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 |
|---|---|
| Frida MCP dnakov/frida-mcp An MCP-compliant server that enables AI systems to interact with mobile and desktop applications through Frida's dynamic instrumentation capabilities, allowing for process management, device control, JavaScript execution, and script injecti | |
| Epistemic Envelope dnanatihor/epistemic-envelope Enables catalog teams to expose data API responses through MCP tools while rendering each claim in a distinct labeled layer — certified findings, profiling observations, and AI inferences — with policy controls that can withhold unverified | |
| MCP Warden dnanatihor/mcp-warden Enables AI agents to reach upstream MCP tool servers through a central policy gateway that authenticates each agent, enforces least-privilege and default-deny rules, and applies response obligations such as redaction, inference stripping, P | |
| @deunobicho/mcp dnb-editorial/deunobicho-mcp Enables AI apps using Model Context Protocol to access canonical Brazilian jogo do bicho and Loteria Federal data, including live results, groups, dream book, odds, history, and legal status. | |
| FIWARE MCP Server dncampo/fiware-mcp-server A bridge between the Context Broker and other services, implementing basic operations for entity publishing, updating, and querying in FIWARE environments. | |
| MCP Linux Deployment dnchandra/mcp_linux Enables management of Windows servers from Linux through an MCP server with per-user installation. Provides tools to control Windows systems via API with secure credential management. | |
| efferent-ble-simulator dncore/efferent-ble-simulator Enables AI agents to start, configure, and monitor simulated Bluetooth LE fitness devices such as smart trainers, power meters, speed/cadence sensors, and heart rate monitors over real Linux BlueZ radios via stdio or HTTP. | |
| scra dncwolf/scra Enables web search via DuckDuckGo and content extraction from URLs using Readability.js. | |
| research-digest dneish2/research-digest-mcp Enables AI assistants to search, retrieve, and manage a personal arXiv paper library over MCP, with explainable relevance ranking, trend analysis, saved papers, and reading suggestions — all running locally without accounts or external serv | |
| MiniMax Coding Plan MCP dngo21511/minimax-coding-plan-mcp Enables MCP clients such as Claude Desktop, Cursor, and Windsurf to perform web searches and analyze images through MiniMax APIs, returning structured search results and AI-generated answers about images from URLs or local files. It is tail | |
| medimate-ddi-mcp dngphuc05/medimate-ddi Enables clients to resolve drug name sets into exact source identities and check every unordered pair in a prescription list against hash-pinned DDInter-derived source assertions of one to eight drug names. Returns recorded interaction evid | |
| lendlord-mcp dniasoff/lendlord-mcp Enables AI agents to manage a Lendlord landlord account through its private JSON API, covering properties, documents, tenants, maintenance reports, tasks and alerts, rent, transactions, compliance, and filing emails against properties. Supp | |
| bw-modeling-mcp dnic-dev/bw-modeling-mcp Enables AI assistants to read, create, and modify SAP BW/4HANA modeling objects via the internal REST API, including aDSOs, InfoObjects, transformations, DTPs, queries, and more. | |
| Android Source Explorer MCP Server dnilsson6358/android-source-explorer-mcp Enables on-demand access to actual AOSP and AndroidX source code, allowing AI tools to search classes, extract method bodies, inspect inheritance, and navigate definitions or references across Android framework internals and Jetpack librari | |
| MCP DB Results Anonymizer dnjfr/mcp-db-results-anonymizer Acts as an anonymizing proxy between AI agents and databases, detecting PII and replacing it with realistic fake data so agents never see real data. | |
| cordra-mcp dnlbauer/cordra-mcp Provides read-only access to Cordra digital object repositories, enabling AI assistants to explore schemas, retrieve objects, and search using Lucene queries. | |
| zimbra-mcp dnlbertoni/mcpzimbradilfer MCP server that exposes a Zimbra mailbox (IMAP, SMTP, LDAP/GAL) as tools for AI assistants, enabling email search, retrieval, sending, attachment handling, and contact lookup via natural language. | |
| mssql-onpremises dnldelarosa/mssql-mcp-onpremises Enables AI assistants to connect to on-premises SQL Server databases using natural language for queries, schema management, and data operations. | |
| Statonic MCP dnldsz/statonicmcp Connects Claude to the Statonic video editor to enable vision-based reference video analysis and AI-driven project authoring. It allows for the direct generation of project variations and automated video structure identification through the | |
| kt-mcp dnlinyj/kohaku-kt-mcp-lite Enables MCP clients to manage a workspace through file reading, writing, editing, searching, Bash/Python execution, and job control, with optional desktop GUI and Cloudflare Tunnel access. | |
| Gemini CLI Orchestrator MCP dnnyngyen/gemini-cli-orchestrator A lightweight MCP server that enables AI agents to perform deep codebase analysis by leveraging Gemini's massive context window for cross-file analysis and intelligent file selection. | |
| iron-manus-mcp dnnyngyen/iron-manus-mcp Enables AI workflow orchestration with an 8-phase process, task delegation via Todos, and role-based agent specialization for complex multi-step tasks. | |
| OpenPlan dnorton94/openplan Enables managing home renovation projects through natural language, covering floors, spaces, budgets, renovation items, schedules, dependencies, notes, and vendor activity via a remote MCP endpoint. | |
| aiTrainer dns-szrvs/aitrainer Personal workout coach MCP server that logs exercises in natural language, tracks progress with SQLite, and provides coaching signals like estimated 1RM and volume trends. | |
| kenari-media-mcp dnshtm9/kenari-media-mcp Enables image generation and editing, video generation and extension, status polling, and download through the Kenari.id media APIs, saving outputs as files on disk. | |
| DNSMint MCP Server dnsmint/dnsmint-mcp-server Lets an agent mint and manage its own hostnames on DNSMint, through the Model Context Protocol. | |
| DT.ly MCP Server dnyantra/dtly Enables AI agents to author and refine JSON-based motion-graphics compositions by editing layers, keyframes, easing curves, text animators, masks, effects, and other animation properties, then previewing rendered frames or video output. | |
| MCP Docs Server dnys1/mcp Aggregates documentation from multiple sources (llms.txt format or web scraping) and provides semantic search capabilities using vector embeddings and hybrid search for each documentation source. | |
| Domain Checker do-community/do-remote-mcp-server-template Enables checking domain availability using WHOIS and DNS resolution, with support for single and batch queries. | |
| HomeKB MCP Server do-md/homekb Enables natural language interaction with a personal knowledge base stored locally on your computer, supporting semantic search, note reading, and writing through Claude Code or mobile apps. | |
| tanium-gateway-mcp do345/tanium-gateway-mcp Enables natural language querying of Tanium assets, vulnerabilities, patches, and deployment information through the Tanium Gateway GraphQL API, integrating with MCP hosts like Claude Desktop, Cursor, VS Code, and Gemini CLI. | |
| kali-mcps do374/awsome_kali_mcpservers Enables users to run Kali Linux security tools such as Nmap, nm, objdump, strings, and tshark through an MCP client for network scanning, binary and symbol analysis, string extraction, live traffic capture, pcap analysis, and Docker-sandbox | |
| fcp-mcp-server do374/fcp-mcp-server Enables Claude and other MCP clients to read, edit, and generate Final Cut Pro XML timelines, including cut detection, markers, roles, transcript-based editing, keyframes, speed curves, and live pushes into a running Final Cut Pro instance, | |
| XActions MCP Server doanbactam/xactions Enables AI agents to automate Twitter/X tasks (scraping, posting, following, etc.) via 140+ MCP tools, no API key required. | |
| DMTicket MCP Server doanhnd9989/dmticket-mcp Provides AI agents live access to a DMTicket workspace for managing contacts, conversations, messages, tags, broadcasts, sequences, flows, triggers, and webhooks, enabling reading, segmenting, messaging, and automating tasks. | |
| mcp-opentym doanhtuan123/mcp-opentym A lightweight MCP HTTP server giving AI assistants real tools to interact with your Windows machine, including running commands, file access, system info, web search, and browser automation. | |
| finviet-confluence-mcp dobadevv/finviet-confluence-mcp An MCP server that enables AI agents to read Confluence page content by URL, supporting self-hosted Confluence with basic auth. | |
| ask-oracle-mcp doberkofler/ask-oracle-mcp Enables Oracle Database schema introspection and SQL execution over stdio, letting MCP hosts list tables, describe columns, and run SQL—read-only by default with opt-in writes. | |
| CodeIndex MCP doberkofler/codeindex-mcp Enables MCP clients to query a local, read-only SQLite code index for status, file outlines, symbol search, references, dependencies, and bounded symbol source without loading the whole repository into context. It currently supports TypeScr | |
| Doberman dobermancore/doberman-core The guarddog that watches your AI and stops before it goes rogue. It combines a deterministic core and dynamic AI layer to get the best both worlds of reliability and personalizaiton. | |
| task-manager-mcp doberoi21/task-manager-mcp A task manager MCP server that demonstrates all three MCP primitives (tools, resources, prompts). Enables users to manage tasks, read task summaries and details, and run structured planning/review prompts through natural language. | |
| Computer-Controller-Bridg dobona/computer-controller-bridge Enables AI clients on Windows to control the local mouse, keyboard, and screen understanding via MCP stdio, allowing automated workflows like viewing the screen, locating elements, clicking, typing, and verifying results. | |
| ricoberry-mcp doc-shashank/ricoberry-mcp Enables AI assistants to programmatically create, validate, store, and hot-swap interactive quizzes and study bundles into a desktop learning application, with analytics and local REST integration. | |
| Engram-Mem docaohieu2808/engram-mem Enables persistent memory for AI agents, combining episodic and semantic memory with LLM reasoning, accessible via MCP. | |
| amoCRM MCP Server docatwork2026/amocrm-mcp MCP server for amoCRM integration, enabling AI assistants to manage leads, contacts, companies, tasks, and more via natural language. | |
| docbrain docbrain-ai/docbrain Self-improving documentation engine that ingests Slack and GitHub PRs to detect knowledge gaps and improve documentation automatically. | |
| Doccler MCP Server doccler-app/mcp-server Enables AI assistants to interact with the Doccler documentation platform, allowing users to query, create, search, generate, publish, and organize documents directly from their IDE. | |
| MCP WordPress Server docdyhr/mcp-wordpress Enables comprehensive WordPress site management through natural language in Claude Desktop, supporting multiple sites with 59 tools for content creation, media management, user administration, and performance monitoring. | |
| Simplenote MCP Server docdyhr/simplenote-mcp-server Integrates Simplenote with Claude Desktop, allowing AI assistants to read, create, update, search, and manage your Simplenote notes as a memory backend or content source. | |
| chrometools-mcp docentovich/chrometools-mcp Enables AI-powered Chrome automation through natural language, providing 56+ specialized tools for browser interaction, page analysis, scenario recording, and visual testing. |
45,251–45,300 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.