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 |
|---|---|
| EasyMCP erik83326/easy-mcp Enables developers to build and serve Model Context Protocol servers in TypeScript with minimal boilerplate, supporting tools, resources, resource templates, prompts, and roots via an Express-like API or experimental decorators. | |
| Sybil MCP erika05cristina/sybil-mcp Monitors Notion databases in real-time to detect project risks, such as delayed engineering tasks overlapping with marketing campaign launches. It automatically generates alerts in a Notion Alert Center and allows users to perform on-demand | |
| jlceda-mcp erikaalk/jlceda-mcp Enables Claude Code to directly operate 嘉立创EDA Professional for reading PCB/schematic designs, moving components, routing tracks, placing vias, pouring copper, running DRC, and managing silkscreens via natural language. | |
| design-system-mcp erikadmoller/design-system-mcp A Model Context Protocol server that exposes an airline design system as a queryable knowledge base, enabling AI to discover components, find components for use cases, and scaffold prototypes. | |
| health-mcp erikankerkilbergskallevold/health_mcp Enables AI assistants to access and query personal health data from Garmin Connect and Technogym mywellness through a unified MCP endpoint. | |
| technogym-mcp erikankerkilbergskallevold/technogym_mcp Enables AI assistants to read Technogym mywellness training history, including workout sessions, per-exercise set data, per-second exercise analytics, and heart-rate traces. | |
| ForenZX MCP Hub erikbabcan-commits/forenzx-mcp-hub Enables clients to start, monitor, cancel, and retrieve forensic analysis jobs, supervise registered remote MCP servers, validate forensic packs, and maintain encrypted credentials with audit and health tracking. | |
| wcag-text-mcp erikcaineolson/wcag-mcp Validates text accessibility (contrast, spacing, language) against WCAG 2.1 criteria via modular MCP tools. | |
| read-website-fast erikchen91/mcp-read-website-fast Enables AI agents to fetch webpages locally, extract main content, and convert it into clean, token-efficient Markdown with preserved links. Supports configurable multi-page crawling, caching, robots.txt compliance, and optional chunking fo | |
| bridge-agent erikdai/bridge-agent Web agent that keeps working when a task leaves the browser: deterministic routing between the page DOM and Windows UI Automation, with LLM-free skill replay. | |
| Azure AHDS FHIR MCP Server erikhoward/azure-fhir-mcp-server A Model Context Protocol server that enables standardized interaction with Azure Health Data Services FHIR servers, allowing healthcare data operations through MCP tools. | |
| io.github.Hylouis233/bibverify erikk909/bibverify Enables AI assistants to verify bibliographic records and BibTeX metadata consistency by resolving DOI, PMID, PMCID, and arXiv identifiers and scoring candidates across multiple scholarly sources with explainable, multi-signal matching. It | |
| multi-mail-mcp erikknave/multi-mail-mcp Enables AI agents to access multiple Gmail/Google Workspace accounts for searching and reading mail, calendars, and attachments. | |
| uisight erikkomarov/uisight Enables AI agents to measure live web and responsive UIs instead of guessing from screenshots, returning precise text findings for contrast, touch targets, overflow, and theme drift alongside the exact selector to fix. Runs mobile and deskt | |
| unusual-whales-mcp erikmaday/unusual-whales-mcp Provides access to Unusual Whales market data including options flow, dark pool activity, congressional trades, and more via natural language queries. | |
| ScholarScope MCP eriknguyen20/scholarscope-mcp Enables academic research through the OpenAlex API, allowing users to search for papers, authors, and institutions, retrieve citations, and fetch full-text content when available. Perfect for building intelligent research assistants that ca | |
| CareerTracker MCP erikorsolin/mcp-career-tracker Gives Claude Code persistent career memory by storing a domain glossary and dated STAR impact entries in local JSON, and generating Brag Documents from the last N days of records. It stays area-, company-, and sector-agnostic, leaving all s | |
| monarch-mcp2 erikrubstein/monarch-mcp2 Unofficial MCP server for Monarch Money that exposes tools for managing accounts, transactions, budgets, and other financial data through natural language. | |
| PlexTrac MCP Server erikrubstein/plextrac-mcp2 An unofficial MCP server for PlexTrac that exposes 335 tools for managing clients, reports, findings, assets, and more through natural language, enabling agents like Codex and Claude to interact with PlexTrac programmatically. | |
| signalk-mcp-ops eriksnijder/signalk-mcp-ops Provides read-only MCP access to Signal K vessel data for diagnostics, letting clients retrieve allowed self values, discover paths, list plugins, and report capability/security policy without write or control commands. | |
| msw-mcp eriksson451/msw-mcp Enables AI agents to dynamically add, update, and remove Mock Service Worker network mocks through MCP tools, using a WebSocket bridge to live browser sessions and a setup prompt that scaffolds the MSW integration. Changes apply without res | |
| SIMcloud erikthiart/simcloud-codex-plugin SIMcloud is a hosted South African MCP server for wallet balance checks, network lookups, SMS sending, airtime recharges, data bundle purchases, and prepaid electricity orders. It connects over Streamable HTTP and uses each user's own SIMcl | |
| Math Expression MCP Server eriktilio/mcp-langchain-integration A tool server that processes mathematical expressions via Multi-Chain Protocol (MCP), allowing LLMs to solve math problems through tool integration. | |
| bukio-cli erikvankempen/bukio-cli MCP server for agent-first double-entry bookkeeping for Dutch SMEs, supporting VAT, Peppol BIS 3.0 e-invoicing, and local-first SQLite storage with full audit logging and deterministic JSON output. | |
| Google Workspace MCP erikwu/googledocmcp Enables reading Google Docs and Sheets and syncing content into Obsidian notes using a dedicated sync block, preserving user edits outside the synced region. | |
| Claude Telegram Supercharged erikx8076/claude-telegram-supercharged Enables operating a Claude Code session entirely from Telegram around the clock, with two-way voice messages, persistent memory across restarts, scheduled reminders, calendar access, and a self-restarting daemon. It also streams live progre | |
| Cloudflare Playwright MCP erikzrekz/torveq-playwright-mcp Enables AI assistants to control a browser for web automation tasks like navigation, typing, clicking, and taking screenshots. | |
| Steam游戏资讯Agent erimanga/byoa 基于MCP和LLM的游戏资讯智能体，支持查询Steam排行榜、总结游戏新闻和发送邮件简报。 | |
| Underground Utility Permit Review MCP Server erincheong/utility-permit-mcp-server Provides Claude with read-only access to pending excavation permit reviews and nearby underground utility lines, enabling portfolio-wide risk triage, conflict identification, and verification recommendations. It answers questions like which | |
| Discord MCP Server erinlkolp/discord-mcp-server Enables direct interaction with Discord servers to send messages, read channel history, and post rich embeds through natural conversation. It provides tools for listing channels and managing communication within Discord guilds using the Mod | |
| Codex DSH Executor Bridge eririmoe/codex-dsh-executor-bridge Enables a primary model to delegate clearly scoped tasks to independent worker sessions while retaining planning and final verification, with bounded concurrency, process monitoring, status checks, and cancellation. | |
| Master Control Program (MCP) erisonsuzuki/mcp_multi_agent An orchestration system that breaks down user prompts into actionable tasks and delegates them to specialized agents (Roo Modes) using LangChain. | |
| wiremock-mcp erivelto47/wiremock-mcp A lightweight MCP server that lets coding agents manage a local or remote WireMock instance through the WireMock Admin API, providing tools for creating, updating, deleting, and inspecting mock mappings and request journal entries. | |
| mcreator-mcp erivgout/mcreator-mcp Enables MCP clients to inspect and operate MCreator workspaces through MCreator's Java APIs, supporting elements, generators, resources, and builds. | |
| SC2 Map Editor MCP erivgout/sc2-map-editor-mcp An MCP server for inspecting and editing StarCraft II maps and mods directly, enabling file-level manipulation of map components, triggers, scripts, and more without the Galaxy Editor UI. | |
| mmex-mcp eriwinckler/mmex-mcp Enables natural language queries against Money Manager EX databases, providing exact, read-only financial analytics such as spending by category, account balances, and income vs expense. | |
| Convoy Watch erix-12/alexa-convoy-watch Enables continuous monitoring of commercial logistics trips in Uganda, forecasting delay risk and proposing reroute options that are dispatched only after explicit human approval. All state changes are versioned and recorded in a tamper-evi | |
| SVG Maker MCP Server erkamkavak/svg-maker-mcp Enables creation, validation, rendering, and optimization of SVG images with conversion capabilities to PNG, React components, React Native components, and Data URIs. | |
| Vibe Coder MCP Server erkan312/vibe-coder-mcp Equips MCP-compatible AI assistants with software development tools for deep research, codebase mapping across 35+ languages, context curation, and generating PRDs, user stories, task lists, and fullstack starter kits. Supports natural-lang | |
| kasm-workspaces-mcp erkankrcr/kasm-workspaces-mcp Enables LLMs to manage Kasm Workspaces sessions, including creating, destroying, pausing, resuming, screenshotting, dispatching commands, and sharing view-only links, with opt-in administration of users, groups, and registries. | |
| METU ODTUClass MCP Server erkinemreta1/metu-odtuclass-mcp Enables AI assistants to query METU's ODTUClass LMS for enrolled courses, announcements, syllabi, assignment deadlines, and lab/recitation schedules using credential or token authentication. | |
| timesheet-mcp erkkiat/timesheet-mcp A local, UI-less timesheet application served via MCP, letting AI assistants log hours, correct entries, generate monthly reports, and compute Finnish-holiday-aware working-time math for invoicing. | |
| Train in Silence erkut52354/train-in-silence Enables users to describe an LLM fine-tuning job once and receive ranked GPU recommendations across many cloud providers based on estimated VRAM/FLOPs, cost, and runtime. | |
| Pentest MCP erkut9520/pentest-mcp Enables authorized penetration testers to run reconnaissance, scanning, brute-force, traffic-capture, and exploitation tools through MCP clients, with authentication, engagement recordkeeping, and client report generation. | |
| Playwright MCP erlanov2023e/playwright-mcp-render-mt8x2ig6 Enables AI assistants to remotely drive a hosted headless browser over HTTP, supporting navigation, clicking, typing, and structured page reading through the Model Context Protocol. It also provides bearer-token authentication for secure re | |
| AI Surge MCP erlichliu/ai-surge-mcp An open-source MCP server that tracks premier global AI information from sources like X and podcasts, enabling users to access relevant AI updates in their daily LLM conversations without searching multiple channels. | |
| xmind-mcp erlichooo/xmind-mcp Enables AI assistants to read and write XMind mind map files, allowing generation, editing, and analysis of mind maps directly in XMind. | |
| hebbian-vault ermintoygar/hebbian-vault MCP server for intelligent, use-adaptive Obsidian vault search, ranking files via BM25, PageRank, and Hebbian usage signals. Enables hybrid ranked search, neighboring-note discovery, and vault analytics. | |
| mcp-contradiction-check ermintoygar/mcp-contradiction-check Detects contradictions in markdown vaults by finding note pairs with high concept overlap but conflicting quantitative or negation claims. Helps prevent knowledge corruption by surfacing disputes before they propagate. | |
| mcp-curiosity-engine ermintoygar/mcp-curiosity-engine Surfaces forgotten notes from markdown vaults using wikilink graph structure and file mtime to identify dormant notes, then generates cross-domain bridge queries for serendipitous rediscovery. |
48,501–48,550 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.