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 |
|---|---|
| TrakSYS MCP Server ea2-programmer/mcp-project An MCP server that provides secure, read-only access to the TrakSYS manufacturing analytics platform through entity-based tools and guided investigation prompts. It enables users to interact with manufacturing databases and perform data ana | |
| mcp-shell-sudo eaangrino/mcp-shell-sudo Enables executing local commands via an argv-based tool with optional non-interactive sudo, command allowlisting, and filesystem write confinement using Bubblewrap. | |
| Excalidraw MCP App Server eaccmk/eaccmk_excalidraw-mcp Enables streaming hand-drawn Excalidraw diagrams with smooth viewport camera control and interactive fullscreen editing. | |
| integrity-checker-mcp eachristgr/roots-integrity-checker-mcp MCP server for the CMS File Integrity Checker. Enables users to submit and query file integrity jobs through natural language. | |
| MISP-mcp eacus/misp-mcp Enables AI assistants to interact with MISP threat intelligence platforms through natural language, supporting event search, creation, user management, and report generation. | |
| agent-handoff eadamesj/agent-handoff-ledger Enables Claude Code, Codex, and DeepSeek Harness agents to share a local SQLite task ledger with resumable handoffs, single-writer leases, append-only history, and a bounded handoff budget. | |
| Grain MCP Server eadm/grain-mcp-server Enables browsing, retrieving, and downloading meeting recordings and transcripts from Grain via browser automation, bypassing the need for enterprise API access. | |
| mcp-toolkit-server eadnyaix/mcp-toolkit-server Enables file operations, database queries, web search, and calculations through the Model Context Protocol, allowing integration with clients like Claude Desktop and Cursor. | |
| agent-stealthbrowser-adapter eagle10162015-coder/agent-stealthbrowser-adapter Provides a persistent headed CloakBrowser session with encrypted vault import, account listing/filling, password saving, and fingerprint health checks for LLM agents. | |
| Kamailio MCP Server eagle26/kamailio-mcp-server Enables AI-powered control and automation for Kamailio SIP servers, including config generation/linting, live JSONRPC operations, and database provisioning via MCP and CLI. | |
| PatchProof MCP eaglebooth/patchproof-mcp Enables local npm supply-chain inspection through tools for repository scanning, SBOM generation, dependency audit, and evidence reporting. Uses deterministic mock data and does not query live APIs. | |
| MCP Guidelines Server eagleffz/demo-ea-mcp A remote MCP server that serves versioned Enterprise & Architecture guidelines (security, architecture, compliance) to LLM clients via Streamable HTTP with Bearer-token authentication. | |
| MCP Research Server eaglelandsonce/mcp2_test Provides tools for automated company research, competitor identification, and business model analysis to generate comprehensive business intelligence. It enables users to extract market keywords and synthesize competitive insights via AI-po | |
| Engineering Knowledge Graph MCP Server eaglera/fishbowl Provides a stdio MCP bridge for coding agents to query and record engineering knowledge locally, preserving debugging history, failed attempts, and verified solutions. | |
| Planet Hunter MCP eagnespuerto/planet-hunter-mcp Connects AI assistants to Vetstar, MAST, SIMBAD, VizieR, Gaia DR3, ExoFOP-TESS, the NASA Exoplanet Archive, NASA ADS, Crossref/DataCite, the UAT, and Zenodo so users can vet TESS candidates, fit ephemerides, check contamination and novelty, | |
| utau-lyrics eagnespuerto/utau-lyrics-mcp Turns lyrics plus a chord progression into a .ust file for UTAU/OpenUtau (one note per syllable, pitched to the chords) together with a same-length backing track as .mid and .wav. Also previews syllable splits, renders backing from chords a | |
| MyAIServ MCP Server eagurin/myaiserv A high-performance FastAPI server supporting Model Context Protocol (MCP) for seamless integration with Large Language Models, featuring REST, GraphQL, and WebSocket APIs, along with real-time monitoring and vector search capabilities. | |
| fooddb eait-fit/fooddb Enables querying a global food nutrition database of generic and branded products, including search by name, lookup by barcode, and retrieval of resolved nutrient values pinned to a dated snapshot. Coverage spans USDA FoodData Central and O | |
| prettycode-mcp ealvaradomena/prettycode-agent Enables compatible AI clients to list, read, validate, preview, and apply local code changes in existing R and Python scripts through five MCP tools, without calling an AI model itself. | |
| Discord MCP Bridge eam2539/discord-mcp-bridge Enables local AI agents to securely search and read Discord messages and channels visible to the current client, without requiring a bot or user token. | |
| mssql-mcp eamonboyle/mssql-mcp An MCP server that enables AI assistants to query and manage Microsoft SQL Server databases using natural language. | |
| mcptape eange1o/mcptape Enables users to record any stdio MCP server session once, replay it offline with identical responses, and diff recordings to pinpoint behavior drift. | |
| gemini-mcp-bridge eanikishin-hub/gemini-mcp-bridge Enables Claude to work with a user's Google/Gemini subscription to generate and edit Nano Banana images, manage and continue Gemini chats, choose models and Gems, run Deep Research, and check usage limits, with output files delivered as tem | |
| WeChat Provider eaopen/wechat-provider Enables local MCP clients to inspect WeChat chats, retrieve and search indexed messages, and submit tracked send-message tasks through native desktop automation on macOS and Windows. | |
| nocturna-mcp eaprelsky/nocturna-mcp MCP server for Nocturna astrology APIs, providing 20 tools for natal charts, transits, synastry, progressions, returns, and chart image rendering. | |
| openciv3 earakely-scale/agentenv-openciv-plugin Enables LLM agents to play a headless, deterministic 4X civilization game through ten MCP tools for turn briefs, unit orders, city management, research, and map exploration, with scoring against engine AI and do-nothing baselines. | |
| Warcraft III for AgentEnv earakely-scale/agentenv-wc3-plugin Enables an LLM agent to play a melee match against the game's built-in AI by exposing raw wc3env orders as MCP tools, with games graded and native replays saved. | |
| Amicus MCP Server earchibald/amicus-mcp A state persistence layer that enables seamless handoffs between different AI coding assistants by maintaining a shared context bus. It provides tools for tracking summaries, next steps, and active files to ensure continuity across developm | |
| earful earful-app/earful Enables agents to speak text and read documents aloud on the user's computer, with tools for speaking, reading, stopping playback, and saving audio. | |
| C4C: Mortgage Industry Regulations MCP Server earl-hash/c4c-mcp-server Enables AI tools to search, retrieve, and verify verbatim federal mortgage and consumer-finance regulatory text and citations, check currency and version status, and run guided compliance review playbooks within a self-hosted environment. | |
| nc-mcp earlofburl/nc-mcp Enables LLM agents to read and write Nextcloud files, notes, calendars, tasks, contacts, and Talk messages through a secure authenticated MCP endpoint. | |
| mcp-gemini-image earlybird-technology/mcp-gemini-image An MCP server that provides image generation capabilities using Google's Gemini 2.5 Flash Image Preview model. | |
| notebooklm-py-diet-mcp earlyprototype/notebooklm-py-diet-mcp Connects AI coding agents to Google NotebookLM, enabling querying notebooks, adding sources, and generating artifacts like reports, podcasts, and slide decks. | |
| remote-jobs-api earnnova-dev/remote-jobs-api Live normalized remote-job data across 5 boards — one keyless endpoint, one schema, skill fit-score. No API key required. Tools: search jobs by skills + salary floor, live market stats, and computed salary bands. | |
| mcp-feedback-enhanced earthchen/mcp-feedback-enhanced MCP server that establishes feedback-oriented development workflows with dual Web UI and desktop application interfaces, enabling AI to confirm with users via prompts and real-time feedback to reduce speculative operations and improve effic | |
| Claude-Flow earthmanweb/claude-flow-plugin Multi-agent AI orchestration platform for Claude Code that enables deploying and coordinating specialized agents in swarms with self-learning, fault-tolerant consensus, and enterprise security. | |
| mcp-wp-cli-terminus earthmanweb/mcp-wp-cli-terminus Enables AI agents to run WP-CLI commands on WordPress sites, including byte-faithful post and meta copying with checksum verification, over local Docker, Pantheon Terminus, or SSH. | |
| tideline earththing/moon_and_tides MCP server that provides tide predictions, station lookup, and tidal event alerts for US coastal locations using live NOAA data. | |
| code-graph-mcp eas4ai/code-graph-mcp MCP server for comprehensive code analysis, navigation, and quality assessment across 25+ programming languages. | |
| EaseCation User Center MCP Server easecation/ec-usercenter-mcp-server An MCP server for the EaseCation user center that provides admin and user tools to interact with UC backend services. | |
| rhino-mcp easehee/rhino-mcp Enables Claude to drive Rhino 8 and Grasshopper for geometry creation, manipulation, and analysis via natural language. | |
| exyu-mcp easingthemes/exyu-mcp An MCP server that gives AI agents ex-Yugoslav cultural context, resolving cultural references with accurate quotes, attributions, and slang meanings from a citable database. | |
| Google Trends MCP eason-gao3/google-trends-mcp A production-grade Google Trends MCP server for AI workflow integration. Supports batch research of up to 50 keywords with cross-batch normalization, compare up to 5 keywords precisely, async task support, REST API + GPT Actions, and 7 majo | |
| draw-io-mcp eason-pan-ep/draw-io-mcp Enables creating and editing Draw.io diagrams via natural language, supporting shapes, connectors, and multi-line text. | |
| Sui MCP Server easonc13-agent/sui-mcp An MCP server providing tools for Sui blockchain interaction, including wallet management and Move smart contract development. It enables users to build, test, and publish contracts, query on-chain objects, and execute transactions through | |
| linux-harness-mcp easontechno/linux-harness-mcp Exposes a Linux host with shell, Python, and filesystem tools as MCP tools over HTTPS, enabling AI agents to execute commands and manage files remotely. | |
| KCSC Standard MCP easternwise98/kdh-standard-mcp Parses Excel/PDF construction calculations and retrieves Korean construction standards (KCSC/KDS/KCS) for AI-driven review, enabling automated structural calculation verification. | |
| mysql-mcp eastgatedev/mysql-mcp A MySQL MCP server for local stdio clients, enabling database queries and management with read-only/write modes, audit logging, and configurable security. | |
| konquest-meta-ads-mcp eastmapquest735/konquest-meta-ads-mcp A Windows-ready MCP server to manage Meta Ads with Claude Code, providing ad creation, targeting checks, diagnostics, and safety gates for supervised ad operations. | |
| shopping-mcp eastmg/dsh-shopping-mcp Unifies Taobao, JD, and Pinduoduo product search, item detail lookup, and affiliate link conversion (including coupons) into one set of tools exposed to MCP clients, using only official open-platform APIs. Runs in mock mode with realistic f |
46,701–46,750 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.