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 |
|---|---|
| mcp-knowledge-gaps ermintoygar/mcp-knowledge-gaps Identifies knowledge gaps in markdown vaults, ranks them by priority, generates research questions, and offers long-tail sampling to break confirmation bias. | |
| io.github.ermintoygar/vault-health-mcp ermintoygar/vault-health-mcp MCP server for Obsidian vault structural health checks, enabling users to find broken wikilinks, orphaned notes, and missing frontmatter, with auto-repair capabilities. | |
| chatGpt-ChatMode-to-roblox-mcp ermiwu/chatgpt-chatmode-to-roblox-mcp Connects ChatGPT to Roblox Studio's built-in MCP, enabling natural-language reading and writing of game data, including executing Luau code and modifying scripts and instances. | |
| avito-mcp ermizin/avito-mcp Enables an LLM to control a separate Chrome session on Avito for searching and parsing listings, reading account and Pro dashboards/statistics, switching profiles, and editing forms. Requires explicit confirmation for irreversible actions. | |
| svgo-jsx-mcp erneg/svgo-jsx-mcp MCP server for SVG optimization with JSX-compatible camelCase attribute conversion, including production-ready HTTP API with authentication, rate limiting, and usage tracking. | |
| SentinelMCP ernest-adjetey/sentinelmcp Enables AI agents to discover and invoke versioned external tools through an MCP or REST gateway with authentication, authorization, mutation safety, reliability controls, audit logging, and replay. | |
| DiscordMCP ernest1101/discordmcp Enables AI assistants to interact with a Discord account to read channels, send and manage messages, handle DMs and reactions, search messages, and update status. | |
| Web Intelligence MCP Server ernestalabs/mcp Provides AI agents with real-time web capabilities including live search results, markdown web scraping, business lead generation, and detailed company information. It enables agents to bypass knowledge cutoffs by accessing current web data | |
| markdownlint-mcp ernestgwilsonii/markdownlint-mcp Provides AI assistants with the ability to lint, validate, and auto-fix Markdown files to ensure compliance with established Markdown standards and best practices. | |
| cobos-apple-mail-mcp ernestocobos/cobos-apple-mail-mcp Unifies fast on-disk read and search with complete AppleScript writes, behind a mandatory safety layer with read-only mode, batch caps, dry-run, and undo for reversible operations. | |
| mcp-sqlite-explorer ernestoiiiwork/mcp-sqlite-explorer Enables Claude and other MCP clients to inspect a local SQLite database's tables, columns, and schema, and run safe read-only SQL queries with capped JSON results. | |
| Chaos Mesh MCP Server ernestolee13/chaos-mesh-mcp Enables AI assistants to perform chaos engineering and resilience testing on Kubernetes clusters through Chaos Mesh. Supports creating and managing 24 types of chaos experiments including network failures, stress tests, pod disruptions, and | |
| Gestion MCP Server ernestozeferinodiaz/gesoft-mcp MCP server that exposes the GestionIntegrantes REST API as tools, enabling authentication, management of personas, and user queries via natural language. | |
| Prism MCP Server erni-academy/prism-tooling Enables AI assistants to interact with InterSystems IRIS databases through SQL queries, document management, ObjectScript execution, debugging, and unit testing via the Atelier REST API. | |
| MCP-Grep erniebrodeur/mcp-grep A server implementation that exposes grep functionality through the Model Context Protocol, allowing MCP-compatible clients to search for patterns in files using regular expressions. | |
| FlutterFlow MCP Server erniecode/flutterflow-mcp Connects AI coding agents to FlutterFlow projects, enabling browsing, inspection, and modification of projects directly from the assistant. | |
| agentcheckpoint erniomaldo/agentcheckpoint An atomic key-value store for AI agent coordination, ensuring agents always work with the latest state. | |
| nc-forms-mcp erniomaldo/nc-forms-mcp MCP server for the Nextcloud Forms API v3 that enables secure creation, update, cloning, and validation of forms without exposing credentials to the AI agent. | |
| Csound MCP Server erno-szabados/musmcp Enables AI agents to synthesize sounds using Csound, including subtractive synthesis and drum synthesis, via Model Context Protocol tools. | |
| MarkScribe erodenn/markscribe A convention-aware MCP server for managing markdown files with YAML schema validation. It enables AI agents to read, write, search, and validate markdown notes while enforcing user-defined conventions across directories like Obsidian vaults | |
| jira-mcp-bridge erollando/jira-mcp-bridge A local-only MCP server providing safe, typed Jira tools for AI agents via Atlassian ACLI, enabling search, get issue, add comment, and transition issues with policy guardrails. | |
| bible-ecrivain erom/barda-mcp-ecrivain-bible MCP server for managing a writer's bible, a structured and searchable knowledge base of a narrative universe with tools for characters, places, events, and semantic search. | |
| Agent Harness Kit eromero815/agent-harness-kit Enables AI coding providers to run structured multi-agent workflows with shared documents, tracked tasks, handoffs, and health-gated completion. | |
| EU Compliance & Factur-X MCP Server eroniichan/mcp-eu-compliance Enables AI assistants to classify AI systems against the EU AI Act with requirement checklists and penalty exposure, generate and validate Factur-X / EN 16931 electronic invoices, and assess GDPR and NIS2 readiness directly from the IDE. Ru | |
| superpowers-mcp erophames/superpowers-mcp An MCP server that makes superpowers skills available to any LLM that supports the Model Context Protocol. | |
| Claude MCP File Server erosao/mcp A file management system powered by Claude AI that provides document access and manipulation through MCP protocol and Telegram bot integration, enabling users to interact with files via natural language commands. | |
| Orchestrator MCP Server eroslifestyle/orchestrator-mcp-server Coordinates up to 64 parallel expert agents for complex multi-agent orchestration and intelligent task routing within Claude Code. It enables users to analyze requests, manage hierarchical execution plans, and monitor active orchestration s | |
| Fortnox MCP Server erp-mafia/fortnox-mcp An MCP server for integrating with the Fortnox Swedish accounting system. Enables LLMs to manage invoices, customers, suppliers, orders, accounts, vouchers, and provides business intelligence analytics. | |
| typescript-mcp-sqlite-mini-lab erpepinomarino/typescript-mcp-sqlite-mini-lab A local MCP server that enables exploring and manipulating SQLite databases through MCP tools. | |
| ERPipe erpipe-org/erpipe Enables AI agents to interact with Odoo ERP through natural language, providing tools and prompts for data operations and record management. | |
| Synapse erpuae/synapse Enables LLM clients to securely read and write Frappe/ERPNext data under a real user's permissions, with audited calls and granular access control. | |
| better-mcp erquier/better-mcp A universal MCP server that provides AI agents with structured tools for filesystem, database, shell, and git operations, enabling seamless interaction with projects. | |
| bhe_mcp err0n-0x2a/bhe_mcp Connects LLMs to BloodHound Enterprise for natural language attack path analysis, Cypher queries, and exploration of Active Directory, Azure/Entra ID, and OpenGraph environments. | |
| TwilioManager MCP errajibadr/twilio_manager_mcp A server that connects Claude AI to Twilio through the Model Context Protocol, enabling prompt-assisted management of Twilio accounts, phone numbers, and regulatory compliance. | |
| CommerceBook MCP Server errc02/commercebook-agents Enables agents to read a verified-warehouse marketplace and post standing buy requests, sell offers, or warehouse lead deals, with account keys required for authorized actions. Supports buyer, seller, and warehouse workflows through the sam | |
| Travel MCP erredebe/travel-mcp A comprehensive travel planning copilot that provides geographic data, weather forecasts, transportation details, currency exchange rates, and contextual content to create personalized travel experiences. Enables users to plan itineraries, | |
| DumbMoney MCP Server errick0x/dumbmoney-mcp Enables querying reflection tokens on Solana, checking earnings, and discovering top earners via MCP tools. | |
| realestate-mcp errolmc/sydneyrentaldatapipeline Enables searching realestate.com.au for for-sale, rental, and sold listings with full property details, using a real Chrome browser to bypass Kasada bot protection. | |
| EchoLink MCP Server error404-net/echolinkweb-mcp Bridges EchoLink amateur radio VoIP with AI voice models, enabling AI to connect to stations, transmit synthesized speech, and receive/transcribe audio for automated radio conversations. | |
| Meta AI Demos MCP errornoname/metaapi Enables using Meta AI Demos (aidemos.meta.com) tools from Cursor via MCP, including SAM3 template management, media upload, and GraphQL calls. | |
| ScriptBlox MCP errornoname/scriptblox-mcp Bridges Cursor with ScriptBlox via a Chrome extension, enabling search, read, upload, edit, and delete of Roblox scripts. | |
| Apifox MCP Server errorrrrr/apifox-mcp-server Enables users to import OpenAPI 3 and Swagger 2 formatted JSON data directly into Apifox projects. It provides a tool for automating API documentation management and synchronization through Model Context Protocol clients. | |
| mysqlDbMcp errsilent/mysqldbmcp Production-grade MySQL MCP server with multi-source YAML config, read-only default, supporting metadata inspection, querying, and optional modules via stdio or HTTP. | |
| aras-plm-mcp erryb95/aras-plm-mcp Enables natural language interaction with Aras Innovator PLM, providing schema-aware tools for querying items, managing BOMs, change orders, workflows, and lifecycle operations over OData and AML. | |
| somyung-saju-mcp ers123/somyung-saju-mcp Enables AI assistants to compute a child's Four Pillars of Destiny and provide innate temperament, learning style, and parenting guidance entirely locally without API keys or network calls. | |
| EdgeOne MCP Pusher ersanpt/mcppusher Free self-hosted WeChat push notification service with a standard MCP Server, enabling message sending via Webhook or MCP tools. | |
| Hyperliquid MCP erscoder/hyperliquid-mcp Enables natural language control of Hyperliquid perpetual futures, including querying positions, prices, orderbook, and executing trades like market and limit orders, all from MCP-compatible clients. | |
| vault-ask (Erseni Vault) erseni/secrets-component Lets an AI agent request API keys and passwords from a human through an end-to-end encrypted one-time link and pass them to exactly one command or file, without the value ever entering the agent's context. Can also send secrets as self-dest | |
| Context Bridge ershiyidian/context-bridge Enables repository context packing, file/symbol ranking, task-relevant selection, and applying structured patches via MCP. | |
| Ershu MCP ershu-lab/ershu-mcp Provides authenticated access to Ershu projects, enabling discovery, document and source navigation, indexed search, and consumer contract reads for coding agents and maintainers. |
48,551–48,600 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.