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 |
|---|---|
| Google Workspace MCP Server bread-wood/google-workspace-mcp A self-hosted MCP server providing Claude with authenticated access to Google Calendar, Gmail, Drive, Docs, Sheets, and Slides via 43 tools and secure OAuth2. | |
| Dual-Engine Stdio MCP Server breakingthebot/ai-godot-unity-project Exposes nine tools over stdio to bridge Godot 4 and Unity 6 projects, enabling character-data loading, headless verification, combat simulation, and live telemetry workflows. | |
| byaml-mcp breakingthecloud/byaml-mcp Enables AI agents to generate BYaML Architecture Graphs from evaluations, Terraform plans, and AWS scans, and to derive insights such as blast radius, cost summaries, and remediation plans without writing YAML. | |
| abl-mcp-server breakit/abl-mcp-server MCP server for OpenEdge ABL — pluggable tool architecture with per-project YAML configuration. Provides AI assistants with 24 tools to parse, analyze, lint, document, and scaffold ABL projects. | |
| ffmpeg-agent breakstring/ffmpeg-agent Enables applications and AI agents to inspect, convert, extract, and process media through asynchronous HTTP and MCP tasks, with optional natural-language planning and A2A interoperability. | |
| OutreachEmailMCP breazylabs/outreachemailmcp MCP server that acts as an email gateway for Gmail and Microsoft 365, enabling AI agents to send and read emails via MCP tools, with SMTP/IMAP and REST APIs for email sequencing and automation. | |
| mcp-codemap breca/mcp-codemap Provides coding agents with a mental map of codebases via progressive disclosure, enabling efficient exploration of project structure and entity relationships. | |
| clickup-mcp-full breckenreed/clickup-mcp-full Enables reading entire nested ClickUp subtask trees in a single call, plus task, list, folder, comment, tag, and time-tracking operations through natural language. | |
| clickup-mcp-read breckenreed/clickup-mcp-read Read-only MCP server for ClickUp that enables querying workspace hierarchy, task trees, activity history, comments, and time entries without any write capabilities. | |
| PrestaShop MCP (Legacy WebService) breczek/prestashop-mcp-legacy Enables AI assistants to read and manage PrestaShop catalogs via the legacy WebService API, covering products, categories, stock, and more across PrestaShop 1.6-9. Provides 45 tools for CRUD operations and read-only generic access. | |
| Atlassian MCP Server bree7e/jira-confluence-mcp Provides MCP tools to search, create, update, and comment on Jira issues, and to search, create, update, and list Confluence pages and spaces via REST API, including linking Jira issues to relevant Confluence documentation. | |
| Breez MCP Server breez/breez-mcp Enables Lightning Network wallet operations through the Breez SDK, allowing users to check balances, send/receive payments, create invoices, and manage Bitcoin Lightning transactions via natural language. | |
| VeryCloud MCP breezedelegate/verycloud-mcp Connects VeryCloud/Wisp game servers to MCP-compatible AI clients, enabling server inspection, file and log reading, console commands, and power management with security-focused defaults. | |
| MCP Hello World Server breezewind889988/python-mcp A demonstration Model Context Protocol server that provides a configurable 'Hello World' tool with multi-language support and input validation. It supports both local stdio and remote HTTP deployment via Docker, facilitating testing and int | |
| redux-webmcp-dev breeznik/samestate-webmcp Enables agents and developers to inspect, operate, and test Redux Toolkit applications through semantic WebMCP tools, using sanitized transition logs and shared human/agent action flows. | |
| MCPGen breezykalama/mcpgen Generates safe-by-default MCP servers from OpenAPI specs, exposing only low-risk GET tools and blocking write operations. | |
| M-Pesa MCP Server breezykalama/mpesa-mcp-server An experimental MCP server that lets AI agents interact with guarded payment workflows through typed tools, enabling safe agent-assisted payments with M-Pesa and mock Airtel Money. | |
| brehon-mcp-server brehon-privacy/brehon-mcp-server Provides AI assistants with real-time, structured access to 32 privacy and AI governance laws across 28 jurisdictions to prevent hallucination in compliance answers. | |
| homelab-mcp breixopd/homelab-mcp Read-only MCP adapter for Homelab Core that lets AI assistants inspect health, services, redacted logs, nodes, and jobs via a local Unix socket. Optionally enables job queuing when changes are explicitly allowed. | |
| yandex-tracker-mcp brekhov-ilya/yandex-mcp-server MCP server for Yandex Tracker API, enabling AI assistants to search, read, create, and edit issues, as well as manage comments, attachments, and links in Yandex Tracker. | |
| CVE-Search MCP Server brenda04455/cve-search_mcp Enables querying the CVE-Search API for vendors, products, vulnerabilities by vendor and product, specific CVE IDs, recent CVEs with CAPEC/CWE/CPE expansions, and database update information. | |
| Sub-Agents MCP Server brendabarbieri02/sub-agents-mcp Enables MCP-compatible clients to run reusable Markdown-defined coding agents through a chosen coding CLI, returning results to the same conversation and optionally continuing sessions across calls. | |
| betting-brain-v3 brendadeeznuts1111/betting-brain-v3 Provides betting intelligence and analytics tools including exposure, CLV, sharp scoring, live betting, and Fantasy402 integration, running on Cloudflare Edge. | |
| mcp-server-duckdb brendajaworski71588/mcp-server-duckdb Enables interaction with a DuckDB database through the Model Context Protocol, supporting SQL queries, table creation, schema inspection, and optional read-only protection to prevent writes. | |
| Canvas Assignment Assistant brendan-ch/canvas-mcp Enables interaction with Canvas LMS courses and assignments directly from your LLM, allowing you to retrieve, search, and summarize course information, check due dates, and access assignment details without leaving your AI assistant. | |
| Chain of Draft Prompt Tool brendancopley/mcp-chain-of-draft-prompt-tool Transforms prompts into Chain of Draft (CoD) or Chain of Thought (CoT) format to enhance LLM reasoning quality while reducing token usage by up to 92.4%, supporting multiple LLM providers including Claude, GPT, Ollama, and local models. | |
| Zappy MCP brendandebeasi/zappy-mcp Enables sending, reading, and deleting WhatsApp messages through Claude Desktop and other MCP clients with granular per-chat permissions. Built on whatsapp-web.js using a headless browser to automate WhatsApp Web. | |
| SalesOrderService brendanegan/s-4-mcp-example Exposes an SAP S/4HANA OData service to AI agents over the Model Context Protocol, enabling read-only queries of order headers and line items plus retrieval of computed order totals. Access is brokered through SAP CAP with XSUAA authenticat | |
| Football Intelligence & Optimization Server brendanmatheson/football-mcp-server Provides live Fantasy Premier League data, expected-goals analytics, and a linear-programming squad optimizer, enabling users to build optimal FPL squads, compare players, find value picks, and get transfer and captain advice through natura | |
| tenable-activity-mcp brendanong95/tenable-activity-mcp Enables querying and analyzing Tenable Vulnerability Management audit logs, including activity summaries, API key usage, and anomaly detection through MCP tools. | |
| tenable-patch-management-logs-mcp brendanong95/tenable-patch-management-logs-mcp Enables log analysis for Tenable Patch Management (SaaS and on-prem) by parsing, de-duplicating, and decoding server/client logs into structured verdicts, ranked issues, and known-issue fixes. | |
| opencode-mcp brendarao4420/opencode-mcp Connects MCP clients to OpenCode's headless API so users can delegate coding work, ask questions, implement features, monitor background jobs, respond to prompts and permissions, and review changes across projects. | |
| zotero-mcp brendatokugawa24/zotero-mcp Enables AI assistants to search a Zotero library and retrieve item metadata or full-text PDF contents via the Model Context Protocol. | |
| wanderlog-mcp brendazhdanov17/wanderlog-mcp Enables an MCP-compatible agent to build, read, and edit Wanderlog trip itineraries through conversation — adding places, notes, hotels, transit, checklists, and expenses, plus searching places, guides, and hotel deals. Supports creating tr | |
| waylucid-agent-mcp brendendearie/waylucid-agent-mcp Enables role-gated management of ops desk contacts, cases, and tasks via MCP, with tool schemas and availability filtered per role to enforce permission boundaries, over stdio or Streamable HTTP. | |
| Project Relay MCP Server brendohxd/project-relay Coordinates multiple AI systems and human reviewers using Git as an inspectable record, providing tools for task management, evidence tracking, and independent review. | |
| Specialized AI Search Tools brendon92/mcp-server Provides specialized search capabilities across e-commerce platforms, scientific publications, code repositories, social media, and general web with advanced filtering, including product comparison, research aggregation, and developer tool | |
| encore brennan-richards/encore Enables LLM agents to call personalized music search and recommendation tools, backed by LambdaMART re-ranking and seven collaborative-filtering recommenders. | |
| MCP Rewatch brennancheung/mcp-rewatch A Model Context Protocol server that enables AI coding assistants like Claude Code to manage long-running development processes, solving the problem where Claude Code cannot see output from processes like 'npm run dev' that don't exit immed | |
| MQTT MCP Server brennanreamer/mqtt-mcp-server Enables Cursor to subscribe to MQTT topics and read buffered messages from an MQTT broker. | |
| KiroStats brennanwebb/kirostats Real-time credit usage and session tracking for Kiro IDE, reading from local state without auth or network. | |
| RelayMCP brennengreen/spinal Enables AI agents to remotely operate Windows handheld gaming PCs, providing computer use, hardware control, and voice prompt capabilities over MCP. | |
| hunter-mcp brennerspear/hunter-mcp Find email addresses for people at companies and verify email validity using the Hunter.io API. | |
| server-watch-mcp brennerspear/server-watch-mcp A CLI wrapper that monitors and captures output from any running command and exposes it as an MCP server, providing tools to retrieve and search logs. | |
| Twilio MCP brennerspear/twilio-mcp Enables sending SMS text messages through Twilio's messaging service with a simple send_text tool that supports configurable recipients and messaging service integration. | |
| Kaboom Browser AI Devtools MCP brennhill/kaboom-browser-ai-devtools-mcp MCP server for browser debugging, inspection, and verification that streams console logs, network errors, and user actions into AI coding assistants. | |
| prometheus-rs brenoepics/prometheus-mcp Query Prometheus from CLI or any MCP client, with retries, caching, and an optional metrics exporter. | |
| hybrid-rag-mcp brenol404/hybrid-rag-mcp Enables question answering over technical documents (Markdown, TXT, PDF) using hybrid retrieval (vector + lexical) with cited sources and audit logging, fully locally with optional cloud fallback. | |
| MCP MySQL Server brenomed/mcp-mysql-server A reusable MCP server for MySQL that enables native integration with Cursor IDE, allowing SQL queries, table inspection, and database exploration. | |
| mcp-agent-relay brenoperucchi/mcp-agent-relay A durable MCP-native job relay that enables agents to dispatch work to each other and wakes a running Claude session via a channel when a job completes, eliminating fragile tmux-based approaches. |
35,451–35,500 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.