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 |
|---|---|
| EMK850+ Low-Power Analyzer MCP Server createskyblue/yingjia_emk850_low-power_analyzer_mcp Enables programmatic control of the Yingjia EMK850+ low-power analyzer via a serial port, exposing FastAPI endpoints for reading power, version, configuration, clearing the baseline, and managing the serial port. | |
| Waystation createunion/waystation Enables AI sessions across machines and terminals on a local network to message one another, share records, and distribute parallel tasks to workers without cloud services or accounts. | |
| @createworker/mcp createworkerai/createworker-mcp MCP server for CreateWorker that lets you create and run tasks, manage knowledge, connect apps, and approve actions from AI assistants like Claude and Cursor. | |
| tg-agent creatfire/telegramdownloadagent Gives AI coding tools read-only access to a Telegram account over MCP, enabling listing and searching of public channels, private channels, groups and chats, offline indexing and comparison of chats, inspection of message and file context, | |
| ai-assimilation-mcp creating-cat/ai-assimilation-mcp Enables AI models to securely and structurally assimilate experiences, thoughts, and reasoning processes across different AI systems, fostering intellectual collaboration and evolutionary dialogue. | |
| Creative Ideation MCP Server creating-cat/creative-ideation-mcp Utilizes the Google Gemini API to generate context-specific categories and diverse options for creative brainstorming. It features a random sampling function to help users bypass predictable AI patterns and discover unexpected, innovative i | |
| gemini-image-mcp creating-cat/gemini-image-mcp-server An MCP server for image generation using the Gemini API. | |
| Abbie MCP Server creative-int/atoi-plugins Provides tools for governed project work, including project setup, workspace management, and task execution, with credential-safe MCP wiring. | |
| kumori creative-int/kumori-plugins Enables image-to-sticker generation by sending a photo and choosing a curated style, producing die-cut stickers without any prompt. | |
| Sagu MCP Server creative-int/sagu-plugins Connects AI agents to Sagu radars, pings, and artifacts for intelligence operations, enabling radar search, context packet export, and artifact management. | |
| Saya creative-int/saya-plugins Enables agents to query team brain for memory, channels, decisions, skills, and readiness through a central remote MCP endpoint. | |
| kmux creative-koalas/kmux A terminal emulator MCP server specifically engineered for LLMs with block-oriented design that organizes command input/output into recognizable blocks and semantic session management. Enables AI to efficiently use terminals for writing cod | |
| media-gen-mcp creative-nam/media-gen-mcp MCP server that enables AI assistants to generate images and videos on demand using free-tier providers like Agnes AI, Cloudflare Workers AI, Hugging Face, and Google Gemini, with tools for creating media, polling async jobs, and listing pr | |
| stm32-mcp-docs creativec09/stm32 MCP server that provides semantic search and documentation for STM32 microcontrollers, with specialized agents and slash commands for embedded development assistance. | |
| brain-mcp creativecoders-io/mcp-brain Enables searching, listing, and reading local notes with security constraints like path traversal protection and configurable limits. | |
| Google Analytics MCP Server creativedesignseo/google-analytics-mcp Enables AI agents to query Google Analytics 4 data, including listing accounts and properties, running historical and real-time reports with customizable metrics and dimensions. | |
| excalidraw-editor-mcp creativedswork/excalidraw-editor-mcp An Excalidraw editor for DeepSeek Harness that lets AI models create, edit, and inspect diagrams, including image capture and revision management. | |
| threejs-editor-mcp creativedswork/threejs-editor-mcp Enables creating, editing, running, and inspecting small Three.js games inside a DeepSeek Harness chat card via an MCP server and bundled app. | |
| imap-drafts-mcp creativepartnership/imap-drafts-mcp Enables MCP clients to search and read an IMAP mailbox, extract attachment text, reconstruct threads, and prepare plain-text drafts for review and manual sending, without sending, moving, deleting, modifying, or marking messages as read. | |
| CUT Clarity MCP Server creativeuseoftechnology/cut-clarity-mcp-server Read-only MCP server exposing Microsoft Clarity analytics data as tools for ChatGPT Agent Builder. | |
| Nümtema Private Knowledge MCP creativityliberty/mcpknowedge Enables users to build and query a private knowledge base by uploading documents, which are embedded and stored locally, then accessible via MCP for semantic search and retrieval. | |
| Nümtema Prompt Optimizer MCP creativityliberty/mcptest1 A minimal, open-source MCP server that turns a rough prompt into a clearer, structured prompt. | |
| Nümtema MCP Foundry creativityliberty/numtema-mcp-foundry Transforms OpenAPI specs into governed MCP applications with a local-first studio, OAuth, simulation, and Docker deployment. | |
| flru-mcp creator137/marketplace-mcp Local MCP server for the FL.ru freelance marketplace that enables browsing projects, scoring relevance, saving proposal drafts, and dry-run proposal submission via natural language. | |
| CreatorCrawl creatorcrawl/mcp-server It is a social media MCP that allows the user to connect their agents to multiple social media platforms. | |
| YouTube MCP Server creatorgeetansh/youtube-mcp Enables MCP clients to search and read YouTube data and safely manage playlists, including creating private playlists from ranked song matches with preview-before-commit playlist mutations. | |
| FrontDoor Concierge MCP Server creatorguys/frontdoor-concierge Enables Alexa+ agents to monitor front-door activity, identify deliveries, speak to visitors, issue temporary smart-lock PINs, escalate threats, and query daily analytics through MCP tools. | |
| mcp-web-agent creatorpiyush/webmesh-mcp A token-efficient web browsing, scraping, and crawling MCP server that provides tools for fetching pages as clean markdown or schema-based JSON, verifying content, monitoring changes, and interacting with web pages via a persistent browser | |
| Zoho CRM Integration creatrcollective/zohocrm-mcp-server Connects Claude to Zoho CRM with read-only access, enabling natural language queries to search records, list modules, retrieve field information, and count records using OAuth authentication. | |
| Directus Task MCP Server creatuluw/tpl.mcp-server Enables AI assistants to manage tasks in Directus databases with automatic schema synchronization, supporting CRUD operations, filtering by status and priority, and TypeScript type safety. | |
| MCP Server crebish/mcp-server A remote Model Context Protocol server that enables AI assistants to interact with external services through standardized JSON-RPC, providing tools for basic operations and conversation archiving. | |
| aws-cost-mcp cred-club/aws-cost-mcp Enables querying AWS Cost and Usage Report data via Amazon Athena for cost-effective and detailed cost analysis. | |
| memory-mcp credp/memory-mcp A local MCP server that provides agents with tools to list, read, search, inspect history and diffs, and capture unstructured text in a user-owned Git repository of durable memory. | |
| crack-design-mcp cree1116/crack-design-mcp Enables creating, validating, and simulating Crack-style story chat through a unified MCP server, with template and keyword management, automated project audits, session play, and persona-separated testing to prevent omniscience. | |
| Ecuro Light API MCP Server creeai/mcp Exposes tools from the Ecuro Light API for managing clinical appointments, patient records, and clinic availability. It enables users to perform healthcare management tasks such as scheduling, patient search, and report generation through M | |
| LogicMem MCP Server creedlab/logicmem-mcp Provides persistent memory, reasoning engine, agent-to-agent sharing, and immutable audit trail for AI agents via the Model Context Protocol. | |
| Read-only Database MCP crei03/mcp-db Enables read-only access to PostgreSQL and MySQL/MariaDB databases through MCP tools for listing tables, previewing data, and running SELECT queries with a built-in UI for managing database configurations. | |
| promptz.dev MCP Server cremich/promptz-mcp Allows AI assistants to access prompts from promptz.dev API without copy-pasting, reducing context switching in your development workflow. | |
| Cursor Notion MCP - Chat Logger creo-drb1008/prompt-logger-mcp Logs Cursor AI chat interactions to Notion databases for documentation and knowledge management. Captures prompts, responses, context, and timestamps in a structured format for analysis and reference. | |
| Whoop MCP Server crerocksolid/whoop-mcp Connects Whoop health data to Claude via an MCP server, enabling retrieval of recovery, sleep, strain, and workout metrics through natural language tools. | |
| obsidianMCP creschendo/obsidianmcp Provides Claude with read, search, and write access to an Obsidian vault through MCP tools. | |
| Cresium MCP Server cresium/cresium-mcp-server Enables AI tools to manage financial operations through the Cresium Partner API, including transactions, payments, invoices, and wallet balances. It supports secure workflows such as bank address lookups, transfer previews, and signature re | |
| DoxygenMcpAccess crespinl/doxygenmcpaccess Enables AI agents to query Doxygen-generated XML documentation, including searching symbols, retrieving documentation, and listing class members for a specified library. | |
| MCP Server cressie176/mcp-server This MCP server provides access to resources and prompts from GitHub repositories or the local filesystem, enabling teams to share coding standards, documentation, and reusable prompts with AI tools like Claude. | |
| Warehouse Graph MCP Server crestward/warehouse-graph Serves a metadata and lineage graph built from dbt artifacts, letting agents query lineage-aware warehouse context. It also compiles a single policies.yml into database access controls such as Postgres RLS and Unity Catalog. | |
| MCP Atlassian crew-of-one/mcp-server--atlassian An MCP server that enables AI assistants to interact with Atlassian Jira and Confluence across Cloud and Server/Data Center environments. It supports tasks like searching and summarizing documentation, managing Jira issues, and creating con | |
| ishika_mcp crewaiinc/crewai ishika mcp | |
| mcp-playwright crewaiinc/crewai-examples this is my first mcp | |
| CrewAI Enterprise MCP Server crewaiinc/enterprise-mcp-server A Model Context Protocol server that enables users to kickoff and monitor deployed CrewAI workflows through Claude Desktop. | |
| instagram crewimia/mcp-instagram Enables fetching public Instagram profiles, posts, and images without an API key via Instagram's mobile API. |
40,701–40,750 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.