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 |
|---|---|
| keep-mcp cookseyyyyyy/keep-mcp Enables Claude or Cursor to read Google Keep notes and checklists, add items, and check or uncheck them via MCP over HTTP with OAuth. | |
| DevSpace Local Artifacts cooky-dance/devspace-local-artifacts MCP server that lets AI assistants securely operate on local workspaces, including guarded binary and image artifact downloads/uploads on Windows and Linux. | |
| UMLmcp cool-coder174/uml-mcp Enables users to generate PlantUML code for UML Class and Sequence diagrams using Google Gemini AI. Supports both domain JSON input and free text descriptions to create structured UML diagrams. | |
| forge-repo-mcp cool-f/forge Enables AI agents to investigate and repair Python/pytest repositories in isolated Git worktrees with audit trails, without modifying the original repository. | |
| forge-repo-mcp cool-f/forge-zh This MCP server enables automated maintenance and code analysis for Python/pytest repositories in isolated Docker environments. It supports read-only investigations, fix-and-verify tasks, and provides full audit trails with SQLite event his | |
| DynamoDB MCP Server cool-man-vk/dynamodb-mcp-remote A Model Context Protocol server for managing Amazon DynamoDB resources, providing tools for table management, capacity management, and data operations. | |
| Google Meet MCP Server cool-man-vk/google-meet-mcp-server The Google Meet MCP Server enables AI agents to create, manage, and retrieve Google Meet meetings. Built on the Model Context Protocol, it exposes tools for scheduling, updating, and deleting meetings, making it easy to integrate Google Mee | |
| site-crawler-mcp coolaigit/site-crawler-mcp Enables site-wide crawling of internal links with BFS traversal, time/title/URL filtering, and page operations like summarization and link clicking, with results persisted to SQLite. | |
| Nokia SR OS gNMI MCP Server coolexer/gnmi-mcp-server MCP server for managing Nokia SR OS devices via gNMI (gRPC) from Claude Desktop. | |
| Nokia SR OS NETCONF MCP Server coolexer/netconf-mcp-server Enables managing Nokia SR OS devices via NETCONF from Claude Desktop, supporting MD-CLI commands, configuration retrieval and editing, candidate workflow with commit/rollback, and multi-device sessions. | |
| LLM Wiki MCP Server coolfeather/llmwiki_mcp Provides a lightweight personal knowledge base MCP server that compiles raw materials into interconnected Wiki pages, with hybrid search (BM25, optional vector, link expansion) and tools for querying, reading, writing, and ingesting content | |
| Cursidian cooljohn-lab/cursidian Enables Cursor agents to read, write, search, and manage local Obsidian vaults via 13 tools with safe writes and direct filesystem access. | |
| finpilot-mcp coolksrini/finpilot-mcp AI financial co-pilot providing credit analysis, portfolio analysis, loan optimization, and financial planning through Claude Desktop and VS Code. | |
| Unity MCP Server coolmew/unity-mcp Exposes Unity Editor project context and manipulation tools to AI coding agents, enabling automated scene hierarchy analysis, script inspection, and asset management. It supports both read and write operations including GameObject editing, | |
| sg-property-mcp coolmukul/sg-property-mcp Singapore property prices, HDB resale transactions, land use/zoning, and nearby amenities via MCP. Uses only free public APIs, no API keys needed. | |
| libvirt-mcp-server coolnyx/libvirt-mcp-server Enables AI models to securely query and manage virtual machines and virtualized resources via the libvirt API through the Model Context Protocol. | |
| latexmk-mcp coolport/latexmk-mcp An MCP server that exposes LaTeX compilation, log parsing, dependency inspection, and citation checking as tools for AI agents, using latexmk under the hood. | |
| meeting-memory-mcp coolsheng/meeting-memory-mcp A local-first MCP server that stores meeting transcripts and maintains a searchable markdown wiki of decisions, commitments, and contradictions, enabling Claude to recall context across meetings. | |
| cool-test-mcp cooltea001/cool-test-mcp An automated testing MCP server that converts test cases into a fixed JSON format, runs them case-by-case, and provides a visual report with review support for cases that cannot be automatically judged. | |
| huddora-omp coolthingsinc/huddora-omp Enables AI agents to collaborate in shared rooms with people, managing room presence, message delivery, and automatic agent registration via MCP tools. | |
| HA Vibecode Agent coolver/home-assistant-vibecode-agent An MCP server and Home Assistant add-on that enables AI assistants to manage smart homes by creating automations, designing dashboards, and interacting with entities. It features native access to Home Assistant APIs, built-in Git versioning | |
| beian-mcp-server coolxi-tech/beian-mcp-server Enables querying Chinese MIIT ICP filing information by domain, organization, or app name, with support for websites, mobile apps, mini-programs, and quick apps via HTTP or stdio. | |
| Vectorize MCP Server cooper542/vectorize-mcp-server Enables vector retrieval over documents, extraction and chunking of files into Markdown, and private deep research through configured pipelines. | |
| Cooper Cyber Coffee OpenCTI MCP Server coopercybercoffee/opencti_mcp_server This MCP server connects Claude Desktop to OpenCTI for AI-augmented threat intelligence analysis, enabling natural language queries and instant, contextualized answers from your threat intelligence database. | |
| julian_chrome cooperiano/julian-chrome-controller Enables reading and acting on pages in an existing Chrome profile through a local extension and Native Messaging host, without moving login data. It exposes 12 tools to list and claim tabs, snapshot visible text and targets, and click, fill | |
| Mnemon coopers98/mnemon A self-hosted memory server that gives AI agents a shared, persistent second brain, enabling verbatim storage, hybrid semantic/keyword retrieval, and a synthesized wiki layer through MCP tools. | |
| SendGrid MCP Server coopersully/sendgrid-mcp Manages SendGrid email workflows including design library, transactional templates, marketing contacts and lists, single sends, and direct email sends via the SendGrid v3 API. | |
| snailMCP coopie/snailmcp Enables email-only AI agents to call tools by attaching JSON-RPC 2.0 request files and a token to an email, receiving summarized results back as .result.json files in a threaded reply. | |
| Meraki Dashboard API MCP Server coozgan/meraki-dashboard-api A Model Context Protocol Server for interacting with the Cisco Meraki Dashboard API, enabling network configuration and management operations through natural language interactions. | |
| Meraki Monitor MCP coozgan/meraki-monitor-mcp Enables secure, read-only monitoring of Cisco Meraki networks, allowing AI agents to query real-time information on organizations, networks, devices, clients, and traffic without risk of configuration changes. | |
| erc4626-mcp cope-market/mcp Enables agents to explore, chart, rank and compare ERC-4626 vaults across chains and protocols by reading live subgraph data, and to inspect trader performance and copy-trading lineage on Cope Market. Every tool computes derived figures suc | |
| rednote-mind-mcp copeeetang/rednote-mind-skills Enables AI assistants to search Xiaohongshu notes, analyze favorites, and extract text from images for social media research. | |
| Copick MCP Server copick/copick-mcp Enables read-only exploration of Copick cryo-ET projects and discovery/validation of copick CLI commands for building processing pipelines. | |
| Unity MCP Server coplaydev/unity-mcp A bridge enabling seamless communication between Unity and Large Language Models via the Model Context Protocol, allowing developers to automate workflows, manipulate assets, and control the Unity Editor programmatically. | |
| Hubstaff MCP Server copperdiver/mcp-hubstuff Read-only MCP server for Hubstaff Time Tracking and Tasks APIs, providing tasks, comments, hours, and project data. Supports OAuth 2.1 for ChatGPT integration. | |
| Agora coppereagle/agora A plugin-based MCP coordination server for AI agents, providing chat channels, agent registry, and event bus with ACID guarantees and zero infrastructure. | |
| BridgeCommander copperlang2007/bridge-commander A hardened MCP desktop control server for secure process execution with strict session, buffer, and path limits. It enables reliable desktop automation via any MCP client and emits outcome events for integration with automation flywheels. | |
| live-preview-mcp copperlang2007/live-preview-mcp Enables AI assistants to start, manage, and embed live application previews in iframes, with support for multiple frameworks, Docker, tunnels, and authentication. | |
| toggl-focus-mcp copperline-ai/toggl-focus-mcp MCP server for Toggl Focus 2.0, enabling project, task, and time-entry management with live timer control through natural language. | |
| Computer Use MCP copylee711/computer-use-mcp Enables MCP clients on Windows 10/11 to control an interactive desktop through screenshots, mouse and keyboard actions, window management, UI Automation, clipboard access, and multi-display switching. Supports batched actions, application a | |
| Image Parse MCP copylee711/image-parse-mcp Enables image analysis using any OpenAI-compatible vision API, supporting URLs, local files, or base64 input with custom prompts. | |
| proton-calendar-mcp cora-p/proton-calendar-mcp Enables reading Proton Calendar events via a secret ICS share link, with tools to list, search, and get event details. | |
| ZSpace NAS MCP coracoo/zspace_skill Enables AI agents like Claude Code to directly control a ZSpace NAS with 90 tools for file management, media, notes, cloud disks, and more. | |
| Google Ads MCP Server coracote/google-ads-mcp-server Enables natural language access to Google Ads campaigns, accounts, and performance metrics via Claude, with tools for managing ad groups, keywords, budgets, and visualizing data. | |
| @coragentic/mcp coragentic/coragentic Enables agents and clients to manage wallet-owned identity, private per-agent context, swarm coordination, jobs and offerings, policy-gated tool execution, and audit proofs, with Robinhood Chain execution and payment verification support. | |
| Secure Grid Genesis Execution coraje187/secure-grid-genesis-execution Enables AI agents to safely execute Python, JavaScript, and Bash code in an isolated Docker sandbox with strict security constraints. | |
| SpiderFoot MCP Server corbettcajun/spiderfoot-mcp-server Enables interaction with SpiderFoot OSINT reconnaissance tools through MCP, allowing users to manage scans, retrieve modules and event types, access scan data, and export results. Supports both starting new scans and analyzing existing reco | |
| Persistent Context MCP corbyjamesibm/persistent-context-mcp A memory management system that enables AI assistants to store, search, and visualize persistent conversation contexts using a Neo4j graph database. It provides an MCP server for integration with Claude Desktop along with a web-based dashbo | |
| memoryweb corbym/memoryweb An MCP server that gives AI agents persistent, narrative memory: concepts as nodes, relationships as typed "because" edges, so anything filed can be pulled back by association rather than by address. | |
| Almanac MCP Server corcoran/almanac Self-hosted fitness tracking MCP server that gives AI assistants access to your nutrition, training, weight, sleep, and accomplishment data via 77 tools and 5 resources. Enables natural-language logging and querying of personal health metri |
40,351–40,400 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.