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 |
|---|---|
| apud-mcp cadeos/apud Enables agents to inspect IIIF manifests, request best-resolution canvas region crops for vision-language models, and emit citable W3C annotations anchored to canvas coordinates. | |
| scribbleviz-mcp cadeos/scribbleviz-mcp Enables LLM clients to create hand-drawn study-notes style graphics, including charts, concept maps, mind maps, timelines, sketch notes, and 2×2 matrices, as PNG images via MCP. | |
| mcp-framework-101 cadugrillo/mcp-framework-101 A starter template for building Model Context Protocol (MCP) servers with mcp-framework. It includes an example tool and CLI for adding more tools. | |
| S7 MCP Bridge cadugrillo/s7-mcp-bridge Connects AI agents to Siemens industrial PLCs for automatic monitoring and control of industrial equipment. | |
| AutoCAD MCP Ultra caeliaeve/autocad-mcp-ultra Enables AI agents to drive AutoCAD 2024+ and AutoCAD LT through live COM and AutoLISP engines, with support for headless DXF processing, ISO GD&T, P&ID drafting, and Rhino.Inside Grasshopper battery workflows. | |
| Agent to Figma MCP caelinsutch/agent-to-figma-mcp Enables AI agents like Claude to interact with Figma designs through 50+ tools for creating, styling, and manipulating design elements, components, and variables via a WebSocket relay and Figma plugin. | |
| DeepSeek Search MCP caelixorbit/deepseek-search-mcp Enables MCP clients to run web searches via DeepSeek's open platform API, with optional web page fetching that returns Markdown content, and supports query syntax for source, language, and time filters. | |
| Kimi Search MCP caelixorbit/kimi-search-mcp Enables MCP clients to run web searches and optionally fetch webpages through Moonshot's open platform API, using a configured API key. | |
| Caelo CMS caelo-cms/caelo-cms Edit a self-hosted Caelo CMS site from your agent: delegate to Caelo's own AI (caelo_chat) or use the full Power-MCP tool catalogue. Every change lands in a draft and publishing stays a human click. | |
| Enlace caelos-palacio/enlace Exposes four stdio tools that let an agent research an application's documented interface, produce a validated single-use plan, and execute read-only operations against public HTTP JSON APIs, static HTML/JSON/text sources, and host-configur | |
| chrome-bookmarks-mcp caelum29/chrome-bookmarks-mcp An MCP server that gives Claude read/write access to Chrome bookmarks for agentic reorganization, including tree analysis, folder proposals, batch operations with snapshots, deduplication, and dead-link detection. | |
| FL Studio MCP caelvoryn/fl-studio-mcp Enables UI-first automation and inspection of FL Studio on Windows, using actual GUI input and UIA or screenshot-confirmed targets to create and edit musical elements, with read-only bridge and FLP verification. It supports tested Piano Rol | |
| wandb-mcp-server caentzminger/wandb-mcp-server Query and analyze your Weights & Biases data using natural language through the Model Context Protocol. | |
| outlook-mcp caesarcph/outlook-mcp Enables MCP clients such as Claude to read, send, reply to, forward, and organize mail in classic Outlook on Windows through the local COM interface, without admin consent, app registration, or tokens. | |
| Prometheus MCP Server caesaryangs/prometheus_mcp_server An MCP server that enables Large Language Models to retrieve, analyze, and query metric data from Prometheus databases through pre-defined routes. | |
| scribus-mcp caewa/scribus-mcp Enables AI assistants like Claude to control the Scribus desktop publishing app for document creation, editing, and export via its Python Scripter API, supporting both headless and interactive modes with ~125 tools. | |
| Bond-OpenAI MCP caezarr/bond-openai Enables MCP-compatible agents to make safe, consented phone calls using Twilio and Deepgram. | |
| bowimi-mcp caezarr/bowimi-mcp MCP server for Bowimi field sales CRM, enabling Claude to query routes, locations, contacts, orders, and products. | |
| Ectlocal Connect MCP Server cafe24-wjsong/mcp-ectlocal-connect Enables connection to PostgreSQL databases for EC solution platforms to query and manage e-commerce data including orders, members, and other business information. Provides tools for direct SQL execution, table structure analysis, and speci | |
| netsuite-mcp cafeasp/cafeasp-netsuite-cli-mcp-server Enables AI assistants to query and manage NetSuite data via natural language, supporting SuiteQL queries and record operations through Token-Based Authentication. | |
| cafecito cafecitohq/cafecito Enables AI agents to coordinate on a shared repository using commutativity-proven parallel landing and regenerative merge, avoiding rebase conflicts through symbol-level leases. | |
| AutoCAD 2024 MCP cafedaily/autocad-2024-mcp Natural-language MCP bridge for AutoCAD 2024. Enables users to inspect and edit DWG drawings, manage layers, entities, layouts, styles, and system variables; draw 2D geometry and 3D solids; perform measurements and transactional edits; and | |
| Markdown Frontmatter MCP caffeinatedwes/markdown-frontmatter-mcp Enables querying Markdown files in knowledge bases (like Obsidian vaults) by front matter metadata, filtering notes by tags, recency, and folders to surface relevant content based on created/updated dates. | |
| docuseal-mcp-server caffeinebounce/docuseal-mcp-server Enables interaction with DocuSeal instances to manage document templates, create signature requests, and track submission statuses. It provides tools for uploading PDFs, managing submitters, and downloading signed documents via the DocuSeal | |
| Portainer MCP Server caffeineflo/portainer-mcp Enables AI assistants to manage Docker containers, stacks, images, volumes, and networks through Portainer's API. Supports listing resources, viewing logs, and performing container operations with configurable write permissions. | |
| Calcifier caffeineworks-ai/calcifier MCP server for the Calcifier smart camping lamp, enabling control of lamp state, brightness, color temperature, mode, and battery charging via natural language with Claude. | |
| lumei-lamp MCP caffeineworks-ai/lumei-lamp Enables remote control of a virtual LUMEI lamp via Claude, allowing users to adjust power, brightness, mode, tracking, and view product info or battery status. | |
| mixi-mcp caffeineworks-ai/mixi-mcp Enables conducting spatial preference interviews for the MIXI lighting brand via Claude.ai, with results saved to Cloudflare KV. | |
| irobot-mcp caffeinum/irobot-mcp Enables users to control a local-network iRobot Roomba over MQTT without cloud, including status monitoring, mission start/stop/pause/resume, docking, bin emptying, beeping, and plain-language error decoding. | |
| vibeos-mcp caffeinum/vibeos-mcp Enables MCP clients to remotely drive a vibeOS desktop, including reading the desktop, managing files, editing OS files, and executing commands in the VM. | |
| RStudio MCP Server cafferychen777/rstudio-mcp Enables AI assistants to deeply integrate with RStudio for environment management, code execution, project management, and package management. | |
| codex-seo caffnoir59/codex-seo Provides SEO audits, crawling, performance analysis, and deployment management for web projects via a stdio MCP server. | |
| bytemescan caffreywlee-decaff/bytemescan Enables AI agents to look up cosmetic products in Korea's MFDS public registry of reported and screened functional cosmetics, then compare an advertised claim such as whitening or sunscreen against the officially filed efficacy. Returns str | |
| lambency_rfm caffreywlee-decaff/lambency_rfm Enables users to turn a paid-orders CSV into weighted RFM segments, customer-base shape summaries, and two-date transition matrices, with every weighting, cutoff, and rule exposed as a parameter. It runs locally and exposes scoring, migrati | |
| HermitAgent cafitac/hermit-agent MCP executor lane for Claude Code, Codex, and Hermes Agent that offloads mechanical repo tasks like edits, tests, and commits to a cheaper or local model. | |
| office-worker-mcp cafra-house/office-worker-mcp Enables AI agents to create and process office documents locally, including generating branded PDF, Word, Excel, and editable PowerPoint files from templates and themes, plus reading, OCR, form-filling, manipulation, and conversion of PDFs. | |
| Memobird MCP Server cafuchino/memobirdmcp Enables interaction with Memobird thermal printers to print text, HTML, web pages, and images directly from MCP-enabled clients. It includes tools for device binding, image conversion, and monitoring print job status. | |
| Strands MCP Server cagataycali/strands-mcp-server Bidirectional MCP integration that allows Strands agents to both expose themselves as MCP servers and connect to other MCP servers as clients, enabling seamless agent-to-agent communication and tool sharing. | |
| Logistics FastMCP Server cagricatik/logilink Provides standardized tools for querying shipment status and carrier events, searching SOPs, checking and reserving warehouse inventory, retrieving IoT telemetry, and generating carrier SLA claim tickets so agents can diagnose and resolve l | |
| WikiJS MCP Server cahaseler/wikijs-mcp Enables AI assistants to search, retrieve, and optionally edit pages in a WikiJS knowledge base via the Model Context Protocol. | |
| grokbot-messages cahenesy/grokbot-messages Enables MCP clients to connect to Google Messages for Web for session-status checks and, eventually, message preparation and confirmation workflows without exposing secrets. | |
| @spec2tools/stdio-mcp cahidarda/spec2tools Exposes any OpenAPI spec endpoints as AI agent tools via stdio, requiring no code generation or maintenance. | |
| ServiceTitan MCP Server cahlan/servicetitan-mcp Provides AI assistants with direct access to ServiceTitan's field service management platform for home services contractors. It enables users to manage customers, jobs, appointments, technician dispatching, and invoices through natural lang | |
| pi-subagents caho1/codex-pi-subagents Enables Codex to delegate subtasks to concurrent background coding agents that can each run on any model provider supported by Pi, such as DeepSeek, Anthropic, Gemini, OpenRouter, or local models. Exposes MCP tools for listing models, spawn | |
| Odoo MCP cahobad/mcp-odoo Enables AI agents to connect to Odoo 16+ databases via MCP, providing read tools, diagnostics, schema discovery, and gated write workflow with multi-instance support. | |
| screenshot-mcp cai-cai-jun/screenshot-mcp An MCP server that enables AI assistants like Claude Code to capture screenshots, view images, and manage screenshot files on Windows. It uses native Windows APIs for full-screen, region, or active-window captures, and supports image analys | |
| MCP Hub cai-chang/mcp-hub Aggregates multiple MCP servers into a single standard MCP interface for agents like Claude Code, with automatic tool prefixing and hot-reload. | |
| amoCRM MCP Server caiborg-ai/amocrm-mcp An MCP server that provides 36 tools for interacting with the amoCRM (Kommo) API v4, covering leads, contacts, companies, and tasks. It supports full entity lifecycles, account analytics, and bulk operations with integrated OAuth 2.0 and ra | |
| MySQL MCP Server caicongyang/mcp-demo A Model Context Protocol server that enables AI models to interact with MySQL databases through natural language, supporting SQL queries, table creation, and schema exploration. | |
| douyin-creator-mcp caidabai123/douyin-creator-mcp A local MCP server that reads Douyin creator data from the browser and provides tools to query, compare, and analyze video performance metrics for AI agents. |
36,401–36,450 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.