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 |
|---|---|
| meetings-mcp aminafara123/meetings-mcp Exposes meeting transcripts to any MCP-capable AI client so it can list meetings, page through a single transcript, and search across all of them for a topic with exact timestamps. Speaker labels, emails, phone numbers, and paths are pseudo | |
| triage-mcp aminafara123/triage-mcp Enables MCP-capable AI clients to read a local AI ticket triage queue and human decision log through four read-only tools for checking queue status, listing pending review items, viewing recent decisions, and searching decisions. It does no | |
| workpapers-mcp aminafara123/workpapers-mcp Enables AI clients to query and trace ITGC audit workpapers, including controls from risk to test result, findings by rating and status, and open items. | |
| aisafety-mcp aminamos/aisafety-mcp A stateless, read-only MCP server that exposes the public AISafety.com directory API through eleven search tools, letting users query AI safety communities, organizations, events, training programs, jobs, funding opportunities, courses, adv | |
| artsmia-mcp aminamos/artsmia-mcp Enables searching and exploring over 90,000 artworks from the Minneapolis Institute of Art, including high-res images, gallery locations, artist bios, and curated highlights. | |
| blazemeter-explorer aminamos/blazemeter-explorer-mcp Enables querying and invoking BlazeMeter's public API v4 explorer operations, including vault settings, session management, and static asset routes. | |
| gbfs-mcp aminamos/gbfs-mcp Enables AI assistants and developers to search 1,000+ public bikeshare systems and fetch live station, free-floating vehicle, alert, and vehicle-type data through the General Bikeshare Feed Specification. | |
| genius-mcp aminamos/genius-mcp Enables searching Genius song and artist metadata, retrieving artist catalogs, and fetching annotations through the official Genius API. | |
| metrotransit-mcp aminamos/metrotransit-mcp Enables real-time bus and light rail departure lookups, route and station search, and service alerts for Minneapolis–Saint Paul Metro Transit through MCP. | |
| hindsight aminamos/muse-hindsight-connector Enables Muse Code to store and retrieve long-term memories via Hindsight, providing recall, retain, reflect, and status operations shared across coding agents. | |
| plex-mcp-server aminamos/plex-mcp-server Exposes every documented Plex Media Server API operation as a callable tool, plus curated tools for library browsing, media search and editing, playlists, collections, live sessions, user analytics, recommendations, watchlists, playback con | |
| studyofus-agent aminamos/studyofus-agent Enables local agent interactions with a mock Study of Us API through tools for health checks, catalogs, current user info, reports, and voting. | |
| tods-mcp aminamos/tods-mcp Enables LLMs and developers to inspect, validate, and merge Transit Operational Data Standard feeds with GTFS supplements, query crew runs, vehicle block assignments, and deadheads, and run these operations via MCP or CLI. | |
| transit-mcp aminamos/transit-mcp Enables AI assistants to access real-time and scheduled public transit data, including routes, stops, departures, and service alerts, across multiple US metropolitan areas. | |
| selfos-mcp aminebenaceur/self.os Turns any MCP-capable AI assistant into a goal coach backed by a local plain-text vault. Enables creating goals with if-then plans, logging check-ins and habit outcomes, searching notes, and generating weekly reviews, with all reads and wri | |
| InterLogue aminehamlouchi/interlogue Enables users to brief an assignment, record human approval before contact, run a text interview from a fixture, produce a reporter's packet, and check a host-written piece so every quote resolves verbatim to a transcript timestamp before i | |
| Daft.ie MCP Server amineremache/dafty-mcp An MCP server that enables interaction with the Daft.ie API for searching rental properties and retrieving detailed information about specific rental listings. | |
| SupliiChain MCP Sandbox aminersolution/supliichain-mcp-sandbox A lightweight, local inventory-intelligence MCP server that enables querying structured inventory schemas with read-only, zero-config tools for stock levels, velocity metrics, and purchase orders. | |
| io.github.amineutron/mcp-guard amineutron/mcp-agent-template Enables LLM agents to safely invoke enterprise MCP tools under an enforceable guard that applies allowlist policies, caller roles, parameter restrictions, human confirmation for destructive operations, and a correlated JSONL audit log. | |
| MATRIX aminfara/matrix A local, project-scoped requirement management MCP server that enables AI agents to manage tasks and requirements via SQLite. | |
| GSC MCP Server v2 - Remote Edition aminforou/google-search-console-mcp-v2 Connects Claude AI to Google Search Console with OAuth 2.0 authentication, enabling users to analyze search performance, inspect URLs, manage sitemaps, and export analytics data through natural language conversations. | |
| Google Search Console MCP aminforou/mcp-gsc Connects Google Search Console with Claude AI to enable SEO professionals to analyze their SEO data through natural language conversations, providing access to property information, search analytics, URL inspection, and sitemap management. | |
| mcp-printer aminha1248/mcp-printer Let Claude print documents on any USB or network printer. | |
| scanner-mcp aminha1248/scanner-mcp Enables scanning documents via network (eSCL) or USB (WIA/SANE) scanners, returning inline images, OCR text, or saved PDFs for Claude to read. | |
| okf aminhzdev/opencontextscitool Builds a keyword-searchable index from markdown documentation bundles and serves it to LLM agents via MCP, with retrieval logging and reporting for curation. | |
| mcp-de-picnic aminm1364/mcp-de-picnic Enables LLMs to search Picnic's grocery catalog, manage the shopping basket, and select delivery slots for Picnic's grocery service in Germany and the Netherlands. | |
| Bale MCP Server aminmadaniofficial/bale-mcp-server Enables LLMs to authenticate with a Bale Messenger account and then inspect dialogs, read chat histories, send/edit/forward messages, and manage contacts, groups, channels, reactions, and presence. Supports multiple locally stored account s | |
| coolify-mcp amintt2/coolify-mcp Enables AI agents to manage self-hosted Coolify v4 instances, including listing applications, safely handling environment variables with masking and dry runs, deploying, restarting, and reading logs. | |
| fluentui-mcp-server aminvishvam/fluentui-mcp-server Comprehensive MCP server for Fluent UI React v9 development, providing component knowledge, design tokens, code generation, and validation tools. | |
| mcp-devdb aminyx/mcp-devdb A safe, read-only MCP server for local development databases (PostgreSQL and SQLite) that provides guarded introspection tools like schema listing, sample rows, and explain plans with column masking and query budgets. | |
| Shopify MCP Server amir-bengherbi/shopify-mcp-server Enables interaction with Shopify store data using the GraphQL API, supporting product, customer, and order management with comprehensive error handling. | |
| QA-MCP-Learning-Lab amir-yaqoob/qa-mcp_learning-lab Showcases principal-level QA architecture using MCP tools and Playwright for validating security, business workflows, contract safety, and cross-layer consistency. | |
| mcp-trellis amir1824/mcp-trellis ost-agnostic MCP + OAuth ports — you bring the runtime and IdP; the library owns the connector protocol.
Web-standard Request → Response. Same handler on Cloudflare Workers, Next.js App Router, Deno, Bun, and Node HTTP via mcp-trellis/node | |
| Binance MCP Server amir45400/binance-mcp1 Provides live Binance USDⓈ-M Futures market data via WebSocket, including prices, 24h tickers, order books, recent trades, and kline candles. | |
| tradefloor-mcp amir45400/tradefloor-mcp-main Enables AI assistants to analyze smart-money market structure from candlestick data, identifying trend, character shifts, liquidity sweeps, fair value gaps, order blocks, and pullback zones. | |
| S22 Web Agent MCP Server amir89hamzah/s22-web-agent Provides MCP tools for web page scanning, data extraction, local storage, markdown report generation, and browser inspection using Playwright on a Samsung S22. | |
| Basecamp MCP Server amira0293/basecamp-mcp-server Enables MCP-capable clients to read and manage Basecamp 3 projects through OAuth-authenticated API calls, covering projects, todos, messages, card tables, documents, uploads, comments, events, webhooks, and search. | |
| Stock MCP amira762/stock-mcp Enables AI agents and HTTP clients to access standardized financial market data and analysis across A-shares, US equities, ETFs, indices, and cryptocurrencies, including technical indicators, fundamentals, news, filings, money flow, and CSV | |
| Octopus Deploy Official MCP Server amira851/mcp-server Enables AI assistants to inspect, query, and diagnose problems within an Octopus instance, and optionally create releases, deploy releases, run runbooks, and adjust feature toggles through MCP tools. | |
| LinkedIn MCP Server amiradmin/linkedin-mcp-server Enables AI assistants to publish public text posts to an authenticated LinkedIn profile via the Model Context Protocol. | |
| Jira JQL Tool amiralamox/mcp-servers Enables Claude to interact with Jira through JQL (Jira Query Language) queries using the Model Control Protocol, allowing natural language access to Jira issue tracking and project management. | |
| remote-access-mcp amiralimanzar/remote-access-mcp Turns any Linux server into an AI-agent-accessible machine over HTTPS, allowing MCP clients like ChatGPT, Claude, and Grok to securely control files, run shell commands, inspect system state, query SQLite, and work with git behind a bearer | |
| CodeBot MCP Server v2 amirbiron/mcp-server An extended MCP server for managing code snippets, performing code analysis, and handling deployments via Render and GitHub. It enables users to perform code reviews, track issues, and manage service operations through natural language inte | |
| opencode-samcp amirdaraby/opencode-samcp Enables AI agents to spawn and manage headless opencode sessions as sub-agents for coding work, including parallel jobs, session continuation or forking, transcripts, and cleanup. It returns structured results such as final messages, tool-c | |
| Dritan MCP amirdauti/dritan-mcp Enables personal agents to access Solana market data and execute token swaps via the Dritan SDK while maintaining local wallet security. It provides tools for wallet management, real-time token price tracking, and secure transaction signing | |
| Open-Meteo MCP server amirhoseintaghizadeh/open-meteo-mcp Gives language models weather tools for place search, multi-day forecasts, and location comparison, with no API key or configuration required. | |
| Server MCP Agent amirhossein-danesh1234/server_mcp Enables ChatGPT and MCP clients to safely inspect and operate a Linux host through OAuth-protected, workspace-bounded file, Git, process, systemd, and Docker diagnostics, plus human-approved edits and operations. | |
| Balsamiq Wireframes MCP Server amirhossein-papakikashani/balsamiq-mcp-server Enables AI assistants to autonomously create, layout, and export interactive UI mockups as native .bmpr files or Wireframe JSON, integrating with Balsamiq Wireframes 4.x. | |
| AIO Tests MCP Server amirhosseinhanifehzadeh/aio-tests-mcp Enables searching, reading, creating, and updating AIO Tests test cases in Jira from any MCP client, supporting Jira Cloud and Server/Data Center with a read-only mode. | |
| commits-to-issues amirhosseinkz/commits-to-issues Lets AI agents turn a repository's git history into proposed GitHub issues grouped into units of work, each with a commit checklist and links, then create and close them only after approval. Planning is read-only and creation defaults to a |
28,101–28,150 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.