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 |
|---|---|
| eastmoney-skills2mcp essos-bot/eastmoney-skills2mcp Provides 11 MCP tools for querying A-share market data, financial reports, stock screening, hot topics, self-selected stocks, and LOF arbitrage using natural language, powered by East Money / Miaoxiang APIs. | |
| mcp-everything-search essovius/mcp-everything-search Integrates Everything file search with Claude Desktop, enabling instant Windows filesystem search via natural language queries. | |
| LoL Data MCP Server estaed/lol_data_mcp_server A comprehensive League of Legends data ecosystem that provides access to champion statistics, item data, and patch history via the Model Context Protocol. It enables analysis of game mechanics, build optimization, and meta tracking through | |
| mcp-facebook-ads estapel-ai/mcp-facebook-ads Enables managing Facebook ads campaigns, ad sets, ads, creatives, insights, and audience targeting via Meta's Marketing API. | |
| SolidworksMCP Local estasi/solidworksmcp-local Enables MCP-capable AI clients to control an interactive SOLIDWORKS 2025 session through a durable shared queue with whole-operation locking, document targeting, and explicit recovery. | |
| Estate Atlas SD-MCP estate-atlas/sandiego-mcp MCP server for querying the San Diego Municipal Code, bulletins, permits, parcels, and zoning data with citations and freshness guarantees. | |
| Guardian MCP Toolkit esteban-fonseca-dev/mcp_toolkit_guardian Real-time architecture governance tool that enforces Clean Architecture, DDD, SOLID, TDD, and Security rules across 8 languages using 11 specialized agents. | |
| SAP MCP Server estebandavila-amrize/template_workspace Enables natural language interaction with SAP systems via the ADT REST API, bridging Kiro IDE to SAP for development workflow management. | |
| Trello MCP Server estebanhiguitad/trello-mcp Enables interaction with Trello boards, lists, and cards using the Model Context Protocol. Supports operations like fetching boards, lists, cards, and searching across boards. | |
| Model Coupling Platform Server estebaniit/cs550_mcp A FastAPI-based JSON-RPC 2.0 server implementation that enables users to work with HDF5 files, submit Slurm jobs, retrieve CPU information, and visualize CSV data through standardized API endpoints. | |
| Chilipad MCP estebansolis/chilipad-mcp Enables an assistant to locally discover and control supported Sleepme bed devices, check water status, adjust temperatures, retrieve Sleep Tracker reports, and manage saved routines. | |
| WordPress MCP Hub estebanstifli/wp-mcp-hub A local MCP gateway that connects AI clients to multiple remote WordPress MCP servers, enabling tool discovery, testing, and invocation with secure authentication and centralized configuration. | |
| Testing Agent MCP Server estella219/ariadne-test-agent-system Provides self-healing UI/API test automation via Plan-Generate-Run-Heal cycle, exposing MCP tools for test platforms to trigger batches and retrieve reports. | |
| usps-epf-mcp estermer/usps-epf-mcp Enables an LLM to interact with the USPS EPF V2 REST Services API for listing files, requesting download manifests, streaming binary EPF files to disk, and updating file statuses. | |
| TMB Bus Arrival Times esteveavi/ibus-mcp Provides real-time bus arrival information for TMB (Transports Metropolitans de Barcelona) bus stops, showing when buses will arrive in minutes with line numbers, destinations, and directions. | |
| kitsu-mcp estienneg/kitsu-mcp Enables users to query and manage Kitsu/Zou production data, including projects, shots, assets, tasks, people, previews, video review, and optional write actions, through an MCP interface. Supports local stdio use and hosted HTTP connectors | |
| Game engine runtime mcp estiwito/game-engine-runtime-mcp An MCP server connecting Claude AI with game engine runtimes (Unity & Godot) for automated testing, log filtering, and scene hierarchy inspection. | |
| OmniFocus MCP Server estrenuo/omnifocus-mcp-server An MCP server that enables AI assistants to interact with OmniFocus on macOS via JXA, supporting task, project, folder, tag, perspective, and search operations. | |
| mcp-weather-israel-playwright esty783/mcp-weather-israel-playwright Enables LLMs to fetch live weather forecasts for Israeli cities by controlling a Chromium browser to scrape weather data from weather2day.co.il. | |
| Cabinet Assistant MCP connector esubalew-kunta/mcp A remote-MCP service enabling Claude to manage Notion tasks and cases and query Supabase data with a preview-confirm pattern for safe writes. | |
| KnowFlow MCP esurovtsev/know-flow-mcp A unified knowledge retrieval tool for MCP-compatible LLMs, enabling structured external knowledge access from local files and future integrations. | |
| finance-mcp esurovtsev/mcp-finance-server-py A minimal MCP server that converts company names to stock symbols and fetches financial data from Yahoo Finance using two example tools. | |
| locator-mcp eswarr11/locator-mcp MCP server for scanning browser pages and collecting element locators (XPath, testId, CSS). | |
| Myelin et-do/myelin Myelin provides persistent, brain-inspired memory for AI agents, enabling cross-session and cross-tool context retention with local, private storage. | |
| toolsthatdontupload-mcp etacbae6768-a11y/toolsthatdontupload-mcp Enables AI assistants to search and run over 500 tools for PDF, text, data, crypto, network, and conversion tasks, with file processing done locally or at the edge so inputs are not uploaded. | |
| Core etafund/chat-on-steroids Enables ChatGPT to work on a local project by reading and editing files, running shell commands, keeping terminals and desktop sessions open, and splitting work across durable workers whose context persists between tasks. Long-running work | |
| mcp-server-playground etak64n/mcp-server-playground An MCP server that demonstrates the Model Context Protocol using a mock SQLite database of an online store, offering tools for product search, sales analysis, and reviews, along with resources and prompts for learning MCP integration. | |
| SerpApi MCP Server etanaka808/serpapi-mcp Enables querying Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay and many other engines to retrieve organic results, news, images, shopping, weather and stock data in real time. Returns structured JSON or token-efficient Markdown, with optio | |
| brainlayer etanhey/brainlayer Local-first persistent memory layer for AI agents. Provides hybrid search (FTS5 keyword + vector embeddings) over 223K+ knowledge chunks via MCP. Tools: brain_search, brain_store, brain_entity, brain_subscribe. Features pub/sub with stable | |
| cmuxlayer etanhey/cmuxlayer Terminal multiplexer MCP server for orchestrating parallel AI agents. Manages workspaces, panes, surfaces with send_input/read_screen/spawn_agent/stop_agent tools. Supports Claude Code, Codex, Gemini, Cursor CLI agents with lifecycle manage | |
| VoiceLayer etanhey/voicelayer VoiceLayer MCP server enables AI coding assistants to speak and hear via local, on-device speech-to-text and text-to-speech, with no cloud dependencies. | |
| ocean-conditions-agent etavacoli/ocean-conditions-agent Enables checking live tide, swell, and wind data for La Jolla surf spots, with an AI agent that makes judgment calls like a local surfer. | |
| JPI MCP Server etep82/jpi-mcp Enables AI assistants to interact with the Just Plan It (JPI) job scheduling and resource management system through 69 MCP tools covering full CRUD operations for jobs, tasks, templates, components, and resources. | |
| Remote MCP Hub etern1ty-crypto/remote-mcp-hub Enables AI assistants to securely access and control a Windows machine remotely, running commands and managing files via an MCP server protected by Bearer-token authentication and exposed through a Cloudflare Tunnel. | |
| Remote MCP Hub etern1ty-crypto/remote-mcp-hub-iran Enables remote access to local filesystem and Windows command execution through MCP-compatible clients like Notion AI, Claude, and Cursor via secure public tunnels with bearer authentication and proxy support. | |
| Remote MCP Hub etern1ty-crypto/remote-mcp-hub-linux Enables AI assistants to securely connect to and execute commands on a remote Linux server via Cloudflare Tunnel, with bearer-token authentication. | |
| remote-mcp-hub-mac etern1ty-crypto/remote-mcp-hub-mac Enables macOS users to securely connect AI assistants such as Notion AI, Claude, and Cursor to their local files and terminal through an MCP server protected by a Bearer token and Cloudflare Tunnel. | |
| Weather Query MCP Server eternachen/mcp-playground An MCP server implementation that allows users to fetch and display weather information for specified cities, including temperature, humidity, wind speed, and weather descriptions. | |
| ledger-mcp eternal-roman/ledger Enables AI agents to perform exact-decimal double-entry accounting by calling tools that compute money, validate and post entries, verify equations, and produce deterministic audit hashes and citation-grounded artifacts. | |
| ee-mcp-public eternalengineos/ee-mcp-public Enables read-only access to EternalEngine public API endpoints, providing 43 GET-only tools for querying PostFrame and PayGate data with your own API key. | |
| SJTU MCP eternalwavee/sjtu-mcp Wraps the SJTU Zhiyuan No.1 API as a local MCP server, allowing direct use of SJTU models in Claude Code and Codex without custom integration scripts. | |
| Jev Reflex eternitiesai/jev-reflex Enables coding agents to make small, bounded decisions around tasks via stdio MCP, supporting source-bound context, durable budgets, bulk jobs, and measured outcomes while leaving planning and reasoning with the main model. | |
| weather-mcp-server eternityg2/weather-mcp-server A weather query MCP server based on FastMCP, supporting Chinese city names and fetching real-time weather data from wttr.in. | |
| AI Studio MCP Server eternnoir/aistudio-mcp-server A Model Context Protocol server that connects to Google AI Studio/Gemini API, enabling content generation with support for various file types, conversation history, and system prompts. | |
| astrbot-mcp eterultimate/astrbot-mcp Provides tools for AstrBot plugin development including documentation access and hook inventory. | |
| MCP Riddle Game Server etfromchina/mcp-riddle Provides tools to fetch random or categorized riddles, verify answers, and view riddle statistics. It supports communication via HTTP and SSE for seamless integration with AI agents. | |
| docverify-mcp ethan-haas/docverify-mcp MCP server that extracts financial statement figures from PDFs and deterministically verifies all totals before returning them, refusing to disclose any numbers that fail tie-out checks. | |
| embedcalc-mcp ethan-hub26/embedcalc-mcp MCP server providing embedded engineering calculators and code generators as tools for AI agents, enabling precise, deterministic embedded math and C code generation. | |
| PayHub MCP Server ethan-m25/payhub-mcp Enables querying real disclosed salary data across 20 regions, with tools to search jobs, retrieve salary statistics, and find similar roles. | |
| Ecommerce MCP Server ethan-shapiro/ecommerce-mcp-server Enables AI agents to query BigQuery ecommerce datasets like TheLook via guarded, read-only SQL tools (dry_run_sql and execute_sql), with benchmarked performance over wiki-style documentation lookup. |
48,701–48,750 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.