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 |
|---|---|
| arc-mcp andrewgazelka/arc-mcp Enables semantic browser automation for the Arc browser, allowing users to perform web tasks like searching, shopping, and data extraction through natural language commands. | |
| MCPuppet andrewgevans95/mcp-workflow-orchestrator MCPuppet is a workflow orchestrator that enforces policies, audits tool calls, and monitors workflow execution for AI applications using MCP servers. | |
| Oculus MCP andrewgilley/oculus-mcp Enables read-only MCP clients to list tracked projects, saved activity items, and persisted inspection overviews from Oculus.nvim's JSON state, including cached AI explanations and suggested patch locations. It does not modify Oculus state | |
| recall andrewhomeyer/recall-mcp Gives AI assistants a persistent memory across conversations, allowing them to remember user preferences, notes, and facts between chats. | |
| ITMCP andrewhopper/itmcp Secure network administration MCP server that enables AI assistants to safely execute networking commands like SSH, ping, and DNS lookups inside a Docker container sandbox. | |
| Rumble MCP andrewhossam/rumble-mcp Provides AI assistants with access to TheRumble.app investment research data for the Egyptian stock market (EGX), including fundamental calls, technical calls, track records, and portfolios. | |
| io.github.Hylouis233/bibverify andrewj43368/bibverify Enables AI assistants and researchers to verify bibliographic records against multiple metadata sources, detect identifier conflicts, and review explainable match outcomes without destructively editing source files. | |
| Citation Safe andrewjgaber-commits/citation-safe-mcp Deterministic legal citation verification for AI-generated legal briefs. Three-layer verification: CourtListener database lookup, quote-match against primary source, and LLM edge-case verification. Free tier available. | |
| Planning MCP Server andrewjgalea/planning-mcp Provides comprehensive Australian planning property reports, including zoning, overlays, land size, and utility information for AI assistants. This high-performance MCP server is built for Cloudflare Workers and enables real-time property d | |
| Google Search Console MCP andrewjpyle/google_search_console_mcp Provides AI assistants with live access to Google Search Console search analytics, URL inspection, and sitemap management through real API calls. | |
| MCP Fivetran andrewkkchan/mcp_fivetran A server implementation that enables AI assistants to interact with Fivetran's API, allowing for user management, connection listing, and triggering syncs. | |
| Gaggiuino MCP Server andrewklement/gaggiuino-mcp A lightweight server that enables AI clients to access and analyze real-time data from Gaggiuino espresso machine controllers through a simple HTTP API. | |
| shop-mcp andrewkonst/shop-mcp Enables AI agents to read-only analyze a SQLite e-commerce database, exploring schema and running analytical SQL queries over stdio. | |
| Unreal Engine MCP Server andrewkorot/mcp-server-unreal-engine Enables AI assistants to control and automate Unreal Engine through a native C++ Automation Bridge plugin. It supports a comprehensive range of tasks including asset management, actor manipulation, editor control, and blueprint graph editin | |
| supabase-model-context-protocol-server andrewkorot/supabase-model-context-protocol-server MCP server for exploring and querying Supabase databases with interactive React widgets for schema browsing, table viewing, and SQL execution. | |
| cloudflare-dns-cloudflared-mcp andrewkriley/cloudflare-dns-cloudflared-mcp Self-hosted MCP server for administering Cloudflare DNS and cloudflared tunnels, enabling exposure of SSH hosts and web services with Google OAuth access control. | |
| imessage-mcp andrewkriley/imessage-mcp An MCP server that exposes Apple iMessage as tools for AI assistants, enabling reading, searching, and sending iMessages through natural language. | |
| gsheets-mcp andrewkushnerov/gsheets-mcp A small, self-hosted MCP server that gives Claude read/write access to your Google Sheets via the official Sheets API, with local-first security and guard rails. | |
| Codex Gemini Web Bridge andrewli1994/gemini-web-bridge Enables Codex to interact with Gemini Web through browser automation, allowing it to ask scoped questions and analyze public URLs or YouTube videos without a Gemini API key. | |
| ThinkRail andrewliu83/claudecodexthinkrail Enables CLI coding agents to read, query, create, update, delete and validate a project's spec graph through seven spec_* tools, so specs act as the ground truth for every piece of work. The tools are exposed over an MCP stdio server that r | |
| Google Trends MCP Server andrewlwn77/google-trends-mcp Provides access to Google Trends data including status, trending questions, and trending topics via MCP tools. | |
| Kie.ai MCP Server andrewlwn77/kie-ai-mcp-server Enables AI-powered image generation and editing with Nano Banana, plus professional video creation with Veo3, all through Kie.ai's APIs. Includes task tracking, status monitoring, and 1080p video upgrades. | |
| n8n-workflow-downloader-mcp andrewlwn77/n8n-workflow-downloader-mcp An MCP server that enables AI agents to download n8n workflows from URLs. | |
| NocoDB MCP Server andrewlwn77/nocodb-mcp Enables AI agents to interact with NocoDB databases for managing tables, records, views, and file attachments. Supports advanced queries, bulk operations, and full CRUD functionality for storing operational data. | |
| Qdrant MCP Server andrewlwn77/qdrant-mcp Provides semantic memory capabilities using Qdrant vector database with configurable embedding providers, allowing storage and retrieval of information using vector similarity. | |
| undetected-chrome-mcp andrewlwn77/undetected-chrome-mcp Provides browser automation with enhanced anti-detection using undetected-chromedriver, enabling robust web scraping and interaction with sites that employ bot protection measures. It is fully compatible with server-puppeteer and includes n | |
| mcp-imap andrewmalov/mcp-imap Enables AI agents to interact with email accounts via IMAP and SMTP, supporting mailbox listing, email search, retrieval, sending, and management. | |
| apple-docs andrewmason7/apple-doc-plugin Enables AI agents to search and retrieve Apple Developer Documentation instantly with symbol search, wildcard matching, and optional semantic embeddings. | |
| x-search andrewmason7/x-search-tool Enables asynchronous search of recent and full-archive X (Twitter) posts, retrieval of post volume trends, lookup of individual posts, and tracking of API rate limits through the X API v2. | |
| B&R Automation Studio MCP Server andrewmusser/br-automation-mcp Enables AI assistants to interact with B\&R Automation Studio projects by building code, running ARsim simulators, and reading or writing OPC UA variables. It facilitates industrial automation development and real-time variable integration | |
| EdgeFinder andrewnexys/edgefinder-cli CLI and MCP server for EdgeFinder sports analysis. Get AI-powered NFL, NBA, and MLB betting recommendations, player stats, odds, schedules, and Polymarket portfolio tracking from your terminal or AI agent. | |
| mnemoth andrewngo-ini/memoose Enables coding agents to persist and retrieve a typed knowledge graph with ontology, hybrid search, contradiction tracking, and session memory through MCP tools and skills, all without an API key. | |
| agentmemo-mcp andrewpetecoleman-cloud/agentmemo-mcp Persistent memory and human approval for any AI agent.
Give your AI agents the ability to remember across sessions and ask humans for approval before sensitive actions. Works with Claude, Cursor, OpenClaw, and any MCP-compatible client. | |
| odoo-bookkeeping-mcp andrewraof/bookkeeping-mcp MCP server that provides full read/write access to Odoo accounting data including invoices, vendor bills, journal entries, payments, reconciliation, and financial reports, as well as BOQ/Project Budget data when available. | |
| mcp-connector-pattern andrewrozumny/mcp-connector-pattern A reference MCP server for a fictional bike shop that enables managing customers, inventory, orders, and outbound messages, demonstrating best practices for building MCP servers. | |
| allegro-mcp-searcher andrewsakhno/allegro-mcp-searcher Enables Claude Desktop to search products on Allegro.pl by translating user queries into Polish and querying the Allegro API. | |
| Healthcare MCP Server andrewsalopek1/healthcare-mcp-server Enables AI assistants to retrieve and search authoritative healthcare data, including FDA drug information, PubMed literature, health topics, clinical trials, ICD-10 terminology, medRxiv preprints, NCBI Bookshelf content, BMI calculations, | |
| project-fmod-api andrewsetness/project-fmod-api Enables bounded, schema-validated automation of FMOD Studio game audio through MCP/CLI workflows, including inspection, safe mutations, previews, receipts, and high-level workflows for events, assets, parameters, adaptive music, spatial aud | |
| project-supabase-api andrewsetness/project-supabase-api Enables AI agents to safely interact with Supabase through read-only and gated-write tools, with bounded queries, allowlists, and explicit project targeting. | |
| opencomputeruse andrewslabmd/opencomputeruse Enables agents to observe and operate native macOS apps in the background—reading windows, controls, and text along with optional screenshots—and to click, type, scroll, drag, and invoke Accessibility actions in a target app without moving | |
| Azure Assistant MCP andrewstephenson-v1/azure-assistant-mcp Enables natural language exploration of Azure environments by generating and executing KQL queries against Azure Resource Graph. Supports multi-tenant configurations, subscription scoping, and provides direct access to Azure resource inform | |
| agent-versions andrewttofi/versions Enables AI coding agents to fetch the real latest versions of packages from npm, PyPI, crates.io and the Go module proxy, then check manifests or whole projects for outdated dependencies and rewrite them in place. It also reports the curren | |
| openSensus andrewuetyang/opensensus Enables AI agents to query permission-filtered world views, inspect evidence-backed signals, and trace timelines across integrated enterprise systems, handing deep investigation off to vertical MCP servers via verified capabilities. | |
| mcp-chinookdb-server andrewwgordon/mcp-chinookdb-server MCP server providing LLMs with safe, read-only access to the Chinook SQLite sample database, including schema exploration and SQL query execution. | |
| mcpaudit andrewxuturtle/mcpaudit Audits MCP server configurations and packages for security risks such as typosquats, credential exposure, and malicious code, with zero dependencies and no execution. | |
| Jira 9.12.14 MCP Server andrewyun0403/jira-9.12.14-mcp-server Enables AI models to search Jira issues using JQL and retrieve issue details through the Jira 9.12.14 API. | |
| ae-agent-lab-demo andrexes03/ae-agent-lab-alpha Enables Codex to inspect a native After Effects project, make scoped edits, and render frames for review through a local macOS bridge. It exposes MCP tools that drive a named After Effects worker without requiring an in-app panel or separat | |
| Liberty Browser andrey-barros-dev/liberty-browser Enables agents and CLI users to drive their locally installed Google Chrome through a dedicated persistent profile over the DevTools Protocol, so they can navigate open HTTP/HTTPS sites, manage tabs, and inspect pages while keeping existing | |
| MSXLab andrey-dymov/msxlab Enables AI agents to control an MSX emulator for debugging and reverse-engineering, including memory and code inspection, execution control, and saving annotations via MCP. | |
| MCP Desktop Tools andrey-zhuravl/mcp-desktop-tools Enables searching text across configured local workspaces using ripgrep. Provides secure text search capabilities within defined workspace boundaries through both MCP server and CLI interfaces. |
28,801–28,850 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.