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 |
|---|---|
| codifier-mcp alcor6502/codifier-mcp A self-hosted MCP server that maintains a registry of project rules, enabling chats to query which rules apply to them in one call. It manages rule lifecycle with scopes, expiry, approval batches, and immutable history. | |
| OffSec alcyjones/offsec-by-truehacking Enables AI assistants to conduct penetration testing and offensive security workflows, including reconnaissance, exploitation, post-exploitation, threat intelligence, malware analysis, forensics, and reporting through MCP tools. It supports | |
| Aldabra CVE Watch aldabra-sh/cve-mcp Connects MCP clients to a public CVE activity feed and private product watches, letting agents search advisories, save watched products, check and acknowledge matches, and track new or updated vulnerability records. | |
| asc-mcp aldanchenko/asc-mcp Enables MCP clients to read apps, customer reviews, and TestFlight builds from App Store Connect and publish developer replies to reviews while keeping API credentials local. | |
| Family MCP Server aldanin/family-mcp-server MCP server for TheDaninFamily database with tools to query family events and dates. | |
| MCP UJI Academic Server aldanjjay/mcp_uji_academic Enables querying academic data from Universitat Jaume I, including subjects, degrees, locations, and schedules, via MCP-compatible clients. | |
| Aldeano Build MCP aldeanoo/aldeano-build-mcp Enables AI agents to perceive, navigate, interact with, and build inside Minecraft through typed, bounded operations, including deterministic blueprints, verified builds, repair, and creative-mode flight or teleport. Runs as a provider-neut | |
| mcp-rncp aldebertarnaud/mcp-rncp Enables querying French national directories of professional certifications (RNCP/RS) for certification details, validity, competence blocks, and habilitation status using natural language. | |
| mcp-arena aldegad/mcp-area A robot battle prototype that enables users to design, validate, and simulate AI combat scripts through an MCP-integrated consultative workflow. It allows AI agents to guide tactical design, perform DSL script verification, and conduct prev | |
| hyprland-mcp alderban107/hyprland-mcp An MCP server for Hyprland desktop automation that allows AI assistants to see the screen, control mouse and keyboard, and manage windows using native Wayland tools. It integrates OCR for text-based interaction and supports complex multi-mo | |
| Pepe-MCP-Server alderetesergio/pepe-mcp-server Provides AI-powered research capabilities through Perplexity's web interface, enabling web search, deep research, chat, and documentation retrieval without API keys. | |
| MCP Wyze Server aldilaff/mcp-wyze-server Enables control and monitoring of Wyze smart home devices through AI assistants. Supports device discovery, control (on/off, brightness, color), group management, and health tracking for scales with real-time status monitoring. | |
| Cisco PSIRT OpenVuln MCP Server aldoleiva1/mcp-svr-openvulnapi A production-quality MCP server for querying Cisco security advisories via the PSIRT OpenVuln API v2, enabling LLM-powered interfaces to search, filter, and analyze Cisco vulnerability data. | |
| ToolPipe MCP Server aldric-core/toolpipe-mcp-server Provides a suite of 35 developer utility APIs including code formatting, data conversion, and infrastructure generation. It enables AI agents to perform tasks like JSON validation, Dockerfile creation, and network lookups directly through n | |
| Research Validator MCP Server aldrin-56/mcp-research-validator A pure-AI cognitive extension that forces standard 3-Layer Validation to prevent hallucination in academic research. | |
| paperstack aldrin-joan/paperstack Enables arXiv paper search, PDF download, text extraction, and context chunking for LLM pipelines, along with advanced features like citation graphs and reproducibility scoring. | |
| Metal MCP Server aldrin-labs/metal-mcp-server Enables interaction with the Metal Framework by providing documentation search and code generation capabilities using natural language queries. | |
| Metaplex MCP Server aldrin-labs/metaplex-mcp-server The Metaplex MCP Server facilitates access to Metaplex documentation and repository details, enabling users to search and interact with various Metaplex resources through the MCP protocol. | |
| solana-docs-mcp-server aldrin-labs/solana-docs-mcp-server solan docs context | |
| solana-mcp-server aldrin-labs/solana-mcp-server mcp server that allows to do actual actions related to solana
first version adds knowledge about RPC methods and how to call them | |
| kairo aldtorri/kairo Autonomously analyzes projects, generates Playwright tests via OpenAI, runs them, classifies failures, and recommends fixes, iterating up to 3 times. | |
| NeuroRisk aldunate46/neurorisk Enables voice-based early cognitive screening through an 8-step questionnaire, scoring responses with a SageMaker-hosted risk model and persisting session history to S3 for progress tracking. | |
| Google Calendar MCP Server alduncanson/gcal-mcp Provides tools to query, search, and list Google Calendar events using the Model Context Protocol. It enables natural language interaction for checking schedules, searching for keywords, and retrieving upcoming meetings. | |
| Tall MCP Server ale-santos/tall-mcp Provides AI assistants with local access to Filament, Laravel, Livewire, and Pest documentation, enabling offline reference and search. | |
| nano-vm-mcp ale007xd/nano-vm-mcp Governed agent execution gateway for LLM workflows, providing deterministic FSM-based execution, audit trails, and idempotency guarantees via MCP. | |
| sicop_mcp ale241302/sicop_mcp Enables AI assistants to query and analyze Costa Rica's public procurement (SICOP) data, including supplier profiles, market trends, product price histories, and bid comparisons, through a suite of MCP tools. | |
| intervals-mcp ale7canna/intervals-mcp MCP server for intervals.icu that reads training data (activities, wellness, calendar) and creates structured workouts on the calendar, which are pushed to devices like Garmin, Wahoo, Zwift, Coros, Suunto via the official API. | |
| folio-mcp alea-institute/folio-mcp MCP server for FOLIO, the Federated Open Legal Information Ontology. Makes the full ontology available to AI agents as searchable, browsable tools. | |
| commerce-mcp-server aleayrees-com/commerce-mcp-server Enables e-commerce operations such as product search, price updates, and order notes via MCP tools, with secure credential handling. | |
| Second Brain Control Plane MCP Server alebellotta/second-brain-control-plane Provides semantic search, note retrieval, source explanation, daily digests, and health checks for a local Obsidian vault, enabling MCP clients like Claude Desktop and Claude Code to query the second brain via natural language. | |
| mcp-decision-lab alebrito124356/mcp-decision-lab MCP server that enables structured decision-making using weighted decision matrices, sensitivity analysis, and robust recommendations. | |
| mcp-devils-advocate alebrito124356/mcp-devils-advocate Enforces structured adversarial reasoning via devil's advocate, premortem, assumption audit, and steelman protocols to stress-test claims and decisions. | |
| mcp-git-historian alebrito124356/mcp-git-historian MCP server for git archaeology — churn hotspots, blame summaries, bus factor, commit forensics and file history over any local repository. | |
| mcp-memory-vault alebrito124356/mcp-memory-vault An MCP server that gives agents persistent memory with namespaced facts, tags, full-text search, and TTL expiry, all running locally on SQLite with zero external dependencies. | |
| instagram-publish-mcp alebros20/instagram-publish-mcp Enables AI agents to publish images and Reels to an Instagram Business account through the Meta Graph API, with tools for uploading media, creating and publishing containers, managing comments, and retrieving insights. | |
| Alex's Zendesk MCP Server aleburbridge/alexs-zendesk-mcp-server Enables interaction with Zendesk to manage tickets, retrieve ticket fields, comments, and priority based on SLA, as well as get unsolved tickets by agent name. | |
| waymark aleburrascano/waymark MCP server exposing a codebase's OKF knowledge bundle to Claude Code with three schema-enforced query tools: list_concepts, read_concept, and find_concept_by_resource. | |
| radius-mcp-server alec13355/radius-mcp-server Provides full-text search and reading capabilities over Radius documentation and source code, enabling AI assistants to answer questions about the Radius project. | |
| Python Local MCP Server alec2435/python_mcp Provides an interactive Python REPL environment that maintains persistent session state, allowing users to execute Python code and access session history. | |
| streeteasy-mcp alec2435/streeteasy-mcp A remote MCP server that wraps the StreetEasy GraphQL API to enable LLM agents to search and parse NYC rental listings. | |
| storelink-mcp aleccritser/storelink-mcp MCP server exposing the StoreLink grocery stocking API as tools for category buyer workflows, including inventory checks and replenishment orders. | |
| notion-mcp-server alecgrater/notion-mcp-server Enables natural language queries on your Notion workspace, with comprehensive search, page hierarchy mapping, and tools for reading and writing Notion pages. | |
| woffu-manager alechagonzalo/woffu-adapter-mcp An MCP server to manage time tracking and time off on Woffu, allowing users to clock in days, view balances, request leave, and check team availability. | |
| MDS MCP alecharn/mds-mcp A lightweight MCP server that exposes read-only Cisco MDS NX-OS show commands as tools, allowing LLM clients to inspect SAN fabric in plain language. | |
| Blogger MCP Server aleck31/mcp-blogger Enables AI assistants to interact with the Google Blogger API v3 to manage blog posts and metadata. It supports the full post lifecycle including creating, updating, publishing, and deleting content through natural language. | |
| mcp-chrono aleck31/mcp-chrono A comprehensive time and calendar utility server that provides timezone conversions, date arithmetic, and business day calculations for AI agents. It features extensive support for the Chinese lunar calendar, including almanac data, festiva | |
| openshot-mcp alecray/openshot-mcp Enables AI agents to edit OpenShot 4.0 video projects by importing media, detecting a music beat grid, placing clips on the grid, and saving the project. | |
| byteplus-image-mcp alecslacker/byteplus-image-mcp Enables image generation via BytePlus ModelArk with intelligent model routing for logos, UI/UX mockups, and document illustrations. | |
| Doppler MCP Server aledlie/doppler-mcp Enables secure secrets management through the Doppler CLI via natural language interactions. Supports managing secrets, projects, configs, and environments across different Doppler workspaces. | |
| MCP PLAYLIST SERVER alee2602/mcp-server An MCP server that provides intelligent playlist curation tools using Spotify track data and audio feature analysis. It enables AI assistants to create mood-based playlists, find similar songs, analyze audio characteristics, and curate pers |
25,901–25,950 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.