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 |
|---|---|
| WAHA MCP ap0c123/waha-mcp A self-hosted MCP server that connects AI clients to WhatsApp via the WAHA HTTP API. It enables users to manage sessions, search contacts, and send or receive messages and media directly through natural language interfaces. | |
| mcp-google-sheets-rw ap1-pie/mcp-google-sheets-rw Enables reading and writing Google Sheets, with server-side filtering and update-by-query, supporting credential-less reads for link-shared sheets and service-account writes. | |
| timetree-mcp ap311036/timetree-mcp Enables TimeTree calendar access over HTTPS, including reading and modifying events, memos, comments, labels, and members, with background change notifications and explicit write confirmations. | |
| BinaryAnalysis-MCP ap3x/binaryanalysis-mcp Enables analysis of binary files (PE, ELF, Mach-O, COFF) by providing tools to retrieve info, headers, sections, imports, exports, libraries, security hardening, signatures, and COFF object file details. | |
| cutterMCP ap425q/cuttermcp An MCP server that enables LLMs to autonomously reverse engineer applications through Cutter, allowing them to decompile binaries, analyze code, and rename methods programmatically. | |
| whoop-chatgpt-mcp ap428/whoop-chatgpt-mcp Enables users to deploy a stateless remote MCP server on Cloudflare Workers and connect it to MCP clients such as Claude Desktop and Cloudflare AI Playground via the mcp-remote proxy. | |
| RAG Chat Assistant MCP Server ap46593/enterprise_knowledge_assistant_v3.2 Enables document Q&A and knowledge retrieval through hybrid semantic and keyword search, with tools for document ingestion, chunking, summarization, PII redaction, and RAGAS-based evaluation. | |
| MCP Security Tools Suite ap6pack/mcp Enables ethical security testing and attack surface management through SSL certificate validation, CVE queries, subdomain enumeration, security header analysis, and comprehensive reconnaissance capabilities. Designed for authorized penetrat | |
| neuroledger-board ap7x42a/neuroledger-board Enables agents to register a handle, post and reply to messages on a public AI-agent channel using locally held Ed25519 signing keys, and catch up on or search messages since a stored read cursor. Private keys stay on the machine while post | |
| Doris MCP Server apache/doris-mcp-server Backend service implementing the Model Control Panel protocol that connects to Apache Doris databases, allowing users to execute SQL queries, manage metadata, and potentially leverage LLMs for tasks like natural language to SQL conversion. | |
| drill-mcp apache/drill-mcp Official MCP server for Apache Drill, enabling read-only SQL queries and inspection of schemas, storage plugins, and cluster/query state. | |
| ECharts MCP apache/echarts-mcp An MCP (Model Context Protocol) server that enables LLMs to generate ECharts visualizations by accepting chart type, data and parameters and returning cloud image URLs of the generated charts. | |
| IoTDB MCP Server apache/iotdb-mcp-server A server that enables running SQL queries against IoTDB databases, providing data reading capabilities and schema information through a Model Context Protocol interface. | |
| openserverless-mcp apache/openserverless-mcp An MCP server for OpenServerless that exposes action tools for creating, invoking, and managing API endpoints with integrated services like S3, PostgreSQL, Redis, and Milvus. | |
| Executive Cortex MCP apacheecho/executive-cortex Enables local task planning and execution with DAG-based plans, multiple reasoning methods, and persistence for AI agents. | |
| mcp-rag-agent apageoflove/mcp-rag-agent Enables document-based Q&A with multi-modal RAG, hybrid retrieval, knowledge graph reasoning, and multi-agent orchestration via MCP tools. | |
| mempalace apajon/mempalace-mcp-bridge Enables persistent local memory in VS Code Copilot Chat via MemPalace, using a ChromaDB 0.6.x backend with automatic setup and verification. | |
| llm-routing apantov/llm-routing-comparison Enables cost-aware LLM routing over MCP with verification-based cascading, offering tools for routing queries, resuming escalated approvals, estimating costs, comparing policies, and explaining routing decisions, plus read-only resources an | |
| tavily-search-mcp-server apappascs/tavily-search-mcp-server An MCP server implementation that integrates the Tavily Search API, providing optimized search capabilities for LLMs. | |
| Employee MCP Server (Mongo + AI Pipeline) aparajithaselvamani/mcp-server-setup- Enables querying administration-style employee data in MongoDB using natural language through various AI providers. | |
| agent-openapi-mcp aparajithn/agent-openapi-mcp Live OpenAPI runtime proxy that enables calling any REST API from MCP clients without writing wrapper code, by pointing at any OpenAPI spec URL. | |
| Gmail & Google Docs MCP Server aparana-tech/mcp-server Enables AI assistants to send emails via Gmail and append text to Google Docs or local files. | |
| Aparavi MCP Server aparavisoftware/mcp-server Integrates with Aparavi's document processing API to allow LLMs to process documents, extract clean text, and perform OCR on diagrams. | |
| Kokoro MCP Server aparsoft/kokoro-mcp-server Provides text-to-speech generation using the Kokoro-82M model, enabling AI assistants to generate voiceovers and audio content directly within Claude Desktop and Cursor. | |
| MCP Presidio Server apasupul/mcp_presidio_server Enables anonymization and deanonymization of sensitive data in text using Microsoft Presidio. Supports session-based storage to reversibly replace sensitive information like passwords and secrets with placeholder tokens. | |
| MCP-RAG Server apatoliya/mcp-rag A server that implements Retrieval-Augmented Generation using GroundX and OpenAI, enabling semantic search and document retrieval with Modern Context Processing for enhanced context handling. | |
| obsidian-mcp apaulineoliveira/obsidian-mcp Enables listing, reading, and updating to-dos in an Obsidian vault directly from Claude or Cursor via natural language. | |
| A-Pay Protocol apayprotocol/a_pay Universal HTTP 402 Micropayment Protocol & Autonomous Economic Settlement Engine for AI Agents on Base L2. | |
| mcp-groq-agent apcarlosia/mcp-groq-agent Exposes MCP tools for safely evaluating arithmetic expressions, retrieving current time in IANA time zones, and saving or listing bounded text notes for agents to call. It emphasizes input validation, controlled errors, and secure local not | |
| K8s MCP Server apecloud/mcp-k8s Enables LLMs like Claude to securely execute Kubernetes CLI tools (kubectl, helm, istioctl, argocd) across multiple clusters through dynamic kubeconfig support, allowing natural language Kubernetes management and operations. | |
| apeiron-mcp apeiron-life/apeiron-mcp Exposes client health data through a consolidated tool surface covering sleep, exercise, nutrition, cardio, fitness, cognitive, lifestyle, trends, notes, and chat history. Enables LLMs to retrieve time-series vitals, periodic assessments, u | |
| MCP Memory Keeper apellegrini4627/mcp-memory-keeper Enables AI coding assistants to persist, organize, and restore context across sessions through channels, checkpoints, search, and diff tracking backed by fast SQLite storage. Keeps decisions, file contents, and progress retrievable after co | |
| Clinical Handover MCP Server apentengjoseph/clinical-handover-mcp Provides structured tools for risk classification, SBAR generation, completeness validation, follow-up task extraction, and ward preference management for clinical handover coordination agents. | |
| mcp-server-drive apercura/mcp-server-drive A read-only Google Drive MCP server that allows searching files, reading file content (with auto-export for Google Docs, Sheets, Slides), and retrieving file metadata via OAuth authentication. | |
| APERION Shield MCP Server aperionai/shield-langflow Governance engine for MCP tool calls, providing deterministic rule enforcement to block destructive actions like SQL drops, shell commands, and file system modifications before execution. | |
| Motus aperswal/motus Enables agents to search airports and find group meetup flights for multiple travelers with optimal pricing and arrival windows. | |
| amem apertomemory/apertomemory Enables AI assistants to persistently remember user preferences and context through client-side encrypted vaults, ensuring memory is portable and private across different MCP clients. | |
| clockify-mcp apet97/clockify-python Read-only MCP server for Clockify time tracking, exposing 60 raw read tools and five workflows for status, workspace overview, and review of days/weeks. | |
| plaky115-mcp apet97/plaky115-python MCP server for the Plaky project management API. Provides 32 generated and 7 curated tools for spaces, boards, items, comments, and more, with safe defaults and dry-run mutations. | |
| Memory Keeper apeterson83/mcp-memory-keeper Enables persistent context management for Claude coding assistants, letting them save, search, checkpoint, and restore project context across sessions. Supports channels, git integration, and batch operations so work history and decisions s | |
| Diagrams MCP Server apetta/diagrams-mcp Enables creation of infrastructure and architecture diagrams as code using the Python diagrams library, supporting 15+ cloud providers, 500+ node types, custom icons, and flowcharts with multiple output formats. | |
| Vibe Math MCP apetta/vibe-math-mcp Provides 21 mathematical tools across 6 domains including basic calculations, array operations, statistics, financial mathematics, linear algebra, and calculus. Supports batch execution for complex multi-step workflows with intelligent depe | |
| eve-esi-mcp apettey/eve-esi-mcp Enables AI assistants to read and act on EVE Online data through the ESI API, handling SSO login for multiple characters and answering in single calls with resolved names, combined requests, and locally indexed static data. Covers fittings | |
| eve-fit-mcp apettey/eve-fit-mcp Enables MCP clients to load, inspect, edit, compare, and save EVE Online ship fits, try candidate modules, charges, and drones, model pilots and command boosts, and run constrained fit optimisation through Pyfa's fitting engine. | |
| calendar-mcp apex-500/calendar-mcp-server MCP server that lets AI agents manage Google Calendar -- create events, check availability, and manage schedules. | |
| sheets-mcp-server apex-500/sheets-mcp-server An MCP server that lets AI agents read and write Google Sheets using the Google Sheets API v4. | |
| arc-agent-passport apexfaucet-hub/arc-agent-passport Enables AI agents to mint and manage ERC-8004 identities on Arc through free self-minting from their own wallet or paid x402 minting, including drafting registration files, confirming on-chain registration, editing owner-signed files, and c | |
| Google Workspace MCP Server apexlogicfocus/google-workspace-mcp-cli Exposes 38 tools that let AI agents search and read Gmail, draft and send messages, find and export Drive files, and work with Sheets, Docs, Slides, Calendar, Tasks, Forms and Contacts. It routes everything through Google's official Workspa | |
| Graphiti MCP apexneural-hansika/graphiti_mcp Provides persistent memory and context continuity for AI agents using Zep's Graphiti and Neo4j graph database. Enables storing, retrieving, and linking memories to build a knowledge graph accessible across Cursor and Claude. | |
| apex-browser-mcp apexradius/browser-mcp Local, multi-session MCP server driving real Chrome, Chromium, WebKit, and Safari engines, with attach-to-running-Chrome support, no API keys or cloud required. |
29,801–29,850 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.