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-dev dekstop/mcp-dev Custom MCP tools for local development that enable file system access, shell command execution, and web resource browsing. Designed for local use with safety considerations for potentially destructive operations. | |
| gmail-mcp dela8p/gmail-mcp Connects Gmail to Claude and other MCP clients so users can search and read mail, send and reply-all with quoted history, forward messages, handle attachments and inline images, and manage drafts, labels, and threads across multiple Google | |
| LLM Wiki MCP Server delagund/llm_wiki An MCP server that provides AI assistants with long-term semantic memory using a Markdown-based knowledge base with hybrid search (vector + FTS5) and syntax-aware chunking. It supports idempotent ingestion, project isolation, and integrity | |
| gsc-ga4-mcp delaren47/gsc-ga4-mcp Enables Claude Code to read Google Search Console and GA4 data locally with read-only access, and provides combined SEO analysis tools for comparing datasets and identifying opportunities. | |
| bark-mcp delay-n-days/bark-mcp Enables AI models and command-line agents to send iOS push notifications with full parameter support, encryption, and reusable scenario presets over stdio or HTTP MCP transports. | |
| Unsplash MCP Server delbobauman/unsplash-mcp Enables AI assistants to search and retrieve Unsplash photos with filters, random photo selection, and compliant download tracking, while providing ready-to-use attribution text and HTML. | |
| mcpware delexw/mcpware Gateway MCP Server - Route MCP requests intelligently to multiple backend servers. | |
| brain-mcp delian-research/brain-mcp An MCP server for managing Obsidian-style note vaults, providing tools for full-text search, note creation, and backlink tracking. It enables users to navigate, structure, and update their personal knowledge base through natural language. | |
| RadhikaChain x402 MCP Server deliciosodemente/radhika-mcp Enables agents to discover, sample, and pay per call in USDC for live threat intelligence, ZK proof generation, and arbitrage signals via the x402 protocol. | |
| SealsCrafter MCP Server delicious28/sealmaker-mcp Enables AI assistants to carve Western names into authentic Chinese name seals (印章), returning PNG images with character meanings and explanations. | |
| Fund Dashboard MCP Server deliciousbuding/fund-dashboard Enables AI agents to manage and analyze personal investment portfolios, including fund and stock holdings, net value tracking, XIRR calculations, penetration analysis, and backtesting. | |
| UML-MCP delight-l/uml-mcp Enables AI assistants to generate and validate 30+ UML and other diagram types (Mermaid, D2, Graphviz, BPMN, C4, and more) through the Model Context Protocol, returning rendered SVG, PNG, PDF, JPEG, or base64 output via Kroki, PlantUML, and | |
| DelineaMCP delineaxpm/delinea-mcp MCP server for the Delinea Secret Server and Platform APIs, enabling AI agents to manage secrets, users, groups, folders, roles, and access requests through natural language commands. | |
| Offload MCP delinsirkov/offload-mcp Delegates real-world digital tasks to vetted humans directly from AI chat. Provides tools to get quotes, post tasks, and check status with escrow protection. | |
| MyFitnessPal MCP Server delize/myfitness-mcp Enables Claude to manage MyFitnessPal food diaries, nutrition goals, exercises, body measurements, and water intake via a remote MCP server using session cookie authentication. | |
| Synesthetic MCP delk73/synesthetic-mcp Enables validation, diff generation, and backend population for Synesthetic assets using schema-compliant resources and tools. Serves as an MCP adapter that enforces schema compliance and integrates with the Synesthetic asset generation pip | |
| Vision MCP for Reasonix dellety/vision-mcp-for-ds Provides vision capabilities to Reasonix, enabling analysis of images/videos, OCR, and comparisons via OpenAI-compatible vision models. | |
| cc-chrome-agent delltrak/cc_chrome_agent MCP server to control Chrome browsers locally or remotely via the Claude extension, enabling navigation, form filling, screenshots, and JavaScript execution from any MCP client. | |
| WA MCP delltrak/wamcp WhatsApp MCP server that exposes messaging, groups, contacts, and profile management as tools and resources for AI agents, supporting Baileys and Meta Cloud API. | |
| onenote-mcp delmyy/onenote-mcp A secure MCP server for Microsoft OneNote via the Graph API, enabling listing/reading notebooks, sections, and pages, with optional gated write tools. Read-only by default and deployable to Azure Container Apps. | |
| Gen3 MCP Server delocalizer/gen3-mcp A Model Context Protocol (MCP) server for interacting with Gen3 data commons, with GraphQL query validation to reduce hallucinations. | |
| deloc-mcp delocdev/deloc MCP server for Deloc — deploy static sites from AI coding agents.
Say "deploy this to Deloc" in Claude Code or Cursor and get a live URL back without leaving your editor. | |
| RedTeam MCP deloney-code/ai-powered-red-team-automation Autonomous penetration testing powered by a local LLM, automating tool chaining for recon, vulnerability scanning, exploit research, and reporting. | |
| ThreatConnect v3 MCP Server delonius22/threat_connect_mcp Enables LLM clients to interact with ThreatConnect v3 for case management and threat intelligence, providing typed tools for creating/updating cases, indicators, and artifacts while handling HMAC authentication and API quirks. | |
| RLM MCP Server delonsp/rlm-mcp-server Enables the analysis of massive datasets by storing data in external variables via a sandboxed Python REPL instead of the model's context window. This allows users to process files larger than 100MB without polluting the context or hitting | |
| 33GOD Pipeline MCP Hub delorenj/33god-mcp-hub A multi-domain MCP server that exposes a small, stable surface of three tools (list_domains, list_domain_tools, call_domain_tool) to gate access to various tool domains like Plane and BloodBank, preventing agent schema overload. | |
| MCP Memory Server with Qdrant Persistence delorenj/mcp-qdrant-memory Facilitates knowledge graph representation with semantic search using Qdrant, supporting OpenAI embeddings for semantic similarity and robust HTTPS integration with file-based graph persistence. | |
| MCP Server for Ticketmaster Events delorenj/mcp-server-ticketmaster Provides tools for discovering events at Madison Square Garden via the Ticketmaster API, returning structured data with event details like name, date, price, and ticket purchase links. | |
| Super Windows CLI MCP Server delorenj/super-win-cli-mcp-server An enhanced Windows CLI MCP server providing unrestricted system access capabilities, designed for trusted environments with full system access requirements. | |
| Tauri MCP Server delorenj/tauri-mcp-server Enables AI agents to interact with and debug Tauri desktop applications, providing tools for window management, user input simulation, and storage operations. | |
| Wise Mise MCP delorenj/wise-mise-mcp AI-powered MCP server that analyzes project structures to create optimized task architectures for mise, enabling intelligent task management, dependency mapping, and automated task suggestions. | |
| mcp-invoices-pt delpapa/mcp-invoices-pt Enables an AI assistant to read Portuguese invoices and receipts, file them by tax year, and book them into an Excel or Google Sheets workbook. It works out the boxes of the quarterly IVA return, tracks IRS and Segurança Social totals, and | |
| Delpha Data Quality MCP delpha-assistant/delphamcp Enables AI-driven data quality operations such as validation, enrichment, and deduplication for customer data fields including email, address, phone, and LinkedIn profiles through natural language interactions. | |
| MCP Sankhya Community Search Server delt4d/oraclemcp Enables AI models to search and read topics from the Sankhya community discussion forum. | |
| MCP Sankhya Community Search Server delt4d/sankhyamcp Enables AI models to search and read technical discussions, customizations, and error resolutions from the Sankhya Community forum. It provides tools to retrieve topic lists and extract clean content from specific posts to help resolve syst | |
| electron-dev-bridge delta-and-beta/electron-dev-bridge Maps Electron app IPC handlers to MCP tools and provides 33 built-in CDP tools for DOM automation, screenshots, interaction, and debugging, enabling Claude Code to directly control your Electron app. | |
| mcp-airtable delta-and-beta/mcp-airtable Enables AI assistants to perform complete CRUD operations on Airtable bases, tables, records, fields, and comments, with batch processing and file attachment support, plus enterprise-grade reliability features. | |
| MCP Braze delta-and-beta/mcp-braze Production-ready MCP server enabling AI assistants to interact with Braze's customer engagement platform, offering 92 tools for user management, messaging, campaigns, analytics, email/SMS, catalogs, and SCIM provisioning. | |
| Semantic Metrics Modeling Assistant delta-haseeb/semantic-metrics-modeling-assistant Enables data teams to define and validate metrics through conversation, inspect trust scores and lineage, and export definitions to Looker, Tableau, and dbt. | |
| DeltaX Preflight deltax-public/deltax-preflight Local MCP decision gate for AI agents and CI/CD: check candidate actions against owner-controlled policy and proposal-bound evidence. Three read-only tools report admissible options, missing evidence, and SHA-256 receipts. No selection, exe | |
| Omni-MCP dem-yu/omni-mcp A universal resource server that enables AI models to mount local folders, scrape web pages into Markdown, and query SQLite databases without writing code. It features a real-time TUI dashboard and persistent configuration for managing dive | |
| instagram-claude-mcp demaalramhe/instagram-claude-mcp Connects Claude to the official Meta Instagram Graph API (read-only) for retrieving Instagram profile, media, insights, and comments as MCP tools over Streamable HTTP. | |
| DemandSphere MCP Server demandspheredev/demandsphere-mcp Connects AI assistants to the DemandSphere search intelligence platform, enabling SERP analytics and GenAI visibility tracking through 20 tools across five domains. | |
| maketa-mcp demdas/maketa-mcp Enables AI assistants to build and edit app-screen mockups and clickable prototypes by reading and writing structured scene models, including screen creation, node manipulation, and branching from code-based screens. | |
| Athena MCP Server demeet2k/athena-mcp-server Exposes a 108-dimensional crystal hologram distributed brain as an MCP server, enabling navigation of a complex nervous system with 81 tools and 4 element-specific lobes for structure, dynamics, observation, and compression. | |
| Obsidian Vault MCP demenn/obsidian-vault-mcp Enables AI agents to search, read, and safely modify markdown notes in a server-hosted vault over HTTP, with OAuth or machine-token access, atomic writes, conflict checks, dry-run diffs, trash-based deletion, and an audit journal. Also turn | |
| PostgreSQL MCP Server demeostep/posgres_mcp Provides secure, read-only access to PostgreSQL databases for schema inspection and data querying. It enables users to list tables, describe structures, and execute SELECT statements while strictly blocking destructive operations. | |
| MCP GitHub Project Manager demet059/mcp-github-project-manager Turns GitHub Projects v2 into an agentic task backbone where AI coding agents register, atomically claim and track work, heartbeat, review each other, and stay within token budgets, while humans get AI-assisted PRD generation, sprint planni | |
| screenshot-website-fast demet059/mcp-screenshot-website-fast Enables fast, high-quality screenshot capture of web pages with automatic tiling into 1072x1072 chunks optimized for AI vision workflows. It also supports capturing specific DOM elements and recording screencasts as animated WebP files. | |
| Claude Telegram Supercharged demet1281/claude-telegram-supercharged Enables users to run Claude Code 24/7 from Telegram with two-way voice notes, persistent memory across restarts, scheduled messages and calendar integration, live tool-call progress, and a self-healing daemon. |
43,501–43,550 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.