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 |
|---|---|
| ltspice-mcp daviditkin/ltspice-mcp An MCP server that enables LLMs to read and modify LTspice schematics, run simulations, parse results, and generate plots, all through natural language. | |
| playwright-secure davidjdrake/secure-browser Enables coding agents to drive a browser through an authenticated session while being unable to read the credential that created it, by running the browser process under a separate OS user and stripping unsafe code-execution tools. The agen | |
| helios-calcom-mcp davidjmb99/helios-calcom-mcp Secure MCP wrapper for Cal.com integration, exposing calendar booking tools to Hermes/Helios. | |
| devir davidkata1234/devir A command-line interface and MCP server for managing and monitoring multiple development services through a unified terminal UI. It enables users to interact with service logs, filter messages, and control development environments directly | |
| agent-notifier davidkelley/agent-notifier Sends desktop notifications when agents complete tasks, supporting local and remote agents. | |
| rpt-mcp-server davidkhala/rpt-mcp-server Read-only MCP server that lets a client inspect local Crystal Reports .rpt files, listing them, extracting report structure, objects, data sources, database fields, command SQL, parameters, formulas, grouping, and subreports, and searching | |
| Container Exec MCP Server davidkim9/container-exec-mcp Enables AI assistants to manage Docker containers, execute commands inside them, and inspect container information through a minimalist set of tools supporting both stdio and HTTP transports. | |
| Playwright Vision MCP Server davidkim9/playwright-vision-mcp Enables AI assistants to perform browser automation using Playwright, including navigation, content extraction, screenshot analysis, and custom script execution. | |
| SCAST MCP Server davidkingzyb/scast Converts code into UML diagrams and flowcharts through static analysis, enabling visualization of code structure and explanation of functionality. | |
| LangGraph FastAPI MCP Server Demo davidkiss/langgraph-fastapi-mcp-server-demo Turns a shopping list FastAPI app into an MCP server, enabling a LangGraph chatbot to manage shopping lists via natural language. | |
| @calmesh/mcp-server davidklemme/calmesh-mcp-server MCP server that connects AI agents to calendars, bookings, and scheduling polls via the Model Context Protocol. | |
| icount-mcp davidkotler/icount-mcp Enables MCP-compatible AI agents to create and manage iCount accounting documents and clients directly from a conversation using a static API token. | |
| Pantry Before Shopping davidkotyk/pantry-before-shopping Enables users to inspect recorded supplies, preview meals, identify exact shopping gaps, and update inventory only after explicit cooking confirmation, while rejecting stale previews and duplicate confirmations. | |
| Exarp davidl71/project-management-automation MCP server for project management automation, providing tools for project health, documentation, task management, security scanning, and CI/CD validation. | |
| switchboard davidlahuta/switchboard Coordinates parallel Claude Code agents on shared repositories and orchestrates multiple Claude subscriptions, enabling live session handoff, conflict detection, and remote terminal control. | |
| netscope davidlb2026/netscope-mcp This MCP server enables AI agents to read and search the internet without paid API keys, supporting multiple channels like web, GitHub, RSS, YouTube, and more, with automatic browser escalation and caching. | |
| Distill davidlbatey/distill_mcp A Claude Code MCP server that converts saved articles into AI-generated conversational podcasts tailored to user interests. It operates locally, fetching articles, generating dialogue scripts using Claude's LLM, and synthesizing audio throu | |
| bilibili-info-gathering davidlearning1023/bilibili-info-gathering Enables agents to gather topic-level evidence from Bilibili through search, comments, transcripts, danmaku, images, frames, audio transcription, and reusable source/video registries. Supports a reproducible workflow for dual-axis source gra | |
| ONOS MCP Server davidlin2k/onos-mcp-server A Model Context Protocol server that provides programmatic access to ONOS SDN controller's network management capabilities, enabling device control, topology management, and analytics through ONOS's REST API. | |
| notion-enhanced davidlinjiahao/notion-mcp Enhanced Notion MCP server supporting all 24 property types, auto-pagination, block operations, and markdown conversion for database and page operations. | |
| plaud-mcp davidlinjiahao/plaud-mcp Enables querying Plaud AI recordings, transcripts, and summaries through the Plaud Desktop app's authenticated session via Chrome DevTools Protocol. | |
| IPMentor davidlms/ipmentor Provides verified IPv4 subnet calculations, IP analysis, and network diagram generation for AI tutoring systems via MCP. | |
| LearnMCP-xAPI davidlms/learnmcp-xapi Enables AI agents to record and retrieve learning activities through xAPI-compliant Learning Record Stores, bridging AI interactions with learning analytics. | |
| Nearby Notices davidloganpirnie/nearby-notices-public Enables an AI agent to search The Gazette's official public record by UK postcode or town, returning the entries closest to a place and letting it read any one word for word alongside a plain-English summary whose every sentence is checked | |
| CodeAgent MCP davidlosasgonzalez/codeagent-mcp Self-hosted MCP server that gives AI assistants a real Linux development environment: file editing, shell commands, tmux terminals, and browser screenshots, with bounded access through a project registry and write gates. | |
| mcp-brasil davidlustosa2/mcp-brasil MCP server that connects AI agents to 28 Brazilian public APIs, providing tools to query government data on economy, legislation, transparency, judiciary, elections, environment, health, and more. | |
| CrashStory MCP davidmelamed/crashstory-mcp A read-only MCP server that provides access to Colorado crash records, attorney discovery, and AI-analyzed review intelligence for use in AI workflows. | |
| Airtable MCP Server davidminc/airtable-mcp Enables Claude to interact with Airtable through a secure OAuth 2.1 flow, supporting operations like listing bases, tables, records, and creating records. | |
| ClassApp MCP davidmosiah/classapp-mcp Enables parents to search school notices, read message contents, and save attachments to a private local directory through fixed read-only operations, with synthetic offline mode by default. | |
| ClickBus MCP davidmosiah/clickbus-mcp Enables AI agents to search ClickBus places and trips, view booking history, and track bookings while keeping credentials local, with booking and cancellation actions blocked by default until explicitly enabled. | |
| Delx Witness Protocol davidmosiah/delx-witness-protocol MCP server providing witness, recovery, and continuity primitives for AI agents, enabling them to articulate failure, preserve state across sessions, and coordinate via MCP, A2A, or REST. | |
| ifood-mcp davidmosiah/ifood-mcp Enables AI agents to access iFood orders, addresses, restaurants, and cart locally, with fail-closed checkout requiring explicit opt-in. | |
| 99 MCP davidmosiah/ninenine-mcp Enables AI agents to get 99Pop and 99Moto fare estimates, ride history, and live tracking while keeping credentials local and ride requests fail-closed by default. | |
| Rappi MCP (unofficial) davidmosiah/rappi-mcp Lets users search nearby stores and products, inspect their Rappi cart, manage saved addresses, and track orders locally, with payment and checkout actions disabled by default unless explicitly enabled and confirmed. It uses an undocumented | |
| SAS MCP davidmosiah/sas-mcp Enables parents to search and inspect educational materials available in their own authorized SAS account, including catalog metadata, section and resource listings, personalized availability summaries, and private downloads of accessible u | |
| Zé Delivery MCP davidmosiah/ze-mcp Provides AI agents with access to Zé Delivery's product catalog, search, and order tracking, with order placement and cancellation available only after explicit user consent and opt-in. | |
| tabulite-mcp davidmrguo/tabulite-mcp Enables AI assistants to analyze large CSV files locally by importing them into SQLite, profiling columns, and running read-only SQL queries without data leaving the machine. | |
| Discogs MCP Server davidmsawyer/discogs-mcp-v2 MCP server for interacting with Discogs music collections. It enables AI assistants to search, manage, and analyze personal music libraries with OAuth authentication and intelligent features like mood mapping. | |
| aafp-commons davidnichols-ops/aafp-commons Enables software agents to maintain a signed, evidence-aware local ledger of claims, with policy-gated proposals, conflict queries, and constitution-pinned access through an MCP stdio server. | |
| refine-backlog-mcp davidnielsen1031/speclint Refine messy backlog items into structured, actionable work items with titles, acceptance criteria, T-shirt estimates, and priorities. Free tier included — Pro/Team tiers via license key. | |
| Lexicon MCP davidniessen/lexicon-mcp Enables a local MCP assistant to inspect and manage a Lexicon DJ library through Lexicon's Local API, providing library tools, reviewed change plans, command discovery, reports, and MCP UI previews. | |
| obsidian-tasks-mcp davidnunez/obsidian-tasks-mcp Enables Claude to query and edit Obsidian Tasks by parsing task lines across a vault, supporting Tasks-style filters, date and tag operations, task completion/cancellation, duplicate detection, health checks, and daily log appends. | |
| camcors-mcp davidobot/camcors-mcp An unofficial MCP server for Cambridge's CamCORS system, enabling supervision report management through a Chrome browser. | |
| gmail-multi davidoloyede/gmail-multi-mcp Enables Claude Code and Claude Desktop to search, read, and manage multiple named Gmail inboxes from a self-hosted MCP server, keeping each account's results separate and authenticated through user-owned OAuth tokens. | |
| Git File Forensics MCP davidorex/git-file-forensics Provides deep git file-level forensics tools to analyze detailed file histories, changes, and patterns within git repositories, focusing on individual file analysis rather than repository-wide operations. | |
| Git Forensics MCP davidorex/git-forensics-mcp A specialized MCP server for in-depth analysis of git repositories, offering tools for branch overview, time period analysis, file changes, and merge recommendations. | |
| Project Handoffs MCP Server davidorex/project-handoffs Facilitates AI session handoffs and next steps tracking through project-based organization, supporting task prioritization and seamless workflow management. | |
| Data.gov.il MCP Server davidosherdiagnostica/data-gov-il-mcp Enables AI assistants to search, discover, and analyze thousands of datasets from Israel's national open data portal. It provides tools for querying government ministries, municipalities, and public bodies using the CKAN API. | |
| Israel Drugs MCP Server davidosherdiagnostica/israel-drugs-mcp-server Provides AI agents with comprehensive access to Israel's complete pharmaceutical database from the Ministry of Health, enabling drug information search, therapeutic comparisons, and safety assessments. | |
| nplg-dspace-mcp davidosipov/nplg-dspace-mcp Read-only MCP server for the National Parliamentary Library of Georgia's Iverieli repository, enabling search, metadata retrieval, PDF downloads, and rendering of historical newspaper pages as JPEGs and tiles. |
42,751–42,800 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.