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 |
|---|---|
| Computrabajo Open MCP diplomartco/mcp-computrabajo-open Enables conversational job search on Computrabajo, including reading full job postings, viewing your CV, and applying to jobs with explicit confirmation. | |
| companylens-mcp diplv/companylens-mcp CompanyLens MCP gives your AI assistant access to real corporate data from official government sources. No web scraping, no hallucinations — verified data from SEC EDGAR, UK Companies House, OpenSanctions, and USAspending.gov. | |
| MCP diposhreeroy/mcp Enables an agent to discover and call local MCP tools over a Streamable HTTP endpoint using Groq for reasoning and tool selection. | |
| Dataproc MCP Server dipseth/dataproc-mcp Enables management of Google Cloud Dataproc clusters and jobs through 22 production-ready tools, featuring intelligent parameter injection, semantic search capabilities, and enterprise-grade security for seamless big data operations. | |
| google-workspace-unlimited dipseth/google_workspace_fastmcp2 This MCP server provides comprehensive Google Workspace integration (Gmail, Drive, etc.) with multi-user OAuth.
Unique features include RAG-powered natural language to Chat card rendering, runtime Jinja2 macro creation, and dynamic tool ma | |
| tmdb-media dipsysu/media-scraper-mcp Provides tools for AI clients to scan, match, and scrape TMDB metadata for local media files, with safe sidecar writing or full Jellyfin-style reorganization including file renaming and NFO generation. | |
| knowledge-base-mcp diptanil-x-42/knowledge-base-mcp A lightweight personal knowledge base MCP server that lets clients store, search, organize, and summarize research notes from a local JSON file. | |
| Telegram Topics MCP Server diptapradipta21/mcp-telegram-topics Enables Claude Desktop, Claude Code, and autonomous AI agents to route messages into Telegram supergroup forum threads and manage topics by creating, editing, closing, reopening, and listing them with tag-to-thread mapping. | |
| WhatsApp Bridge MCP Server diptapradipta21/mcp-whatsapp-bridge Enables Claude Desktop, Claude Code, and autonomous AI agents to send direct WhatsApp messages and urgent formatted alerts to personal or team phones through native MCP tools. | |
| MCP Call Recording Server diptigarg23/mcp-call-recording Enables semantic search over VTT transcript files using AI-powered structured summaries, allowing natural language queries about client call transcripts through Claude Desktop or Copilot Studio. | |
| RCF MCP Server diraw/research-compute-fabric Enables AI agents to plan, confirm, submit, observe, and audit compute jobs across local machines, SSH workstations (including WSL), and Slurm clusters through a unified stdio interface, with node probing, environment evidence, project sync | |
| pupa-mcp dircolin/pupa-mcp Enables turning Korean screenplays and ad storyboards into shot plans and generating AI images/videos across multiple engines while tracking WOON credit usage and saving results to PUPASTAGE projects. | |
| Rami-Kali MCP Server direct-to/kail-mcp Wraps Kali Linux penetration testing tools for authorized security assessments, driven by a local LLM via LM Studio. | |
| warcraft-wiki-mcp direction6275/warcraft-wiki-mcp MCP server that gives LLMs live access to warcraft.wiki.gg API documentation with behavioral notes, restrictions, and patch history for World of Warcraft APIs. | |
| Smart Connections MCP Server director-phil/smart-connections-mcp Enables semantic search and related-note discovery across an Obsidian vault via MCP, providing RAG context blocks for natural language queries. | |
| Directus Content MCP Server directus/mcp Enables Directus users to interact with their data in LLMs, allowing content editors and data analysts to manage content, query collections, and perform data operations using natural language. | |
| SQLite MCP Server direkt/mcp-test Enables querying log data stored in SQLite databases through the Model Context Protocol, allowing natural language interactions with log analysis. | |
| Remote OpenCode MCP Server dirichelet/remote-opencode-mcp A Model Context Protocol (MCP) server that enables remote access to OpenCode AI coding agent, allowing MCP-compatible clients to leverage OpenCode's capabilities. | |
| Pulumi Events MCP dirien/pulumi-events MCP server for managing events on Meetup.com and Luma via AI assistants like Claude. | |
| repoflux dirka111q-maker/repoflux Enables local LLM tools and agentic IDEs to inspect repository token maps, retrieve clean token-bounded codebase snapshots, and audit code for hardcoded secrets via MCP over stdio. | |
| qudi MCP Integration dirkenglund/qudi-mcp-integration Enables natural language control of quantum photonics experiments through the qudi framework. Supports safe instrument control, measurement execution, and safety system management with built-in runlevel protection and parameter validation. | |
| adsb-mcp-server dirkhh/adsb-mcp-server Exposes real-time ADS-B aircraft data from a feeder, enabling natural language queries for aircraft positions, receiver statistics, and flight searches. | |
| UI Perception Engine dirkknibbe/uipe Enables AI agents to perceive and interact with web interfaces by extracting a unified UI Scene Graph from live URLs, providing tools for navigation, element detection, visual analysis, and state tracking. | |
| augLABS augmntd MCP (Xenware) dirrrtyjesus/augmntd-mcp Enables AI agents to securely interact with enterprise systems of record through MCP, with harmonic coherence telemetry, phase-lock analysis, and governance controls that ensure deterministic, non-destructive operations. | |
| dir2mcp dirstral/dir2mcp Serves a folder as an MCP knowledge server: it indexes text, code, PDFs, office documents and audio or video, then answers search and ask calls with citations that name the file, the line range, the page or the time range. Runs fully local | |
| Discogs MCP Server dirtydimmy/discogs-mcp Enables AI assistants to interact with your personal Discogs music collection, including search, mood-aware recommendations, collection analytics, and more. | |
| closed-book-mcp dis70rt/closed-book-mcp Enables zero-hallucination retrieval over local documents using hybrid semantic and keyword search, ensuring answers are based solely on provided PDFs. | |
| spoolman-mcp disane87/spoolman-mcp Enables AI assistants to manage 3D printer filament inventory through Spoolman's API, allowing natural language queries and commands for CRUD operations on vendors, filaments, spools, settings, and more. | |
| disasm.dev MCP server disasm-dev/mcp-server Enables AI assistants to generate DataDome and Incapsula clearance tokens without a headless browser, for development and prototyping. | |
| j2me-pc-lab disc13/j2me-pc-lab Enables MCP-capable agent clients to manage J2ME porting projects through project inventory, method context, task claiming and logging, builds, runs, screen comparisons, and hash-checked source patching with backups. | |
| turbosign-mcp disciplin-run-org/turbosign-mcp Enables sending PDFs for e-signature via the TurboSign API, with tools for sending, reviewing, tracking status, downloading signed documents, voiding, resending, and managing credentials. | |
| Disclose MCP Server disclose-framework/disclose-mcp-server Enables AI agents to query merchant operational signals like return rates, fulfillment accuracy, and chargeback ratios published through the Disclose protocol. Provides tools to fetch merchant disclosures and check signal coverage for compl | |
| discourse-mcp discobrain/discourse-mcp Enables an AI agent to read and act on a single Discourse forum as one user, including posting, private messages, likes, reactions, bookmarks, watch/track/mute, and reading its own notifications via a stdio MCP server. | |
| textual-mcp-server discohead/textual-mcp-server An MCP server that lets AI agents launch, interact with, and inspect Textual TUI applications headlessly. | |
| mcp-counter-server discordit142/mcp-counter-server Provides stateful counter tools for AI assistants, enabling accurate counting and tracking of metrics via tag-based or direct tool calls. | |
| telegram-notification-mcp discountry/telegram-notification-mcp Enables sending notifications to Telegram via a bot, using only native Node.js APIs. | |
| x-post-mcp discountry/x-post-mcp A minimal MCP server for posting tweets to X (Twitter) via API v2, supporting tweet creation, replies, and quote tweets. | |
| ElevenLabs MCP Server discret-digital/elevenlabs-mcp Official MCP server that enables interaction with ElevenLabs Text to Speech and audio processing APIs. It allows generating speech, cloning voices, transcribing audio, and creating sound effects through natural language. | |
| mautic-mcp discret-digital/mautic-mcp A lightweight MCP server that connects Claude AI to Mautic marketing automation, enabling contact management, email sending, campaign operations, and analytics via natural language. | |
| agent-skills-mcp discretetom/agent-skills-mcp Loads Agent Skills from markdown files, exposing them as MCP tools or system prompts for AI agents. | |
| Mock MCP Server discretetom/mock-mcp-server A mock MCP server for testing MCP client implementations and development workflows. Supports tools, prompts, and resources across multiple transport protocols (stdio, HTTP, SSE). | |
| Shinkuro discretetom/shinkuro Enables loading and serving markdown files as prompts from local folders or GitHub repositories. Supports automatic repository synchronization and YAML frontmatter for prompt metadata. | |
| twincat-mcp disectron/twincat-mcp-server Enables an AI agent to drive a Beckhoff TwinCAT 3 setup end to end: read and write live PLC variables and system state over ADS, manage files and processes on the target IPC, build and edit projects through the XAE automation interface, cap | |
| Office MCP Bridge disemay12/office-mcp Lets any MCP client drive an already-installed desktop Microsoft Word, Excel and PowerPoint over COM across 53 tools, editing, formatting, saving and exporting real open files in live windows without cloud services or API keys. | |
| ci-guardian dishagupta2901/ci-guardian Enables headless Claude to review pull requests and triage CI failures on a real GitHub repository, routing all GitHub write actions through the MCP server. | |
| hr-assist dishant1901-prog/genai-hrms-mcp Automates employee onboarding workflows for HR teams, enabling tasks like data entry and email notifications through natural language. | |
| Kaggle MCP Server dishant27/kaggle-mcp Enables AI assistants to interact with Kaggle competitions, including listing competitions, downloading files, submitting predictions, and viewing submission history. | |
| linkedin-mcp-server dishant27/linkedin-mcp-server Enables LLMs to search for LinkedIn profiles and retrieve detailed profile information via the LinkedIn API, supporting secure OAuth2 authentication. | |
| mcp-server-starter dishant27/mcp-server-starter Provides a production-ready TypeScript template for building Model Context Protocol servers with stdio transport, zod-validated tools, stderr-only logging, safe API-key handling, and an example search tool. It enables developers to create a | |
| Medium MCP Server dishant27/medium-mcp-server Enables programmatic interaction with Medium's content ecosystem for intelligent and context-aware content retrieval. |
44,851–44,900 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.