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 |
|---|---|
| ctxdebug ddudle/ctxdebug MCP server that connects WinDbg, IDA Pro, and x64dbg to AI assistants for reverse engineering and Windows security research, offering 160+ tools for debugging, analysis, and cross-debugger workflows. | |
| ElevenLabs Image Generation MCP Server ddunford/elevenlabmcp Generates images from text prompts using ElevenLabs' image generation API via browser automation, with support for multiple models and persistent authentication. | |
| Autotask MCP Server ddurko1950/autotask-mcp Enables AI assistants to interact with Autotask PSA through natural language, providing tools for ticket triage, time logging, company lookups, project management, and more. | |
| Autotask MCP Server ddurko1950/autotask-mcp-2 Enables AI assistants to directly query and manage Autotask PSA data through natural language, including ticket triage, time entry creation, company lookups, project management, billing review, and more. | |
| debate-arena dduyhai90/ai-debate-arena Enables AI agents to engage in structured, turn-based debates with real-time message exchange and human moderation via a web UI. | |
| ddys-mcp ddysiodev/ddys-mcp Official MCP server for the DDYS (低端影视) API, enabling search, details, resources, collections, comments, and media export (STRM, M3U) via natural language. | |
| tokenarchive ddyy/tokenarchive Enables agents to query your archived AI coding usage through read-only tools for usage summaries, project breakdowns, daily trends, and archive health. | |
| qiuxiaoce-mcp ddzyx/qiuxiaoce-mcp Enables AI assistants to query real-time standings, fixtures, Chinese/English club aliases, and tactical data for Europe's top five leagues and global football. | |
| debary-mcp-compliance de-bary-llc/debary-mcp-compliance Provides deterministic fair-housing and advertising compliance checks for US real-estate listings, with rule explanations and rewrite suggestions, ensuring models cannot override the verdict. | |
| protonmail-mcp-server de-blanck/protonmail-mcp-server A read-only MCP server that connects to Proton Mail via Proton Bridge, enabling AI assistants to search, list, and read emails securely without leaving your machine. | |
| Scrooge de-cri/scrooge Provides AI coding agents with pre-edit situational awareness by combining structural call graphs and co-change history to prevent incomplete edits. It surfaces files that historically change together, reducing missed coupled modules. | |
| atlassian-buddy de-cryptor/atlassian-buddy Connects Claude to Jira and Confluence, enabling natural language research, design with Mermaid diagrams, documentation writing, and ticket creation without needing an Anthropic API key. | |
| spike-mcp de-cryptor/spike-mcp Connects Claude to Jira and Confluence for researching, designing spike docs with Mermaid diagrams, writing Confluence pages, and creating Jira tickets. | |
| owntracks-mcp de-niji/owntrackshermes Enables querying an OwnTracks Recorder for current and historical location data, including addresses, stays, distances, devices, and status, through read-only MCP tools. It supports natural-language questions about where someone is or was a | |
| front-asset-intel-mcp de-snake/front-asset-intel-mcp Exposes precomputed asset research and rubric summaries for analyst agents, enabling lookup of asset summaries and full research reports via simple queries. | |
| code-rag-mcp de4er00/code-rag-mcp Enables coding agents to search local repositories through hybrid keyword and embedding retrieval, read matched chunks, and list indexed repos via MCP, without API keys or cloud services. | |
| Expose deadcodedump/expose Easily build MCP tools for Claude desktop app. | |
| BrainBridge deadende/brainbridge Provides AI agents with persistent memory via Google NotebookLM, enabling them to save, search, and retrieve dated sources and query notebooks with citations using a one-time popup login and keepalive session management. | |
| CVForge deadende/cvforge Turns a pasted CV (PDF, DOCX, Markdown, or text) into a polished one-page portfolio website with domain-aware themes and Arabic RTL support, and can generate HTML for preview or deployment. | |
| wecom-msg-audit-mcp deadmau5v/wecom-msg-audit-mcp Enables AI agents to securely access and search enterprise WeChat (WeCom) chat records with full decryption and auditing, supporting message retrieval, decryption, local storage, and querying via MCP tools. | |
| astrology-mcp deadmeme5441/astrology-mcp MCP server for Indian astrology (Jyotisha) that provides deterministic Lahiri sidereal calculations, question-aware natal context, Vimshottari dasha, and current gochara, enabling natural language conversations about astrology with saved bi | |
| openapi-explorer-mcp deadrime/openapi-explorer-mcp Enables AI agents to explore any OpenAPI 3 spec, inspect endpoints and schemas, generate TypeScript types, and make authenticated API calls using credentials mapped to the spec's security schemes. | |
| posthog-toolkit-mcp deadrime/posthog-toolkit-mcp Enables querying PostHog with HogQL, retrieving event and property definitions, session replays, and project lists, plus optional REST API access with safeguards against accidental writes and API key leakage. | |
| Nexus-MCP deadswank001/nexus-mcp A fully local, open-source MCP server that replaces Azure AI Foundry, enabling model management, inference, evaluation, and RAG using Ollama without any cloud dependencies. | |
| serenedash deadtrickster/serenedash Exposes SereneDB server state as read-only MCP tools (status, storage, memory, activity, threads, profile, callgraph, host, config, and optional set_setting) so agents can query live database health and metrics with evidence-backed findings | |
| contribscout deahmedbacha/contribscout Enables ranking GitHub issues by repository maintainer health, checking issue claim status, comparing repository activity, and summarizing contribution guidelines via MCP tools. | |
| openEHR MCP Server deak-ai/openehr-mcp-server Enables MCP clients like Claude Desktop to interact with openEHR REST APIs (EHRbase) for creating compositions, managing EHRs, listing templates, and executing AQL queries. | |
| shadcn dealenx/ai-factory-extension-shadcn-mcp This MCP server provides tools to install and manage shadcn/ui components directly from AI coding agents. | |
| DeAlgo MCP Server dealgo-systems/dealgo-mcp-server Runtime decision firewall for AI agents that exposes the CSC engine as an MCP server, allowing agents to consult before executing risky actions. | |
| dealgo-middleware dealgo-systems/dealgo-middleware Enables agents to read recorded payments and request exact refunds for administrator review, then check approval and provider outcome status without holding Stripe credentials or dispatching refunds. | |
| discord-mcp-server deamondev888/-serveur-discord-mcp Discord MCP Server est un pont entre votre intelligence artificielle et Discord. Il transforme votre bot Discord en un assistant intelligent capable de comprendre et d'exécuter vos commandes. | |
| Claude-Code MCP Runner deamondev888/-simple-claude-api-runner- This MCP server enables remote control and management of Claude Code agents, allowing you to execute missions, configure agent personalities, and integrate with other MCP tools. | |
| anymail-mcp deamondev888/anymail-mcp Connects any IMAP/SMTP mailbox to AI agents via MCP, enabling email read, search, send, reply, and management through natural language. | |
| Browser Manager MCP Server deamondev888/browser-manager-mcp-server Enables comprehensive browser automation and control through Playwright, including launching browsers, managing tabs, web navigation, element interaction, and screenshot capture. Supports detecting and controlling external browsers with rem | |
| imap-smtp-mcp deamondev888/imap-smtp-mcp Exposes any IMAP mailbox and SMTP relay as MCP tools, enabling email management (read, search, send, delete) through MCP-compatible agents. | |
| MCP-Serveur deamondev888/mcp-server-asynchrone A modular and extensible MCP server for managing synchronous and asynchronous tasks, leveraging Docker, BullMQ, and Redis. | |
| Moltbook MCP Server deamondev888/moltbook-mcp-server Enables AI agents to interact with the Moltbook social network, including posting, reading feeds, commenting, voting, and semantic search. | |
| overmind-mcp deamondev888/overmind-mcp Orchestrates and controls multiple AI agent CLIs (Claude-Code, Gemini-cli, etc.) via a unified MCP server, enabling complex multi-agent missions with shared memory and HTTP singleton architecture. | |
| WhatsApp MCP Server deamondev888/whatsapp-mcpserver An MCP server that enables AI to control WhatsApp Web via Puppeteer Stealth for reading and sending messages. It features human-like interaction patterns and anti-ban protections to securely manage chats and communications through natural l | |
| showme dean0x/showme Enables coding agents to open files and git diffs directly in VS Code, allowing users to review code changes without leaving their conversation. | |
| Knowledge Graph Memory Server deanacus/knowledge-graph-mcp A persistent memory server that implements a local knowledge graph using the Kuzu embedded database to store entities, relationships, and observations. It enables AI models to maintain structured long-term context through searchable nodes a | |
| jiangshan-map deanchensj/jiangshan-map Interactive historical atlas of China that resolves ancient and modern places, classical poetry sites, dynastic boundaries, city administrative genealogies, and historical figure trajectories. | |
| testmonitor-mcp deanchong/testmonitor-mcp Enables AI agents to interact with TestMonitor projects, test cases, test runs, results, issues, and more through a local stdio MCP server generated from the official REST API specification. | |
| Postdom MCP Server deanfankhauser/postdom-grokbot Postdom makes videos and slideshows that make your business go viral, then posts them for you every day on TikTok, Instagram, YouTube and 6 more platforms. You just hit approve. Free to start. | |
| Postdom MCP deanfankhauser/postdom-mcp Enables MCP-compatible AI assistants to read a workspace, upload media, and create, schedule and publish branded short videos, slideshows and images to connected social accounts. Also lets assistants review plans, post status and performanc | |
| geotab-mcp deanjbrown/geotab-mcp Exposes the MyGeotab API as AI-callable tools, letting Claude query fleet data, device status, trips, tachograph files, fuel, diagnostics, faults, and driver information across multiple customer databases through natural language. | |
| SGU Brunnar MCP Server deanmcgowan/mcp-sgu-open-data A read-only MCP server that provides access to the Swedish Geological Survey (SGU) wells dataset, enabling search, retrieval, and export of well data with geocoding support. | |
| MCP Sui Tools deanplus/sui-mcp A toolkit that integrates with the Sui blockchain, allowing Claude to request test tokens through a testnet faucet tool when users provide their wallet addresses. | |
| cannons-auctions-mcp deansasek/cannons-auctions-api MCP server for Cannons Auctions API, enabling natural language access to auction data including item search, auction listings, and detailed item information. | |
| osrs-wiki-mcp deansasek/osrs-wiki-api Enables Claude Code to search the Old School RuneScape Wiki, fetch page content, get plain-text extracts, and render images as ASCII art. |
43,151–43,200 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.