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 |
|---|---|
| aps-mcp-server-nodejs autodesk-platform-services/aps-mcp-server-nodejs Provides access to Autodesk Platform Services API, enabling interaction with ACC projects and issues through natural language. | |
| Enhanced Architecture MCP autoexecbatman/arch-mcp A collection of Model Context Protocol servers providing advanced capabilities for AI assistants including professional accuracy enforcement, tool safety protocols, user preference management, and intelligent context monitoring. | |
| todo2code autogrammar/todo2code MCP server that extracts and links code, tasks, documentation, and git history into a graph, then diagnoses discrepancies and generates reports. | |
| Minecraft World Agent autoinfinite/minecraft-world-agent Enables local authoring and testing of Minecraft Java adventure maps through validated MCP tools, including structure building, snapshot/restore, and automated QA. | |
| AutoLearn MCP Server autolearnai/mcp An MCP server that enables AI agents to dynamically create and reuse executable skills (Python functions) from natural language descriptions, with automatic skill crystallization and real-time MCP spec updates. | |
| AutoManus MCP Server automanus-io/mcp-server Enables creating and deploying AI sales agents to WhatsApp and Webchat from AI coding assistants like Claude and Cursor, with automatic website research and no-code setup. | |
| Code Sandbox MCP automata-labs-team/code-sandbox-mcp An MCP server to create secure code sandbox environment for executing code within Docker containers. | |
| Automat Workflows MCP Server automatai/robotic-workflows-mcp-server A remote MCP server that lets AI agents build, run, and manage Automat RPA workflows. | |
| Amazon Ads Simulator MCP automatasleuth/amazon-ads-simulator-mcp Enables read-only inspection of ad-bid recommendations, scenario analysis, and explanation of threshold decisions using synthetic fixtures, without requiring live ad accounts or credentials. | |
| olx-india-mcp automate-with-sanjay/olx_india_mcp_server Enables AI assistants to search and retrieve detailed classified listings, including specifications, images, and seller info, from OLX India. | |
| ebp-directory automated-intelligence/ebp-directory MCP server for querying a cross-referenced directory of evidence-based therapies and interventions, enabling search by query, tier, problem, population, modality, and registry. | |
| fwrule-mcp automateip/fwrule-mcp An MCP server that analyzes firewall rule overlap, duplication, shadowing, and conflicts across multi-vendor firewall policies. | |
| skills-mcp-server automateip/skills-mcp-server Serves SKILL.md-based skills as MCP resources and tools over streamable HTTP, enabling remote discovery and retrieval of skill files with full YAML frontmatter parsing. | |
| AutomateLab AI SEO Magic Button automatelab-tech/ai-seo-magic-button AutomateLab AI SEO Magic Button runs a whole-site AEO/GEO audit and generates a prioritized plan an agent can execute. It combines AI-SEO and Citation Intelligence and ships as a skill, plugin, and MCP server. Product and documentation: htt | |
| instagram-research automatescaleagency/instagram-research Enables local research of public Instagram Reels through a dashboard, CLI, and 22 MCP tools, with optional Codex or Claude Code analysis. | |
| ISE MCP Server automateyournetwork/ise_mcp A Model Context Protocol server that enables programmatic interaction with Cisco Identity Services Engine APIs through standardized, discoverable tools. | |
| Wikipedia MCP Server automateyournetwork/wikipedia_mcp Provides structured access to Wikipedia content including search, summaries, images, links, and more via MCP tools. | |
| adops-mcp automatiabcn/adops-mcp Cross-platform ad management MCP server for Google Ads and Meta
Ads. Campaign analytics, A/B testing with z-test, anomaly detection, and
budget reallocation. 15 tools, 60 tests. | |
| invoiceflow-mcp automatiabcn/invoiceflow-mcp AI-powered invoice automation. Create PDF invoices, predict
late payment risk 0-100, auto-send reminders, reconcile Stripe/PayPal
payments, track cash flow. 10 MCP tools, 4 resources. | |
| leadpipe-mcp automatiabcn/leadpipe-mcp AI-powered lead qualification engine. Ingest leads from any source,
auto-enrich with company data, score 0-100 using weighted AI rules, and export
to HubSpot, Pipedrive, Google Sheets, CSV, or JSON. 8 MCP tools + 3
resources. | |
| shopops-mcp automatiabcn/shopops-mcp AI e-commerce operations manager for MCP. Inventory
forecasting, pricing optimization, RFM customer segmentation, order anomaly
detection, and automated reports for Shopify and WooCommerce. | |
| AdCraft MCP Server automatikstudio/adcraft-mcp Enables AI-powered generation of platform-optimized ad copy for Facebook, Google Ads, and LinkedIn by wrapping the AdCraft API. It allows users to create tailored marketing content based on specific product descriptions, target audiences, a | |
| BrandSnap MCP automatikstudio/brandsnap-mcp An MCP server that generates comprehensive brand identity kits including color palettes, typography, brand voice, and logo concepts. It enables users to transform business values and descriptions into detailed branding and social media guid | |
| CopyForge MCP Server automatikstudio/copyforge-mcp An MCP server that generates conversion-optimized e-commerce product descriptions, bullet points, and SEO metadata using AI. It supports multiple platforms like Shopify and Amazon with customizable tones for various writing styles. | |
| HireScript MCP Server automatikstudio/hirescript-mcp Generates inclusive, bias-free job descriptions by leveraging Claude AI to detect and mitigate gendered, ageist, or ability-biased language. It provides structured feedback through inclusivity scoring and specific alternative suggestions fo | |
| LegalForge MCP Server automatikstudio/legalforge-mcp Enables the generation of professional, jurisdiction-specific legal documents like privacy policies, terms of service, and cookie policies. It allows users to produce structured HTML legal content by providing specific parties, terms, and s | |
| PitchDeck MCP Server automatikstudio/pitchdeck-mcp An MCP server that generates comprehensive AI-powered investor pitch decks for startups and businesses. It produces structured content for slides covering problem statements, market opportunities, and business models based on specific compa | |
| ProofBase MCP Server automatikstudio/proofbase-mcp An AI-powered server that generates realistic, customizable customer testimonials with specific tones, roles, and performance metrics. It enables users to create authentic social proof content through simple natural language prompts. | |
| ProposalPilot MCP Server automatikstudio/proposalpilot-mcp Generates professional, AI-powered freelance project proposals including executive summaries, scopes of work, and pricing structures. It leverages Claude to create tailored proposals based on specific project descriptions, budgets, and time | |
| RemixPost MCP Server automatikstudio/remixpost-mcp An MCP server that repurposes text or URL content into platform-optimized posts for Twitter, LinkedIn, Instagram, and newsletters using AI. It enables users to automatically transform articles and blog posts into engagement-ready social med | |
| ReviewReply MCP Server automatikstudio/reviewreply-mcp An MCP server that generates professional and context-aware responses to customer reviews using Claude AI. It supports multiple tones and business types to provide tailored feedback variations for both positive and negative reviews. | |
| SiteScore MCP Server automatikstudio/sitescore-mcp Provides comprehensive website auditing for SEO, performance, accessibility, and security using AI-powered analysis. It enables users to generate detailed audit reports and actionable improvement suggestions for any given URL. | |
| MCP-Wait automation-ai-labs/mcp-wait A simple MCP server that provides waiting functionality to pause until other tasks finish, with progress reporting and support for CLI or HTTP server with SSE. | |
| RTIdeas MCP API Server automationagent10-max/mcp1 Converts a local MCP server into a remote HTTP-accessible REST API server with MongoDB support for managing brainstorming sessions and ideas. Provides endpoints for listing sessions, searching ideas, analyzing connections, and generating st | |
| perplexity-user-mcp automations-project/vscode-perplexity-mcp Perplexity AI search, reasoning, research, and compute - MCP server, dashboard, and multi-IDE auto-config for VS Code. | |
| CAPforge automatizatodo/capforge MCP server that makes AI agents get SAP CAP/CDS right by providing curated knowledge and a feedback loop with real validation against cds compile. | |
| DataMaker MCP Server automators-com/datamaker-mcp Enables AI models to generate synthetic data, manage templates and connections, push data to destinations, and execute Python scripts using DataMaker's data generation platform. Automatically handles large datasets by storing them to S3 wit | |
| Lumen Resto MCP automattaia/mcp Enables restaurant reservation management and schedule checking through Supabase with multi-tenant support. Designed for WhatsApp and phone agents to verify opening hours, create reservations with automatic table assignment, and handle mult | |
| Gravatar MCP Server automattic/mcp-server-gravatar Provides official access to Gravatar profiles, avatars, and AI-inferred interests using email addresses or profile identifiers. This server enables the retrieval of comprehensive user data and customized avatar images with various size and | |
| WordPress MCP Server automattic/mcp-wordpress-remote Acts as a bridge between local MCP clients and WordPress websites, enabling communication with WordPress through simple REST API requests rather than keeping open connections. | |
| mcp-wpcom-remote automattic/mcp-wpcom-remote A Model Context Protocol (MCP) server for seamless WordPress.com integration, enabling AI assistants to connect to WordPress.com sites with OAuth authentication. | |
| WordPress MCP automattic/wordpress-mcp A WordPress plugin that implements the Model Context Protocol to enable AI models and applications to interact with WordPress sites in a structured and secure way. | |
| WordPress Reader for Claude Desktop automattic/wordpress-reader-mcp Connects your WordPress.com account to Claude Desktop, enabling you to read your feed, check notifications, manage tags and follows, and discover new blogs through natural conversation. | |
| WordPress Design System MCP Server automattic/wpds-mcp Provides AI assistants with access to WordPress Design System component information and design guidance. | |
| Linkd MCP Server automcp-app/linkd-mcp An unofficial Model Context Protocol server that enables programmatic access to LinkedIn data through tools like user search, company search, profile enrichment, and contact retrieval. | |
| automeli-docs-mcp automeli-services-organization/automeli-docs-mcp A read-only MCP server that exposes Automeli's public API documentation (v2 canonical, v1 frozen) to LLMs via fetch and cache over www.automeli.com artifacts. It enables listing, searching, and retrieving endpoints, OpenAPI specs, error exp | |
| Autonnel autonnel/autonnel MCP server built into Autonnel, an open-source funnel builder for e-commerce. Served over HTTP at /api/mcp on your own deploy with a scoped API key, it lets agents read and write funnels, pages, media and orders. | |
| how-to-test-an-mcp-server autonoma-tools/how-to-test-an-mcp-server A minimal MCP server with get_weather and create_ticket tools, used for testing MCP servers across protocol, unit, eval, transport, and auth layers. | |
| arc-baseline-kernel autonomic-resilience-collective/arc-baseline-kernel Peer-reviewed (ACM BCB 2026) within-subject physiological deviation scoring. Real-time IHB baseline queries with SHA-256 trust certificates and autonomous x402 USDC payments on Base L2. No population norms. No human required. | |
| paypreflight autonomosmakerastrahermes/paypreflight Enables AI agents to audit EU payment runs offline—validating IBANs, SEPA character sets, VAT numbers, and control sums—without uploading any data. |
31,801–31,850 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.