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 |
|---|---|
| OmniLiving+ MCP Server farhanmallik05/omniliving-plus Enables autonomous multimodal ambient security and living-room automation by exposing Ring, Fire TV, Bee wearable, Alexa+, and AWS Bedrock vision capabilities through MCP tools, resources, and prompts. | |
| KSOR MCP farhansaeed204/ksor_mcp Enables AI agents to query a governed knowledge base and receive cited answers, or explicitly decline when the record does not cover the question, preventing improvisation over gaps. | |
| QuestMCP farhanullah382/questmcp Enables AI agents to post real-world tasks, match them to people, and release payments through a delegation-based authorization system that enforces scoped, spend-capped permissions. | |
| student-mcp-server farheenrafiq20056-svg/mcp_server_project Enables AI assistants to call tools for adding numbers, evaluating math expressions, getting the current time, and counting words and characters. | |
| Intervals.icu MCP Server farhoodlabs/intervalsicu-mcp A self-hosted, multi-tenant MCP server that exposes the Intervals.icu API—activities, events, wellness, power curves, gear, and custom items—as MCP tools for Claude. | |
| Memento fariborzvrm/memento-mcp Gives AI coding agents persistent, searchable typed memory stored as plain markdown files, allowing them to record decisions, contracts, tasks, evaluations, and session logs and update entries by id. | |
| journal-search-mcp farid521/gemini-journal-search-swarm-mcp MCP server for searching and verifying academic journal PDFs. It uses Tavily search and Gemini Flash Lite to analyze PDF content and return structured JSON results. | |
| gemini-mcp farid521/gemini-mcp MCP server that exposes tools for document judging and summarization using Gemini Flash Lite, designed to be called by Claude. | |
| SSH Nexus MCP faridarjmand/ssh-mcp Enables MCP clients to list SSH hosts, test reachability, retrieve Linux resource metrics, index and search project files, and run remote SSH commands when allowed, with local-first and safety-focused operations. | |
| Hololive MCP faridhafizh/hololive-mcp Provides AI clients with read-only tools to browse a talent roster, fetch individual profiles and social links, and read recent announcements with full article content. | |
| WooCommerce Insights MCP faridhn2/mcpwcm Enables secure, read-only access to WooCommerce store data through MCP-compatible assistants, letting users query products, orders, sales summaries, and inventory alerts without exposing store credentials. | |
| basecamp-mcp farishijazi/basecamp-mcp MCP server exposing Basecamp CLI commands as tools for project management, todos, messages, and more. | |
| s3-mcp-agent farishussain/s3-mcp-agent Enables inspecting Amazon S3 buckets and safely transferring objects using your own AWS credentials, with read-only bucket/object inspection and guarded downloads/uploads. | |
| XiaoZhi MCP Bridge farisi55/xiaozhi-mcp-bridge Bridges MCP for XiaoZhi AI agent using Cloudflare Workers + Durable Objects, maintaining persistent WebSocket connection and enabling custom tool execution. | |
| apple-notes-mcp farmerajf/apple-notes-mcp MCP server for macOS that enables creating, reading, and searching Apple Notes programmatically through tools like find, get by title or ID, and create. | |
| Oculus Debug MCP farmerarmor/oculus-debug-mcp Enables Windows-based AI assistants to run Oculus/Meta Quest Link diagnostics, capture VR screenshots and telemetry, inspect headset/controller state, and apply reversible performance-tuning and Link settings. | |
| Ableton MCP farmhutsoftwareteam/ableton-mcp-extended Control your Ableton with this MCP and get started to make music | |
| aaws - AI-Assisted AWS CLI farmountain/ai_aws_cli A Python CLI package aaws published to GitHub with PyPI distribution via GitHub Actions. Natural language in → AWS CLI command out, with explain, confirm, and safety layers. Available as MCP server. | |
| Model Card Chat farnoosh-afshinrad/model-card-chat-mcp An MCP server that turns the Hugging Face Hub into a conversational model picker with a tool-use eval harness to prove the agent actually uses it correctly. | |
| Jarvis Onshape MCP farouk15160/jarvis-onshape-mcp Enables Claude to create and modify real Onshape CAD models — sketches, extrudes, fillets, patterns, mates, and parametric variables — with every mutation returning structured status, warnings, and geometric deltas. Includes multi-view PNG | |
| shop-database farranfox/shop-mcp Enables safe read-only analysis of a local SQLite e-commerce database over stdio, providing tools for schema inspection and parameterized SELECT queries. | |
| Godot MCP Bridge farrasfadhils/godot-mcp Enables AI assistants to control Godot game engine projects through a WebSocket bridge. Supports scene editing, node manipulation, script management, and project introspection via 163 registered tools. | |
| SolanaViz MCP Server farseensh/goatsolana-mcp Enables Claude to access, analyze, and visualize Solana blockchain data through natural language conversations. | |
| Slack Notifier MCP Server farsght/slack-notifier-mcp-server An MCP server that connects to Slack via Socket Mode (WebSocket) and surfaces real-time message notifications through MCP tools. No public URL or ngrok needed. | |
| slack-user-mcp-server farsght/slack-user-mcp-server Enables AI agents to interact with Slack using a user token, providing full access to message search, channel history, DMs, and posting as the user. | |
| Farhan Agent Bridge farshaikh17/farhan-agent-bridge Enables delegating local background tasks through an existing Codex or Claude Code subscription login and retrieving their status, answers, and usage. | |
| Prompt Refinery MCP Server farukalpay/prompt-refinery Retrieval-grounded prompt refinement engine that repairs and polishes prompts via a single LLM call, exposing a refine_prompt tool for integration with MCP-compatible hosts. | |
| image-generation-mcp farukcan/image-generation-mcp Enables MCP-capable agents to generate and edit images through Gemini or OpenAI, returning an absolute file path instead of image bytes to keep context windows clean. | |
| Lumina farukes/lumina Enables AI coding assistants to generate bespoke design systems by synthesizing OKLCH color palettes, chamfer highlights and spring physics, teaching layout composition grammar, and returning micro-interaction primitives and component bluep | |
| SpinupWP MCP Server farukgaric/spinupwp-mcp Enables AI assistants to manage SpinupWP infrastructure, including servers, WordPress sites, and SSH keys through the SpinupWP v1 JSON API. Users can perform actions like provisioning sites, purging caches, and restarting services via natur | |
| Playwright MCP Server faruklmu17/playwright_mcp Enables web browser automation and inspection using structured data instead of screenshots, allowing AI agents to interact with web pages programmatically through the Playwright framework. | |
| mcp_project farukomer21/mcp_project Provides read-only tools for querying a synthetic e-commerce dataset, including product categories, products, sales data, customer history, and order details. | |
| Azure AI Search MCP Server farzad528/mcp-server-azure-ai-agents Integrates Claude Desktop with Azure AI Search, allowing users to query search indexes using keyword, vector, or hybrid search methods. | |
| MCP-CAN farzadnadiri/peykan Enables LLMs to interact with vehicle CAN bus and OBD-II data through a simulated ECU environment. Provides tools for reading frames, decoding messages via DBC files, monitoring signals, and querying automotive diagnostics without requiring | |
| factledger-mcp fas988840-dev/factledger Deterministic read-only Solana wallet intelligence and risk evidence MCP server with 8 tools for wallet analysis, risk scoring, transaction-cited evidence graphs, SPL token security, and live token pricing. | |
| Unyly Gateway fasadsalatov/unyly-gateway One connector for the whole MCP catalog — 15,000+ servers plus your team's private MCPs — callable from Claude, ChatGPT, Cursor and VS Code through a single OAuth endpoint. No per-server install. | |
| Inspectra fascinax/inspectra Enables hybrid code audits using MCP tools across 12 domains, producing structured, scored, and actionable code quality reports. | |
| AutoFuse fasen24-ai/autofuse Mount, heal, wake and run commands on remote Windows/Linux machines over SSHFS from a macOS menu-bar app. 34 tools with MCP behavior annotations (read-only vs destructive) and agent-friendly error hints. | |
| StreamXpress MCP Server fasenchen/streamxpress_mcp Enables AI to control DekTec StreamXpress for TS stream playback, including file loading, rate adjustment, and TS-over-IP/RF output configuration through remote control. | |
| Universal Database MCP Server fashad-ahmed/universal-db-mcp Enables AI agents to securely query databases (PostgreSQL, SQLite, MySQL, DuckDB) with read-only defaults and multi-layer SQL injection prevention. | |
| markdown-to-html fashionzzz/markdown-to-html A Model Context Protocol server that converts Markdown content to HTML format. | |
| LiveBrain MCP fasping/livebrain-ableton-mcp Enables AI agents to control Ableton Live 12 for music production, including generating grooves, basslines, and percussion, and executing live set operations through MCP. | |
| PriceHunt MCP Server fassihshah/pricehunt-mcp Enables searching and comparing products across Pakistani e-commerce platforms Daraz, Telemart, and iShopping, filtering by price and ratings. | |
| Lodgify MCP Server fast-transients/lodgify-mcp-server Enables interaction with the Lodgify vacation rental API to manage properties, bookings, and calendar data. It provides tools for retrieving property details, creating or updating bookings, and monitoring rental availability. | |
| PlainGov-MCP fasterinnerlooper/plaingov-mcp Retrieves and explains government program information from official Canadian sources using a strict retrieval-first approach, with deterministic eligibility checks and full source attribution. | |
| logflare-mcp fasterv410/logflare-mcp Enables querying and managing Logflare log sources, endpoints, and executing ad-hoc SQL via MCP. | |
| Fastlanepy MCP Server fastlanepython/fastlanepy-mcp A Model Context Protocol server that extends Claude's capabilities by providing tools to interact with the Solana blockchain, allowing AI agents to perform operations like executing transactions, managing wallets, and accessing token inform | |
| @fastly/mcp fastly/mcp Enables assistants to interact with the Fastly API, allowing them to manage services, domains, TLS settings, traffic, dictionaries, ACLs, purge content, and make configuration changes. | |
| mcp-kaneo fastman/mcp-kaneo MCP server for Kaneo task management API. Lets your AI coding assistant manage tasks, projects, labels, and comments in Kaneo. | |
| AACT Clinical Trials MCP Server fastmcp-me/aact_mcp Enables querying clinical trial data from the AACT database (ClinicalTrials.gov) using natural language through tools like list_tables, describe_table, and read_query. |
49,651–49,700 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.