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 |
|---|---|
| LK Transit MCP appkade/lk-transit-mcp Enables MCP clients to explore Sri Lankan transit data offline by finding nearby stops, searching and retrieving routes with ordered stop sequences, checking scheduled arrivals, and inspecting feed coverage status. All results come from bun | |
| Appknox MCP Server appknox/appknox-mcp-depcrecated A Model Context Protocol server that wraps the Appknox CLI for mobile application security testing. | |
| rpcclient-mcp appknox/rpcclient-mcp MCP server for iOS automation via rpcclient, enabling AI agents to connect to iOS RPC servers and perform actions like launching apps, clicking, typing, and gesture control. | |
| Dokploy MCP Server apple-techie/dokploy-mcp A middleware service that allows LLMs and AI assistants to directly interact with the Dokploy platform through a standardized interface, providing access to Docker, project, and application management capabilities. | |
| deep-alley apple2000238/deep-alley Enables AI agents to run a virtual late-night bar in a shared alley world—mixing drinks, managing the bar, taking quests, and interacting with 50 residents through MCP tools, with the same save shared with a web frontend. | |
| skills-wiki appleaa123/skills_wiki_opensource Enables agents to route each request to the right installed skill, load selected skills, and record or list corrections as learnings through five fixed MCP tools. | |
| Skills Wiki appleaa123/skills-wiki AI skills marketplace, management and connector | |
| Bankr Industrial Customs MCP appleabram/bankr-customs-mcp Enables AI agents to perform international trade operations such as calculating landed costs, classifying goods, explaining trade terms, estimating shipping, and converting currencies for Kazakhstan/EAEU/Central Asia trade routes. | |
| Bankr Industrial Customs MCP appleabram/bankr-customs-mcp-v2 MCP server for international trade operations focused on Kazakhstan/EAEU/Central Asia routes, providing tools for landed cost calculation, HS classification, Incoterms guidance, logistics estimation, and currency conversion. | |
| bankr-registry-mcp appleabram/bankr-registry-mcp Central discovery point for 361 x402 capabilities, enabling AI agents to search by task, category, or keyword and retrieve structured capability cards. | |
| NearNow applecore2002-sketch/nearnow Enables AI assistants to find nearby public places such as pharmacies, supermarkets, gas stations, EV chargers, libraries, and post offices, with attributed opening-hours data from OpenStreetMap. | |
| Context Pilot applehell/contextpilot MCP server providing persistent, searchable memory management for AI workflows, enabling Claude Code to store, retrieve, and organize context through CRUD operations and knowledge tools. | |
| Baidu Search MCP Server appleinmusic/baidu-search-mcp Enables AI assistants to perform intelligent web searches using the Baidu Wenxin API, supporting multiple models, search modes, and providing search results with reference sources. | |
| TanukiMCP applejax2/wordpress-mcp A comprehensive MCP server for WordPress automation that enables users to manage content, themes, and site configurations using AI-driven workflows and the WordPress REST API. It provides a wide array of tools for site planning, management, | |
| Agentic Browser applejuice093/agentic-browser Enables agents to control a real Chromium browser with semantic tools, providing compact observations and outcome-verified actions for web interaction tasks. | |
| NULL / REBIRTH applekeynote/null-rebirth Enables users to run a simulated Alexa+ conversation that checks incident status, plans missing evidence, prepares and confirms bounded AWS recovery repairs, applies approved fixes, and reports verified signed evidence. It also provides rea | |
| MemoryPatch applelamps/memorypatch A local MCP memory server for AI agents to manage memory with evidence-backed, versioned mutations, using SQLite with FTS5 for storage and search. | |
| sample-mcp-server applemk2-git/mcp-server-with-fastapi_mcp Provides current weather information for Japanese cities using the Open-Meteo API. A sample MCP server built with FastAPI_MCP to demonstrate integrating MCP with FastAPI. | |
| a-blog cms MCP Server appleple/acms-mcp-server Enables searching and retrieving content, module information, and Twig template snippets from a-blog cms via its GET API. | |
| google-calendar-mcp-lib appler1009/google-calendar-mcp-lib A Google Calendar MCP server that enables listing, creating, updating, and deleting calendar events and calendars through natural language. | |
| Meta MCP Search appler1009/meta-mcp-search Provides a semantic search interface that enables discovery and routing across over 1,000 local MCP tools using natural language queries. It leverages hybrid search and embeddings to accurately match user intent with tool names and descript | |
| Remote MCP Server (Authless) apples2gotoday/remote-mcp-server-authless A Cloudflare Workers-based Model Context Protocol server that can be deployed without authentication requirements, allowing users to create custom AI tools accessible from Cloudflare AI Playground or Claude Desktop. | |
| OpenInputBridge-MCP applet-llc/openinputbridge-mcp An MCP server that exposes OpenInputBridge's kernel-level keyboard/mouse driver as tools, enabling AI agents to send synthetic key and mouse input for GUI/native app test automation. It includes safety gates, rate limiting, and an exclusive | |
| Eufy RoboVac MCP Server appleton/sam A Model Context Protocol server for controlling Eufy RoboVac vacuum cleaners, enabling users to scan for devices, connect to them, and execute various cleaning commands through natural language. | |
| websearch-deepseek applex250/websearch-deepseek-go An MCP server that provides web search powered by DeepSeek's native search API, returning AI-generated answers with source links. Integrates with MCP-compatible clients like Claude Code and Cursor. | |
| ableton-mcp-loopback applicate2628/ableton-mcp-loopback A loopback-bound MCP server that enables MCP clients to control Ableton Live (set tempo, create tracks/clips, add MIDI notes, start/stop playback) over a secure local-only connection. | |
| sparky-bonzai-bridge applied-ai-solutions-hub/sparky-bonzai-bridge Enables the BonzAI app on iPhone/iPad to delegate tasks to an OpenClaw agent on a home PC, providing tools for requests, job results, notes, inbox, and status. | |
| AAS LanceDB MCP Server applied-ai-systems/aas-lancedb-mcp Provides AI agents with database-like operations over LanceDB with automatic BGE-M3 multilingual embedding generation, enabling semantic search, CRUD operations, and safe schema migrations across structured data. | |
| mcp-search-kivest appliedellipsis/mcp-search-kivest Provides AI-powered search, web search, image search, video search, news search, and web scraping via Kivest AI Search API, with smart rate limiting and request queuing. | |
| Frappe MCP Server appliedrelevance/frappe-mcp-server Enables interaction with Frappe Framework sites through comprehensive document operations, schema introspection, report generation, and method execution. Provides secure API-based access to create, read, update, and delete Frappe documents | |
| blipr-mcp applogico/blipr-mcp Enables AI agents to send push alerts to your phone via Blipr, useful for notifying when tasks complete, builds break, or approvals are needed. | |
| Jira + GitHub MCP server applycoding/mcp-jira-github-server Enables AI agents to interact with Jira and GitHub through MCP tools, including searching, creating, commenting on, and transitioning Jira issues and listing pull requests, summarizing diffs, creating issues, and commenting on GitHub. | |
| sap-abap-mcp-server appmaster3000/sap-abap-mcp-server Enables MCP clients to connect to SAP S/4HANA on-premise systems, providing developer-grade read and write access to ABAP source, DDIC objects, table data, syntax/ATC checks, debugging, and transport management. | |
| Appmixer MCP appmixer-ai/appmixer-mcp Enables LLMs to automate workflows and interact with SaaS products and APIs through Appmixer's integration platform. It provides tools for managing automation flows and dynamically exposes custom tools via an MCP Gateway. | |
| MCP Local FastMCP Server appnucleus/mcp.local A FastMCP server providing web search, scraping, image extraction, and mail placeholders, with persistent storage and Docker deployment. | |
| Appo MCP appolabs/appo-mcp An MCP server that streamlines the integration of the @appolabs/appo SDK into web applications by providing tools for code generation, setup validation, and debugging. It enables AI assistants to generate React hooks and components for mobi | |
| Utility Belt MCP appoloncel283-debug/utility-belt-mcp Provides deterministic, stateless tools for common data work including JSON, CSV, text, encoding, hashing, IDs, date/time, and number statistics. | |
| @appouse/godaddy-dns-mcp appouse/godaddy-dns-mcp MCP server for managing GoDaddy DNS records. Enables listing, adding, replacing, and deleting DNS records, and checking domain availability via natural language. | |
| mcp-appstore appreply-co/mcp-appstore This is an MCP (Model Context Protocol) server that provides tools for searching and analyzing apps from both the Google Play Store and Apple App Store. | |
| mcp-pushinator appricos/pushinator-mcp Pushinator MCP lets you send push notifications to your devices from your LLM-powered workflows. | |
| debugger apps-in-toss-community/debugger MCP server for remote debugging of Apps in Toss mini-apps, providing CDP relay and test runner capabilities. | |
| AppsAI MCP Server appsai-inc/mcp-server Enables AI agents to build, deploy, and manage full-stack applications on AppsAI's platform, with tools for project management, backend/frontend deployment, billing, marketplace, domains, and more. | |
| sap-claude-mcp appsap2026/sap-claude-mcp Enables Claude Code to connect to SAP systems via ADT, allowing it to search ABAP objects, read source code, run read-only SQL queries, and check connection status. | |
| Google Search Console MCP Server appscaptain/mcp-gsc-readonly Connects Google Search Console to AI assistants, enabling natural language analysis of SEO data. Provides read-only tools for properties, search analytics, URL inspection, and sitemaps. | |
| AppSignal MCP Server appsignal/appsignal-mcp The official AppSignal MCP Server | |
| TealFlowMCP appsilon/tealflowmcp Enables LLMs to discover, understand, and generate Teal R Shiny applications for clinical trial data analysis. | |
| AdSense-MCP-Server appsyogi-com/adsense-mcp-server Connects Google AdSense to MCP clients like Claude and Cursor, enabling earnings summaries, detailed reports, site status checks, and more via natural language. | |
| GSC-MCP-Server appsyogi-com/gsc-mcp-server Connects Google Search Console to MCP clients to query search analytics, manage sitemaps, and perform URL inspections. It enables users to identify SEO opportunities and generate performance reports through natural language interactions. | |
| Coverage MCP appunni-m/coverage-mcp A local coverage history server that stores coverage snapshots in DuckDB and provides MCP tools for LLMs to query coverage data without reading large reports. | |
| barcode-mcp appvantagelabs2-a11y/barcode-mcp Enables AI agents to decode and render barcodes/QR codes and validate GTINs via the Model Context Protocol, with both hosted and self-hosted deployment options. |
29,951–30,000 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.