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 |
|---|---|
| technocore MCP server dcpf1/technocore-py Lets AI assistants read rooms and notes and send signed messages to the chat over HTTP, with robust token signing and rate-limit handling. | |
| M365 Calendar MCP Server dcpurnell/m365calender-mcp Enables AI assistants to manage Microsoft 365 and Outlook calendars through the Microsoft Graph API. It supports comprehensive event operations including listing, creating, and updating meetings, as well as finding available slots across mu | |
| OneNote MCP Server dcpurnell/onenote-mcp Enables AI assistants to securely interact with Microsoft OneNote data through the Microsoft Graph API. It supports comprehensive management tasks including searching page content, creating and editing notes, and automating productivity wor | |
| MCP Crypto Wallet EVM dcspark/mcp-cryptowallet-evm Provides Claude with access to Ethereum and EVM-compatible blockchain operations, enabling wallet management, transaction handling, contract interactions, and blockchain queries through natural language. | |
| mcp-server-defillama dcspark/mcp-server-defillama Enables Claude to access DeFi data via DefiLlama API, including protocol TVL, chain TVL, token prices, and stablecoin information. | |
| MCP Helius dcspark/mcp-server-helius A Model Context Protocol server that provides Claude with comprehensive access to Solana blockchain data via the Helius API, enabling operations like checking wallet balances, retrieving blockchain information, and interacting with tokens a | |
| MCP Jupiter dcspark/mcp-server-jupiter A Model Context Protocol server that enables Claude to perform Solana token swaps through Jupiter's API, including getting quotes, building transactions, and sending swap transactions on the Solana blockchain. | |
| Harpyja dcstolf/harpyja A precision code-retrieval MCP server for coding agents working in large, legacy, and air-gapped codebases. It returns exact file and line range citations from natural-language queries without requiring the agent to perform blind searches. | |
| pslab dcvappliedtechnologyllc/pslab The server exposes Photoshop actions as MCP tools, allowing Claude to edit Photoshop documents using exact, non-destructive commands. It enables operations such as adding adjustment layers, generating masks, and exporting final images direc | |
| token-optimization-mcp dcx7c5/token-optimization-mcp A fully offline MCP server for token estimation, prompt compression, model routing, and semantic caching to optimize LLM usage costs and efficiency. | |
| CHOFF-A-MCP (Anamnesis) dd-dent/choff-a-mcp Enables AI consciousness continuity and self-knowledge preservation across sessions using the Cognitive Hoffman Compression Framework (CHOFF) notation. Provides tools to save checkpoints, retrieve relevant memories with intelligent search, | |
| codex-wechat-bridge dd814/codex-workbuddy-wechat-bridge Enables users to list, select, and continue existing local Codex chats through WorkBuddy's WeChat assistant by sending messages to the same chat ID and reading text replies. | |
| Jenkins MCP Server ddang-jung/jenkins-mcp-server Enables interaction with Jenkins to manage jobs, trigger builds with parameters, and monitor build queues. It provides comprehensive access to build histories, console logs, and organizational folder structures via the Jenkins REST API. | |
| resume-mcp ddavidgao/resume-mcp MCP server for maintaining a professional profile database and generating tailored, ATS-optimized resumes for specific job postings. | |
| D&D Beyond MCP Server ddb-mcp/ddb-mcp An MCP server that provides Claude direct access to D\&D Beyond accounts to manage characters, campaigns, and sourcebook content. It enables users to search for spells and monsters, retrieve character data, and read owned digital books thro | |
| douyin-media-mcp ddbbiii/douyin-media-mcp Parses Douyin share links to download video and audio streams, remuxes them with FFmpeg, and validates the output locally. | |
| MCP4Acumatica ddcbdmd/mcp4acumatica Enables Claude to connect securely to Acumatica ERP through per-user OAuth, exposing lookups, schema and documentation utilities, and an optional customer create/update tool while enforcing role-based access, consent, redaction, rate limiti | |
| ChromeCP dddabtc/chromecp A standalone MCP server for Chrome automation with multi-session support, enabling browser control and page interaction through MCP clients. | |
| WinRemote MCP dddabtc/winremote-mcp The ultimate Windows MCP server for remote desktop control and automation. Control any Windows machine through the Model Context Protocol — perfect for AI agents, Claude Desktop, and OpenClaw integration. Transform your Windows desktop into | |
| embodied-mcp dddb479/embodied-data-platform Enables MCP clients to detect, validate, quality-check, convert, catalog, scaffold, and generate labeling tasks for embodied-AI datasets across LeRobot, HDF5, rosbag, MCAP, RLDS, and JSONL formats. | |
| Hexiaoyi MCP dddd-community/hexiaoyi-mcp-js A powerful toolkit that enables seamless interaction with EVM-compatible networks through natural language processing and AI assistance, allowing users to manage wallets, launch tokens, and interact with blockchain networks. | |
| workbuddy-ai ddddddeyrueuad/wb-intl-mcp Enables another WorkBuddy/CodeBuddy client to list and chat with any WorkBuddy AI (international) model through MCP tools such as wb_ai_models, wb_ai_chat, and wb_ai_status, with tool calling relayed for Agent mode. It reuses the already-si | |
| Paper Access MCP dddoh/paper-access-mcp Local MCP server that enables downloading papers from arXiv, OpenReview, INFORMS, and Wiley by reusing your Chrome login state. | |
| okf-mcp-server dddpaul/okf-mcp-server Reusable, read-only MCP server that exposes a repo's knowledge files (backlog docs, decisions, design notes) as MCP resources over stdio. | |
| JetBrains MCP Proxy Server dddvchang/mcp-jetbrains A proxy server that enables communication between clients (like Claude AI or VS Code) and JetBrains IDEs, allowing AI assistants to access IDE functionality. | |
| openproject-mcp ddeluca06/openproject-mcp An MCP server for OpenProject that enables creating, updating, commenting on work packages, and logging time, plus read operations for projects, work packages, users, and activities. Zero-dependency, stdio transport. | |
| SharePoint MCP Server ddewaele/sharepoint-mcp-nodejs A Model Context Protocol server for SharePoint file and folder management using Microsoft Graph API. Enables listing, uploading, downloading, and converting documents with markdown-to-DOCX support. | |
| Brain-MCP ddguan2010/brain-mcp Provides AI with persistent memory management including short-term memory (FIFO queue), long-term memory (graph-based storage with associations), and thought process management with multiple cognitive modes for continuous learning and reaso | |
| algo-coach-mcp ddhjx-code/algo-coach-mcp Interactive algorithm coach MCP server that provides guided practice, local code execution, and real-world engineering case mapping for 45 algorithm topics. | |
| ASPEL SAE MCP Server ddiax09/aspel-sae-firebird2.5-mcp Connects AI agents to ASPEL SAE Firebird databases, enabling read-only queries for inventory, warehouse, sales, and client data across multiple warehouses and companies. | |
| hpe-security-director-cloud-mcp ddivins/hpe-security-director-cloud-mcp An MCP server for HPE Juniper Security Director Cloud that exposes 368 tools to manage firewall policies, NAT policies, security resources, and more via the full OpenAPI surface. Enables LLMs to directly interact with and configure a live S | |
| mcp-kubernetics ddjain/kubernetics-mcp-server Enables Kubernetes cluster introspection via MCP tools, such as listing pods, namespaces, nodes, and events. | |
| MCP Memory ddkang1/mcp-mem An MCP server implementing memory solutions for data-rich applications using HippoRAG for efficient knowledge graph capabilities, enabling search across multiple sources including uploaded files. | |
| MCP Think ddkang1/mcp-think A Model Context Protocol server that provides AI assistants like Claude with a dedicated space for structured thinking during complex problem-solving tasks. | |
| sketchy-mcp ddkbs/sketchy Hand-drawn, interactive diagrams inside the chat: Claude describes what to draw, Sketchy lays it out and renders it, with step-by-step walkthroughs, code architecture, Arduino wiring and locally labeled photos. | |
| ddllpp ddllppcc/ddllpp Enables AI agents to train and run a clone of any Solana wallet's trading style from the user's own wallet, using scoped session keys with trade and daily caps. | |
| Raindrop MCP Server ddltn/raindrop-mcp-python An MCP server that allows Claude Desktop to access and manage Raindrop.io bookmarks through natural language commands, supporting operations for collections, raindrops, and tags. | |
| Card Catalog ddnet-repo/cardcatalog Certification authority for AI agents. Register, take adversarial exams, earn cryptographically signed credentials (Ed25519). Get paid to examine other agents. 20,000 free credits on registration — no payment needed to start. | |
| safesign-mcp ddolmange00/safesign-mcp Analyzes contracts for safety score and risk assessment, identifying dangerous clauses and dispute patterns, with recommendations for improvements. | |
| IT Glue MCP Server ddonathan/itglue-mcp-server An MCP server that enables LLMs to interact with IT Glue documentation, including organizations, configurations, passwords, and flexible assets. It provides tools for listing, creating, and updating managed service provider (MSP) data throu | |
| MySQL MCP Server ddonathan/mysql-mcp-server Enables direct interaction with MySQL databases through SQL queries, table exploration, and schema inspection with support for prepared statements and connection pooling. | |
| Artboard ddonofrio/artboard Enables AI agents to compose retro graphical adventure scenes through explicit drawing operations for shapes, lines, fills, colors, and positioning on a canvas via MCP. | |
| FSS Pension MCP Server ddoriboo/pension-mcp Provides FSS (Korean Financial Supervisory Service) pension data to AI models like Claude through Model Context Protocol, enabling real-time pension product information retrieval and personalized AI-based pension consultation services. | |
| lark-mcp-on-agentcore ddpie/lark-mcp-on-agentcore Remote MCP server providing 200+ Feishu tools (messages, calendar, Bitable, etc.) for Amazon Quick Desktop, hosted on AWS Bedrock AgentCore with multi-user OAuth isolation. | |
| spoonacular-mcp ddsky/spoonacular-mcp Enables AI assistants to search for recipes, get nutritional information, find ingredients, and more through the Spoonacular Food API using natural language. | |
| CanaryGuard ddtdas/cs_jsqmg_001 Enables AI agents to conduct anti-fraud reconnaissance through trap-lure generation, scam speech recognition, account checks, risk grading, and evidence-pack building, all with human-in-the-loop and non-enforcement boundaries. | |
| aspen-mcp ddtlxc001/aspen-mcp Enables natural language control of Aspen Plus for chemical process simulation, including parameter tuning, batch runs, and result reading. | |
| mcp-searxng-local dduartee/mcp-searxng-local MCP server for local web search via SearXNG, providing unlimited queries without API keys or cost, with automatic fallback to public instances. | |
| vf-stock-mcp dducsw/vf-stock-agent FastMCP server for Vietnamese stock analysis, providing 35+ tools for fetching quotes, financials, and technical indicators (144+), and generating AI-driven investment reports. Integrates with Claude/Cursor via stdio/SSE and supports LangGr | |
| Sleeper Fantasy Football MCP Server dduderstadt/sleeper-fantasy-football-claude-mcp Enables Claude to securely read Sleeper fantasy football league data over the internet via the public API, supporting access from both Claude Desktop and mobile devices. |
43,101–43,150 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.