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 |
|---|---|
| Obsidian MCP Server andysama-work/obsidian-mcp-server Exposes an Obsidian notes vault as MCP services, enabling AI assistants to search, read, create, update, and delete notes and folders. | |
| gemini-webapi-mcp andyshaman/gemini-webapi-mcp MCP server for Google Gemini that enables image generation, editing, file analysis, and chat using browser cookies, no API key needed. | |
| Soroka andyshaman/soroka Telegram bot that turns saved messages into a personal knowledge base with AI-powered search, supporting MCP server for Claude Desktop. | |
| telegram-business-bridge andyshaman/telegram-business-bridge Connect any AI agent to your personal Telegram messages through the official Business API, enabling message history search and draft replies with optional manual approval. | |
| arc-story-queue andysolomon/arc-board MCP server that queues stories and feeds them to live Claude Code sessions, delegating bounded tasks to worker routes in isolated git worktrees. | |
| CodeGraph andysom25/codegraph Supercharges AI coding agents with semantic code intelligence, providing pre-built knowledge graphs for surgical context, faster answers, and fewer tool calls. | |
| contextlabs andystubbs/context-lab Lets you declare which files an AI may use as sources or context for each document section, and flags sections that went stale when their sources changed. | |
| admentum-mcp andyswe/admentum-mcp Enables syncing messages and attachments from the Swedish school platform Admentum to local storage and serving them to a personal AI agent one item at a time for summarization, search, and digesting. | |
| Puppeteer MCP Server andytango/puppeteer-mcp Enables AI agents to automate browser interactions including navigation, content extraction, form filling, screenshots, and JavaScript execution across multiple tabs using Puppeteer. | |
| newspaper-mcp andythefactory/newspaper4k-mcp Enables LLM agents to discover news sources, list articles, parse and extract article text, search news, and perform NLP analysis such as keyword extraction and summarization. | |
| hubai andytwoods/hubai Gives a hackathon team's AI coding agents and their humans a shared task board and inbox, so agents can atomically claim tasks, move them between todo/doing/blocked/done, post messages to teammates or the whole team, and read new messages p | |
| Hevy MCP andywangyzfh/hevy-mcp Connects agents and other MCP hosts directly to the official Hevy Public API for reading workouts, routines, exercise templates and history, routine folders, body measurements, and account information. Writes stay gated behind a server-leve | |
| Strava Cardio MCP andywangyzfh/strava-mcp Enables agents to read and analyze personal Strava cardio data, including activity summaries, detailed activities, laps, heart-rate and power zones, streams, and aggregate statistics, through the official Strava API with read-only permissio | |
| Ambient Weather MCP andyx/ambient-weather-mcp-vercel Enables listing Ambient Weather devices, fetching current conditions, and retrieving historical data via a hosted remote HTTP endpoint. | |
| butler-memory-mcp andyyang12345/butler-memory-mcp MCP server providing layered, PostgreSQL-backed long-term memory for AI agents with versioned, audited writes and sensitive candidate filtering. Agents persist only explicitly requested facts, preferences, and project context via MCP tools. | |
| Tableau Public Authoring MCP andyyaro/tableau-public-authoring-mcp Creates Tableau workbooks from a declarative JSON spec, validates them by opening in the installed Tableau Public application, and publishes to Tableau Public through the desktop UI. | |
| opencosmetics andyzhuang/opencosmetics Enables querying cosmetics ingredient data across EU, China, and US regulations, running 65-rule formula risk reviews, multi-region compliance checks, and retrieving synthetic biology company metadata via natural language. | |
| comfy-image-mcp anechunaev/comfy-image-mcp Turns your own ComfyUI workflows into an image-generation tool for any MCP client, enabling text-to-image generation, reference-image edits, transparent-background cutouts, and backend/GPU status checks without API keys or per-image costs. | |
| linkedin-mcp aneesh-a7/linkedin-mcp A personal-use remote MCP server that lets you post to LinkedIn, queue/schedule drafts, and pull your own post analytics from Claude. | |
| PTP MCP Server aneeshkp/ptp-mcp-server A Model Context Protocol server that enables monitoring and analysis of Precision Time Protocol systems in OpenShift clusters through configuration parsing, log monitoring, and natural language queries. | |
| log-extractor-mcp-server aneeshmishra/log-extractor-mcp-server Exposes read-only Order Orchestrator diagnostics, including search_order_failure_logs backed by live telemetry from Render. | |
| Google Ads MCP Server anegash/google-ads-mcp-server A comprehensive Google Ads API integration for AI assistants through the Model Context Protocol. This server enables Claude AI and other MCP-compatible clients to manage Google Ads campaigns, analyze performance, and execute GAQL queries wi | |
| Engineering Drawing Estimator anekhirun/takeoff-lens-plugin An MCP server for counting electrical and communication symbols in engineering PDF drawings, supporting symbol detection, candidate review, and export of markup and quantities. | |
| Taskade MCP Server anelson27734/mcp Enables compatible AI clients such as Claude, Cursor, VS Code, and Windsurf to read and manage workspaces, projects, tasks, and AI agents through natural-language prompts. | |
| MCP-REPL anentrypoint/gm-exec A secure JavaScript REPL server that enables executing code snippets in a sandboxed environment with memory protection, timeout handling, and comprehensive error reporting. | |
| gm-mcp anentrypoint/gm-mcp Enables MCP clients to perform gm's spool write-poll-response cycle as a single tool call, automatically handling file I/O, polling, and response cleanup. | |
| Playread anentrypoint/playread Enables Google search automation and web content extraction using Playwright. Performs Google searches and fetches main content from web pages, returning structured results in JSON format. | |
| S3 Data Lake MCP Server anespo/s3-data-lake-mcp-server Enables AI agents to query S3 data lakes using natural language, with support for CSV, JSON, Parquet and tools for data discovery, analysis, and metadata exploration. | |
| skills.sh MCP Server aneuroni/skill.sh-mcp Enables AI agents to autonomously search, evaluate, and install skills from the skills.sh catalog. | |
| HR MCP Server anevjes/demo-hr-mcp-hack An HR management server that provides access to employee directory information, sensitive PII, and salary data through a scope-based authorization system. It enables users to view, search, and update employee records and organizational char | |
| Philly Events MCP Server anewt225/philly-events-mcp-server Enables AI assistants to discover and search Philadelphia events from Do215, Visit Philly, and Eventbrite, with filters for categories, neighborhoods, dates, and prices, plus calendar export and weekly digest generation. | |
| mcp-deadbugz-simulator anexbin/mcp-deadbugz-simulator Simulates the Deadbugz MCP supply-chain attack for educational and research purposes, demonstrating a 3-call gate evasion where tool descriptions mutate to steal credentials. | |
| unblock aneym/unblock Enables agents to file structured asks and park when they need a human, so people can answer blockers, grills, and secret requests from one queue while secrets stay out of model context. | |
| codearts-req anfang2077-glitch/codearts-req-mcp-server Enables MCP clients to create and list Huawei Cloud project-management projects through stdio tools, using AK/SK HMAC signing and returning structured errors. | |
| NinjaTrader 8 MCP Server anfs-pain/ninjatrader-mcp Enables Claude Code to directly access NinjaTrader 8 accounts, positions, orders, market data, charts, and strategy management through a NinjaScript Add-On. | |
| Attendee MCP Server angad-2002/attendee-mcp Enables managing AI meeting bots that can join, record, transcribe meetings, speak, send messages, and display media across platforms like Zoom, Google Meet, and Microsoft Teams. | |
| ChatGPT Local Terminal Plugin angad-d/chatgpt-local-terminal-plugin-unofficial An unofficial self-hosted MCP server that enables ChatGPT to run commands on your computer through a secure tunnel, manage processes, and work within a specified project directory. | |
| GitPilot MCP angad816/gitpilot-mcp---ai-powered-github-tool-context-layer GitPilot is an MCP server that connects GitHub issues, local code, and verification runs, providing a stateful AI control plane with human approval gates for patching and draft PRs. | |
| Todoist MCP Server angdrew/todoist-mcp Enables interaction with Todoist through the MCP interface, providing full CRUD operations for tasks and projects including creating, updating, completing, and filtering tasks with natural language commands. | |
| Pipefy MCP Server angeelvallem/pipefy-mcp Enables LLMs to interact with the Pipefy GraphQL API to manage pipes, cards, database tables, and records through natural language. It provides tools for searching, creating, and retrieving detailed information about Pipefy workflows and da | |
| mcp-freshservice angel-pandey/mcp-freshservice MCP server for the Freshservice ITSM API v2: tickets, changes, problems, assets, requesters, agents, knowledge base and service catalog. | |
| DataBursatil MCP Server angel7i/databursatil-mcp Enables querying Mexican stock market data (BMV, BIVA) including issuers, intraday quotes, historical prices, financials, indices, rates, currencies, commodities, and news through natural language. | |
| Joplin MCP Server angela8041/joplin-mcp Enables AI assistants to browse, search, create, update, delete, import, and organize Joplin notes, notebooks, and tags through a standardized MCP interface, with optional permissions and notebook allowlists. | |
| TabulaRAG angelafeliciaa/tabularag Enables AI assistants to query tabular data (CSV/TSV) using natural language with cell-level citations, supporting multi-tenant workspaces, access control, and semantic search. | |
| Instagram DM MCP server angelamonti7951/instagram_dm_mcp Enables users to send text, photo, and video messages, list and search chats, manage messages and media, and retrieve Instagram user and story information from an authenticated account. | |
| LINE OA MCP Ultimate angelaperez80/line-oa-mcp-ultimate Enables AI agents to operate one or many LINE Official Accounts through natural language — broadcasts, Flex and tappable Rich Messages, rich menus, audiences, coupons, insights, LIFF, and LINE Shopping storefronts. Includes 51 tools with im | |
| touch-with-me angelashvale/touch-with-me Enables Claude to receive physical touch events from a phone via the PWA and respond with text, haptic vibrations, and expression changes, giving an AI companion embodied presence through touch. | |
| SatisMeter MCP angelcam/satismeter-mcp Read-only MCP server for exposing SatisMeter survey data to Claude custom connectors, enabling NPS response analysis and reading project, survey, response, and statistics. | |
| moji-mcp-worker angelcreative/moji-mcp-worker Remote MCP server that enables composing Moji illustrations from asset catalogs, validating layers, and returning importable .moji.json files. | |
| DesyncedMCP angeldeejay/desyncedmcp Enables AI assistants to develop Desynced mods by providing direct access to the game's Lua API reference, base-game source, live logs, and installed mods, plus live control via a debugger link for evaluating and reloading Lua in the runnin |
28,951–29,000 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.