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 |
|---|---|
| Adobe Express MCP Server enventdigital/community-express-dev-mcp Enables Adobe Express add-on developers to scaffold projects, access code examples, query SDK documentation, and get implementation guidance for building Adobe Express add-ons. | |
| openclaw-task-mcp enviableamaretto/openclaw-task-mcp MCP server for OpenClaw task lifecycle management, enabling starting, listing, and checking status of tasks via a Gateway API. | |
| memberpass-mcp envigoinnovations/subscriby-mcp Connects MCP clients like Claude and Cursor to MemberPass workspace, exposing 42 tools for managing projects, plans, subscriptions, members, access codes, payments, webhooks, and analytics. | |
| LLM Council MCP envious-labs-llc/llm-council-mcp Enables Claude Code to consult external LLMs (GPT, Gemini) through multi-turn sessions for second opinions, parallel consultations, and web-grounded research. | |
| mcp-tts enviraldesign/mcp-tts Adds text-to-speech capabilities to Cursor IDE, allowing your AI assistant to speak responses, summaries, and explanations out loud using OpenAI or ElevenLabs. | |
| Basecamp 2 MCP Server envisialearning/basecamp2_mcp An MCP server that wraps the Basecamp 2 REST API, enabling Claude to create and manage todos, projects, and people through natural language. | |
| Shuttle enwaiax/shuttle Enables AI assistants to securely execute SSH commands on remote servers with connection pooling, session isolation, and a web audit panel. | |
| DevSpace Ultra enwong93-sketch/devspace-ultra An MIT-licensed DevSpace distribution with an elastic ChatGPT Classic multi-agent runtime layer for managing multiple independent worker conversations and scaling them dynamically. | |
| Qixin API Service MCP enzetan/qixin-apiservice-mcp Enables AI models to access comprehensive Chinese enterprise data from the Qixin Open Platform, including business details, risk analysis, and legal records. It facilitates keyword-based corporate searches and detailed information retrieval | |
| Trendyol MCP enzifiri/trendyol-mcp Enables AI assistants to search embedded Trendyol Partner API documentation and schemas, then execute any of the 93 marketplace operations—products, stock/price, orders, returns, invoices, webhooks, Q&A, finance, and shipping—across one or | |
| WEEX MCP enzo108216/weex-mcp MCP server providing WEEX market data, account information, and controlled trade execution, with local stdio and HTTP transports. | |
| code-context-v2 enzodevs/code-context-v2 Enables semantic code search across indexed codebases using natural language queries, with support for CLI and MCP interfaces. | |
| wearable-mcp enzojunq/olav Enables an AI agent to read Garmin sleep, readiness and activity data, build an athlete profile, check proposed sessions against code-enforced limits and real calendar availability, and then push approved structured workouts to a Garmin wat | |
| temporal-mcp-server enzomotta/temporal-mcp-server Enables AI assistants to observe and manage Temporal workflows, including listing, starting, signaling, resetting, terminating, querying, and retrieving history, with support for wait_for_activity and webhook utilities. | |
| mcp-box enzotironi/mcp-box Private MCP server exposing the ascii Box API as shell and file tools, letting agents like ChatGPT or Claude drive Linux boxes. | |
| H3C CLI MCP Server enzymecat9/h3c-cli-mcp Telnet-based MCP server for H3C network device CLI, enabling connection, command execution, and device mode detection via natural language. | |
| dsh-mcp-admin enzzzzzz/dsh-mcp-admin Exposes DeepSeek Harness skill and agent preset management as an MCP server, letting remote agents read, create, update, and delete skills/presets over HTTP with audit logging. It enables a production-to-review-to-modification workflow with | |
| eo-mcp eo-mcp/eo-mcp Enables AI agents to autonomously discover, stream, and compute satellite analytics from free government Earth-observation catalogs such as Sentinel-2, Landsat, and Copernicus DEM, with zero API keys or configuration. It supports place-name | |
| eo-mcp eo-mcp/eo-mcp.github.io Enables AI agents to autonomously discover, stream, and compute satellite analytics from free government Earth observation archives. Provides tools for STAC search, spectral indices, elevation profiles, SAR water detection, and sandboxed ge | |
| mcp-call-orchestrator-proxy eoc-llm-tooling/mcp-call-orchestrator-proxy Enables multiple concurrent MCP clients to safely share one backend MCP server by terminating client sessions, serializing forwarded calls, and mirroring the backend's exact tools and schemas. It also reconnects automatically if the backend | |
| claude-inbox eodesign7/claude-inbox Enables Claude chat and Claude Code sessions to exchange tasks, tickets, and project context through a local inbox, including threads, project cards, session status, and shared markdown context. | |
| EODHD MCP Server eodhistoricaldata/eodhd-mcp-server Enables interaction with EOD Historical Data APIs, providing access to 75 read-only tools for financial data including fundamentals, news, screeners, and options via MCP transports. | |
| personal-mcp eoeoe22/personal-mcp Enables Claude to send you a Discord message through a Cloudflare Workers MCP server, triggering a notification with your Discord mention. | |
| Granola MCP Server eoinfalconer/granola-mcp-server Integrates Granola.ai meeting intelligence with MCP clients to provide direct access to meeting notes, transcripts, and workspace organization. It allows users to search and retrieve meeting content through natural language by leveraging ex | |
| Lattice MCP Server eoinfalconer/lattice-mcp An MCP server that exposes the Lattice Talent API as tools, enabling AI assistants like Claude to read and manage people data, goals, feedback, reviews, and more. | |
| arduino-claude-mcp eoinjordan/arduino-mcp MCP server for Arduino IDE 2.0 sketches. It exposes a small REST API plus an MCP stdio bridge so agents can read and write the main .ino file, list sources, and optionally compile with arduino-cli. | |
| wax-mcp-full eoinjosephcurran-code/wax-mcp-full A local-first MCP server for the WAX blockchain that enables AI hosts to query accounts, chain state, AtomicAssets, AtomicMarket, Hyperion history, and WAXP prices, as well as prepare unsigned transactions for wallet signing. | |
| gempack-shop eomgerm/web-mcp-demo MCP server for a demo Nintendo Switch game shop. Enables agents to list/search games, manage the cart, and perform demo checkout while sharing state with the web UI. | |
| sangsik-gdscript-graph eomsangsik/sangsik-gdscript-graph A function-level call-graph indexer for GDScript/Godot projects, exposed as an MCP server so AI coding assistants can answer questions like 'what calls this function?' or 'what would break if I change this signal?' without re-reading the wh | |
| EOSC Data Commons Search eosc-data-commons/data-commons-search Enables natural language search and discovery of open-access scientific datasets through the EOSC Data Commons OpenSearch service. Provides tools to search datasets and retrieve file metadata using LLM-assisted queries. | |
| Systembolaget API MCP Server eoset/bolki-mcp Enables searching and listing products from Systembolaget (Swedish liquor store) with configurable launch date range and optional query parameters. | |
| FreshMCP eosho/freshmcp Provides standardized MCP interfaces for Azure services including Cosmos DB operations (container and item management) and AI Search operations (index management), deployed through Azure API Management gateway. | |
| ATS Jobs MCP server eosphor/ats-jobs-mcp Enables searching live job postings pulled directly from 10 applicant-tracking-system APIs — including Greenhouse, Lever, Ashby, Workday, Personio, Recruitee, Teamtailor, Workable, SmartRecruiters and Breezy HR — using just a company websit | |
| Defuddle Clip MCP eothl/defuddle-clip-mcp Enables local clipping of webpages and YouTube transcripts into Obsidian from an AI assistant, with Markdown preview and saving tools, no browser extension or API key required. | |
| Obsidian Readonly MCP eothl/obsidian-readonly-mcp Read-only MCP server for querying a running Obsidian vault from agentic runtimes, exposing safe Obsidian CLI commands. | |
| Agent Harness Kit eozkan84/agent-harness-kit Enables AI coding providers to run structured multi-agent workflows with shared documents, tracked tasks, handoffs, and health evidence, supporting providers such as Claude Code, Codex CLI, Cursor, Grok Build, and OpenCode. | |
| SerpApi MCP Server eozturk454/serpapi-mcp Enables agents to run multi-engine web searches across Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay and more, along with related live data such as weather, stocks, and news. Results are automatically detected and formatted, and can be ret | |
| epago MCP Server epago-gmbh/epago-mcp Enables MCP-capable clients to read and write directly in epago accounting, including chart of accounts, transactions, invoices, payments, receipts, and tax reports. | |
| bd-skill epakhomov/bd_mcp An MCP server that provides Claude Code with access to Black Duck SCA for managing vulnerabilities, licenses, and policy violations through natural language. It enables users to query component risks and execute Black Duck Detect scans dire | |
| Google Workspace MCP Server epaproditus/google-workspace-mcp-server Provides tools for interacting with Gmail and Calendar APIs. This server enables you to manage your emails and calendar events programmatically through the MCP interface. | |
| Antikor NGFW MCP Server epati-cyber-security/antikor-ngfw-mcp Dynamically loads the Antikor NGFW API schema and exposes eligible endpoints as MCP tools for firewall management via natural language. | |
| devshot epavanello/devshot Enables agents to beautify screenshots by applying gradients, padding, cropping, rounded corners, and shadows, returning the finished image directly. | |
| slack-stdio-mcp epdlr/slack-stdio-mcp Local MCP stdio bridge to Slack's hosted MCP server, enabling agents to use Slack tools (send messages, search, history, canvas, etc.) via local OAuth and token refresh. | |
| NetBox MCP Server epe105/netbox-mcp MCP server for interacting with NetBox API, enabling users to query and manage NetBox resources such as devices through natural language. | |
| Agent Message Bridge epfmydx/agent-message-bridge Enables independently operated AI clients to exchange private 1:1 messages and files using authenticated participant identities, with retry deduplication, status tracking, notifications, and owner conversation inspection. Provides REST and | |
| Skill MCP Server ephemeraldew/skill_mcp A modular plugin system that allows AI agents to dynamically load and use 'skills' from local folders without code changes or restarts. It enables instant capability extension through script execution, hot reloading, and resource bundling. | |
| Zimi MCP Server epheterson/zimi Enables AI agents to search, read, and manage offline knowledge from ZIM files (Kiwix archives) with full-text search, language support, and library management. | |
| kuma-mcp ephi052/kuma-mcp Enables managing Uptime Kuma monitors and groups via CSV-driven sync, with MCP-style commands for inventory synchronization, preview, and status checks. | |
| openapi-mcp-bridge ephrin/openapi-mcp-bridge Transforms OpenAPI definitions into MCP tools for seamless LLM-API integration. | |
| Playwright MCP Server epi-builder/mcp-test Enables web browser automation through Playwright, providing tools for navigation, element interaction, screenshot capture, and accessibility snapshots. Uses streamableHttp transport for seamless integration with MCP clients. |
48,251–48,300 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.