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 |
|---|---|
| quoth mcp djagya/quoth Serves a single read-only tool that returns bounded excerpts from an immutable Markdown-vault snapshot, each cited with its vault path, heading path and line range. It also exposes an owner-reviewed core-memory ledger, so only approved clai | |
| Financial-MCP-Server djampman/stage_mcp_server Provides financial data extraction, calculation, and analysis from XML files via a FastMCP server, integrated with a Streamlit frontend and local LLM for secure corporate data handling. | |
| ghidra-headless-mcp djandrei/ghidra-headless-mcp Enables importing and auto-analyzing binaries with Ghidra's headless analyzer, then listing, decompiling, disassembling, cross-referencing, searching, and annotating them — individually or across a whole project — without requiring a runnin | |
| destiny-mcp djang0000/destiny-mcp Enables Chinese metaphysics Ba Zi (Four Pillars) birth chart calculation and Huangli (almanac) queries via natural language, with lightweight offline setup. | |
| CastFabric MCP Server djangoailab/castfabric Enables AI agents to discover, manage, and stream audio to LAN speakers supporting DLNA, AirPlay, and MiPlay, with playback of URLs, local files, and real-time PCM. | |
| Vitest MCP Server djankies/vitest-mcp AI-optimized Vitest interface that provides structured test output, visual debugging context, and intelligent coverage analysis for more effective AI assistance with testing. | |
| Discord MCP OAuth2 Server djanmagno/discord-mcp-oauth Enables reading Discord messages and server information using your own account via OAuth2, no bot required. | |
| Puppeteer Vision MCP Server djannot/puppeteer-vision-mcp Scrapes webpages and converts them to markdown using AI-powered interaction to automatically handle cookie banners, CAPTCHAs, paywalls, and other blocking elements before extracting clean content. | |
| pxt-anzu-diary-mcp djanzu/pxt-anzu-diary-mcp A simple note storage MCP server that allows adding notes and summarizing them through prompts. | |
| Dreamer MCP djavan-ryuuzaki/dreamer-mcp Enables AI assistants to remotely control a ComfyUI installation via its HTTP API, including generating and editing images, creating transparent assets, generating video and audio, tracking the queue, and downloading results. | |
| Study Bible MCP Server djayatillake/studybible-mcp Enables deep Bible study through tools for original language lexicons, morphological analysis, cross-references, and contextual notes. | |
| Plex MCP Server djbriane/plex-mcp A Python-based MCP server that integrates with Plex Media Server API to search for movies and manage playlists in your Plex media library. | |
| Courier djbrl/courier Enables AI agents to make purchases within user-defined budgets and spending limits using verified identities and PayPal-backed payments, while shops receive signed proof of what was allowed. | |
| ClickUp MCP Server (Enhanced Fork) djclarkson/clickup-mcp-server Integrates ClickUp tasks with AI applications, enabling natural language management of tasks, dependencies, time tracking, tags, documents, and workspace organization. Enhanced fork adds task dependency management and improved parameter han | |
| Productboard MCP Server djcorbett96/kojo-productboard-mcp MCP server for integrating with Productboard to manage customer feedback, fetch notes, search and create features, and link notes to features. | |
| Zendesk MCP Server djcorbett96/kojo-zendesk-mcp Enables fetching and analyzing Zendesk support tickets and Help Center articles for trend analysis, knowledge base management, and drafting new articles. | |
| remote-mcp-server-authless djdamienford-arch/remote-mcp-server-authless Deploy a remote MCP server on Cloudflare Workers without requiring authentication. | |
| Blender MCP Server djeada/blender-mcp-server Enables AI assistants to control Blender via MCP tools for scene manipulation, material assignment, rendering, and Python script execution. | |
| Multi-Account MCP djehuty94/multi-account-mcp Enables local, read-only access to multiple Gmail and Google Drive accounts through explicit per-account aliases, using bring-your-own Google OAuth with secure credential storage and no telemetry or write capabilities. | |
| Firelinks MCP Server djeknet/firelinks-mcp Enables interaction with the Firelinks link shortening platform to create and manage short links, track click statistics, manage custom domains, and compare analytics periods through natural language. | |
| Djelia MCP Server djelia-org/djelia-mcp-server An MCP server for Djelia that brings Bambara transcription, translation, and text-to-speech to any LLM. | |
| io.github.DJeswar/github-issues djeswar/mcp-server-github-issues Lets agents read a GitHub repository's live issues through read-only tools for listing, filtering, fetching details with comments and cross-references, searching, and exploring labels and milestones, with transparent pagination and provenan | |
| asymptomatik-cheatengine djethino/claude-cheatengine Enables Claude Code to drive Cheat Engine on Windows through a local named pipe for attaching to processes, scanning/reading/writing memory, pointer scanning, watchpoints, code patching, Mono/IL2CPP inspection, and screenshots, with safety | |
| Joint Chiefs djfunboy/joint-chiefs Multi-model AI code review with structured debate. OpenAI, Gemini, Grok, and Claude review your code in parallel, then an anonymized arbitration produces a single consensus summary. | |
| node-sqlite-mcp djgadd/sqlite-mcp Lets AI agents query local SQLite database files read-only using Node's built-in sqlite module, providing tools for listing tables, describing schemas, and running SQL queries. | |
| MCP Registry Navigator djibrilibnsaid/mcp-from-scratch Lets users discover, compare, and audit public MCP servers from the official registry, validate server.json metadata, and generate installation snippets and publication checklists. | |
| ui-loop djig/ui-loop Enables coding agents to see the UI they just changed without flooding their context window, returning a structured text summary (console errors, failed requests, overflow, layout shifts, accessibility violations) plus small crops of only t | |
| garmin-personal-mcp djjoman68/garmin-personal-mcp Enables AI assistants to query Garmin training and recovery data—including activities, laps, strength sets, sleep, HRV, stress, and Body Battery—through the official read-only Garmin Connect Personal API. It also enables generating training | |
| Bruno API MCP Server djkz/bruno-api-mcp Exposes Bruno API collections as Model Context Protocol (MCP) tools, allowing AI agents and MCP clients to interact with your API collections. | |
| examen-grado djlarrix/examen-grado Prepares law students for the Chilean bar exam in Civil and Procedural Law, providing adaptive tutoring, spaced repetition, mock exams, and verified legal norms from Ley Chile. | |
| Chroma MCP Server djm81/chroma_mcp_server A Model Context Protocol server integration that creates a persistent, searchable working memory for AI-assisted development by enabling automated context recall and knowledge persistence in Chroma, the open-source embedding database. | |
| Log Analyzer MCP djm81/log_analyzer_mcp A Python-based MCP server that enables AI-assisted log file analysis with features for filtering, parsing, and interpreting log outputs, plus executing and analyzing test runs with varying verbosity levels. | |
| skillhub-mcp djmarat/skillhub An MCP server that lets AI agents search, view, install, and validate skills from the skillhub registry through tool calls. | |
| HubSpot MCP Server djmoore-projects/hubspot-mcp-server Exposes HubSpot CRM data and actions as tools for AI agents, enabling contact lookup, company search, contact creation, and activity logging via natural language. | |
| Brandfetch MCP Server djmoore711/brandfetch-mcp Enables AI assistants to fetch company logos, brand colors, fonts, and corporate information from the Brandfetch API using domain lookups or keyword searches. | |
| Dependency Checker MCP Server djodjonx/dependency-checker-mcp Enables security scanning for npm dependencies by checking manifest and lockfiles against the OSV.dev and Socket.dev vulnerability databases. It provides tools to detect vulnerabilities in specific packages and retrieve detailed technical r | |
| mixcloud-mcp-server djornii/mixcloud-mcp-server Enables MCP clients to search and browse Mixcloud, manage follows, favourites, and reposts, and upload or edit shows (including scheduled publishing) through natural language. Handles OAuth authorisation with sandboxed uploads and token-saf | |
| powerbi-local djorshuam/claude-mcp-powerbi Enables querying open Power BI Desktop models locally, including discovering instances, listing tables and measures, and running DAX queries without cloud login or publishing. | |
| ScreenApp Legacy MCP Bridge djosh-03/screenapp-legacy-mcp Enables read-only access to legacy ScreenApp recordings, transcripts, and stored summaries via MCP, handling OAuth and session compatibility for current MCP clients. | |
| tcm-kb djp0417/tcm-rag-agent Enables MCP hosts to query a curated traditional Chinese medicine wellness knowledge base, run constitution assessments, identify intake information gaps, and obtain rule-based safety checks with five-tier risk conclusions. | |
| datavessel djr4/datavessel-mcp-public Hosted MCP server that gives AI agents read and write access to your full marketing & ecommerce stack — Google Analytics, Search Console, Google & Meta Ads, Shopify, WooCommerce, Shopware, Slack and LinkedIn. 100+ tools across 10 connectors | |
| raindrop-mcp djrcx/raindrop-mcp Search and retrieve curated bookmarks from Raindrop.io directly in AI-powered IDEs, with features like component search and design system extraction. | |
| blpapi-mcp djsamseng/blpapi-mcp Enables access to Bloomberg financial data via MCP, requiring a Bloomberg Terminal. | |
| RenderProof djsand/renderproof A local-first MCP server that captures rendered web evidence including screenshots, motion, pixel diffs, and CSS animation metadata for coding agents. | |
| Craftor djsushilkumar/craftor Universal autonomous MCP platform for WordPress, Elementor, and WooCommerce enabling AI clients to inspect, design, build, test, and manage websites. | |
| UniGrok djtelicloud/grok-mcp-server A local Grok MCP server and gateway that every coding agent on your machine shares, self-routing across xAI's API and Grok CLI subscription with per-call cost tracking while keeping your API key server-side. | |
| Nexus Finance djtellado/nexus-finance-mcp AI workbench for financial contract analysis, risk analytics (VaR/CVaR, RWA Basel III), regulatory compliance (EMIR, REMIT, MiFID II, CBAM, EUDR) and counterparty due diligence (KYB/UBO, OFAC, IMO). Zero Retention. 8 MCP tools. | |
| firewalla-mcp djuntgen/firewalla-mcp Exposes the Firewalla MSP API as tools for Claude Code and other MCP clients, enabling natural-language management of Firewalla boxes, alarms, rules, devices, flows, target lists, and trends with full read/write capabilities. | |
| Better Mealie MCP djwmarcx/better-mealie-mcp Provides complete access to Mealie's API for managing recipes, meal plans, shopping lists, households, and more via natural language from AI assistants. | |
| KOPENG djy89/kopeng Persistent, self-curating memory for coding agents. It enables local, zero-cost context recall through MCP tools with hybrid retrieval and autonomous consolidation. |
45,001–45,050 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.