= 0.2.0), which serves the same 28 Walmart Marketplace domains alongside Walmart Connect Ads and Sam's Club Sponsored Ads. | |
| Mural MCP alymohamedhassan/mural-mcp MCP server for interacting with Mural's public API, enabling browsing and management of workspaces, rooms, murals, and widgets within Mural. | |
| waggle-mcp alyssa2ai/waggle-mcp Provides coding agents with persistent graph-backed memory, storing decisions, reasons, and contradictions across sessions so conversations pick up where they left off. | |
| Edit Twin MCP alyssasworld/edit-twin-mcp Enables Claude Code to read Final Cut Pro projects, plan and apply non-destructive rough cuts, add saved colour and dialogue sound, and learn from manual edits to better match the user's editing style. | |
| garmin-mcp alyssindewonderland/garmin_mcp Connects Claude to a personal Garmin Connect account so users can ask natural-language questions about sleep, HRV, body battery, stress, heart rate, training readiness and activities, and optionally create or schedule workouts and log weigh | |
| FreshRSS MCP Server alysson-souza/freshrss-mcp Enables interaction with FreshRSS instances through the Google Reader API. Supports managing articles, feeds, folders, labels, and OPML import/export for RSS feed aggregation through natural language. | |
| HiveAuth MCP Server alyssonm/hiveauth-mcp A Model Context Protocol (MCP) server that enables LLM applications to perform verifiable credential operations including issuing, verifying, revoking credentials and evaluating presentations within the HiveAuth ecosystem. | |
| SynapticRelay MCP server alzaxnsk-del/synapticrelay-mcp Enables AI agents to search multilingual freelance listings, post and manage offers, send messages, and negotiate deals with human approval via Telegram. | |
| readpic-mcp alzeros/readpic-mcp Analyzes images using a vision model and returns detailed Chinese text descriptions, enabling text-only models to understand pictures from screenshots, UI designs, error logs, and architecture diagrams. | |
| universal-notebook-mcp am-3/jupyter-mcp Enables AI assistants to read, edit, and execute Jupyter notebook files (.ipynb) with live kernel output, without requiring JupyterLab. | |
| Controlium am-will/controlium Chrome extension + MCP bridge that gives Claude control over your real browser via CDP, enabling navigation, clicking, typing, scrolling, screenshots, and JS execution with a visible cursor and tab-bring-to-front. | |
| fal am0y/mcp-fal A Model Context Protocol (MCP) server for interacting with fal.ai models and services, enabling listing, searching, generating content, managing queues, and uploading files. | |
| Airtable MCP Server am1010101/airtable-mcp-sse A Model Context Protocol server that provides read and write access to Airtable databases, enabling LLMs to inspect database schemas, then read and write records. | |
| Ductor MCP Gateway am1010101/ductor-mcp-gateway An authenticated MCP Streamable HTTP server that exposes Ductor's internal API, enabling agent messaging and task management through MCP tools. | |
| S3 MCP Server am1010101/s3-mcp-server Enables interaction with S3-compatible storage services like AWS S3 and Cloudflare R2, supporting bucket management, object listing, reading, uploading, and deletion operations. | |
| AWS FinOps MCP Server am2308/finops-mcp Enables natural language analysis of AWS cloud costs, waste audits, and budget insights across multiple profiles and regions. | |
| mcp-web-search-server am24check/mcp-web-search-server Enables MCP clients to perform web searches and fetch web pages over HTTP, using Exa and Parallel AI as search providers without requiring API keys. | |
| metrc-mcp am253906/metrc-mcp MCP server for METRC cannabis track-and-trace API, focused on processor workflows like inventory checks, transfer reconciliation, and lab results, with read-only safety defaults. | |
| Google Calendar MCP Server am2rican5/mcp-google-calendar Integrates Google Calendar with AI assistants through the Model Context Protocol, allowing users to view and manage calendar events through natural language interaction. | |
| wordpress-mcp am333ni7y/ameeen-seo-agent A high-performance, enterprise-grade Model Context Protocol (MCP) server connecting WordPress sites directly to modern AI agents (Claude Code, Cursor, Google Antigravity, Windsurf, etc.).
Designed with a Dual-Engine Architecture and Zero-T | |
| Datto RMM MCP Server am3cramirez/dattormm-mcp Comprehensive read/write access to the Datto RMM API v2, enabling management of devices, sites, alerts, audits, jobs, variables, filters, and activity logs through 46 tools. | |
| saas-alerts-mcp am3cramirez/saas-alerts-mcp MCP server for Kaseya SaaS Alerts, providing 30 tools to manage security events, customers, users, devices, billing, and reports via the SaaS Alerts API. | |
| vulscan-mcp am3cramirez/vulscan-mcp A central MCP server that exposes fleet-wide vulnerability and PII scan findings to Claude, enabling natural language risk review across multiple clients. | |
| agentlens am5188/agentlens Enables MCP-capable agents to query trust scores, price benchmarks, and ranked agent lists for the OKX.AI marketplace, with premium tools for trust lookup, comparison, and task-based recommendations paid via x402. | |
| mcp-pwsh am6er/mcp-pwsh A persistent, pooled PowerShell MCP server that keeps long-lived named pwsh sessions with clean I/O, enabling stateful command execution and multi-session isolation. | |
| MCP Server Template amaanbilwar/wing-mcp A minimal FastMCP server template for quick deployment to Render with streamable HTTP transport. Provides a foundation for building custom MCP servers with easy local development and one-click deployment capabilities. | |
| ElevenLabs Agents Platform MCP amaanshaikh-dc/elevenlabs-agent-platform-mcp MCP server giving Claude full control over ElevenLabs Conversational AI agents, conversations, knowledge base, tools, tests, telephony, and workspace settings. | |
| Graft amaar-mc/graft Local-first codebase context engine that parses code into a ranked dependency graph and serves it to AI tools via MCP for deep structural understanding. | |
| WordPress MCP amabdomo/wp-custom-mcp A comprehensive WordPress plugin that implements the Model Context Protocol (MCP) to expose WordPress functionality through standardized interfaces, enabling AI models to interact with WordPress sites securely. | |
| oncrawl-mcp-server amaculus/oncrawl-mcp-server MCP server that exposes OnCrawl's API for use with Claude Code and Claude Desktop. Enables Claude to perform deep technical SEO analysis by querying crawl data, Google Search Console metrics, and crawl-over-crawl comparisons. | |
| christina amadeus-ex-machina/christina Enables AI coding agents to navigate massive codebases through fast code property graph queries, sandboxed recursive language model execution, durable semantic memory, and swarm concurrency coordination. | |
| Electron Debug MCP Server amafjarkasi/electron-mcp-server Enables debugging of Electron applications through the Model Context Protocol, with deep integration of Chrome DevTools Protocol for process management and advanced debugging capabilities. | |
| pcb-mcp amagtoto/pcb-mcp Enables AI assistants to read and modify KiCAD PCB designs through the KiCAD IPC API, providing tools for board queries, footprint placement, track creation, DRC, and export. | |
| Arduino MCP Server (Simple) amahpour/arduino-mcp-server-simple Enables AI agents to interact with Arduino boards for compiling, uploading sketches, and serial communication. | |
| google-sheets-mcp amahpour/google-sheets-mcp Enables Claude to read and edit individual cells and ranges in Google Sheets via a local stdio server, authenticating as the user with a one-time Google sign-in. | |
| Income Screener MCP Server amahpour/pyetrade-mcp Connects Claude to E\*Trade for income-oriented trading research, providing real-time quotes, option chain lookups, and put-sell candidate screening with annualized yield filters. | |
| Rigol DP832 MCP Server amahpour/rigol_dp832_mcp_server Controls Rigol DP832 programmable power supplies via Ethernet using VISA TCP/IP, enabling AI agents to manage channels, measurements, and protection settings. | |
| ProxmoxMCP amaialth/proxmoxmcp Enterprise MCP server for Proxmox VE, offering 298 tools to manage VMs, containers, storage, cluster, firewall, and more via natural language. | |
| Multi-Server FastMCP PR Reviewer amaimakhalidsethi/mcp-pr-reviewer A zero-cost, multi-server MCP suite that provides a unified gateway and LangGraph-based automated PR-review agent, enabling code analysis, GitHub operations, and documentation generation via free-tier APIs. |
27,851–27,900 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.