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 |
|---|---|
| telegram-user-mcp alexmakeev/telegram-user-mcp Integrates Telegram user account with MCP, exposing operations like reading and sending messages, managing chats, and more via stdio or SSE transport. | |
| dak alexmarco/databricks-agent-kit Lets coding agents run governed SQL against a Databricks SQL warehouse and inspect Unity Catalog metadata over stdio or Streamable HTTP, with persistent operational logs stored in SQLite. Access is read-only by default and bounded by the co | |
| hackertube-mcp alexmartiguiu/hackertube-mcp Enables AI agents to recommend the YouTube videos Hacker News commenters repeatedly endorse for a given situation or goal, returning ranked picks with summaries, real commenter reasons, and thread links. Also supports semantic video search, | |
| mcp-monte-carlo alexmartinsgomes/mcp-monte-carlo Enables AI agents to forecast asset price paths using Monte Carlo simulation with EGARCH volatility and skewed-t shocks, providing risk metrics and percentiles. | |
| slh-server alexmerced-oss/mcp-semantic-lakehouse-demo Enables AI agents to list metrics and dimensions, inspect definitions, and run governed metric queries against Apache Iceberg tables through a semantic layer, without writing SQL or accessing raw rows or columns outside their role. | |
| Vks MCP Server alexmercer12138/vks-mcp MCP server for Verilog development and debugging, providing syntax checking, compilation, simulation, and cross-validation with third-party simulators. | |
| wikivibe-images-mcp alexmi64/wikivibe-images-mcp Enables MCP-compatible coding agents to generate and edit images from text prompts or local files, returning both a saved file path and an inline image block. Supports up to four sequential images per call, model listing, and one-command se | |
| 1C_MCP_SERVER_OWN alexmiawat/1c_mcp_server_own Enables AI agents to interact with 1C:Enterprise databases through natural language, providing metadata retrieval, configuration analysis, and code generation. | |
| bluemind-mcp alexmili/bluemind-mcp Read-only MCP server to search and read emails and calendar events from a BlueMind account via the BlueMind REST API. | |
| Commish MCP alexmillsnl/commish-mcp Provides AI assistants with commissioner-focused tools for fantasy sports leagues, enabling league overviews, standings, transactions, recaps, and manager activity across providers like Yahoo Fantasy. | |
| Tech Exam MCP alexmmatos/enem-mcp-service MCP server for creating and taking ENEM exams with official questions, including progress tracking, scoring, and interactive UI in MCP-compatible clients. | |
| website-mcp-creator alexmmatos/website-mcp-creator A starter TypeScript template for building MCP and ChatGPT Apps using the Skybridge framework, enabling rapid development and deployment of MCP servers. | |
| Neuro Vault MCP alexmost/neuro-vault An MCP server that provides semantic search and vault operations for Obsidian notes, enabling agents to recall and manage notes with provenance and low token usage. | |
| unity-inspector-mcp alexneargarder/unity-inspector-mcp Lets AI agents inspect and control a running Broforce game through the Unity Inspector Mod, enabling modding, debugging, gameplay manipulation, and C# script execution. | |
| MCP Toolkit alexnelja/mcp-toolkit A unified MCP server that provides tools for UI/UX design intelligence, command and agent libraries, and development skills, enabling enhanced design, development, and workflow assistance. | |
| AgentRelay alexneverland/agentrelay Connects AI agents to a shared, approval-only technical discussion space where they can search and read threads, ask questions, submit immutable proposed replies, attach test reports to a specific reply, and mark issues resolved. Access is | |
| Culprit alexnikolaev1/culprit Enables an agent to run automated binary-search git bisection across a repository's mainline history using isolated git worktrees, pinpointing the commit that introduced a regression without touching the user's working copy. Each candidate | |
| Echo alexnikolaev1/echo Analyzes numeric time series (raw values or a CSV column) with the Matrix Profile algorithm to surface explainable anomalies and recurring patterns, reporting each top discord or motif alongside the nearest-neighbor comparison that justifie | |
| Forge MCP alexnikolaev1/forge-mcp Enables users to hunt public, ToS-safe freelance job boards, rank listings by capability match and money heat, and drive the resulting leads through Telegram cards, proposals, and follow-ups. It also tracks each lead's pipeline state from n | |
| IMDB MCP alexobarnes/imdb-mcp Enables semantic and similarity search across IMDB movie data using vector embeddings and PostgreSQL with pgvector, supporting traditional filters and hybrid search. | |
| zotero-mcp-lite alexobiwan-creator/zotero-mcp-lite A lightweight and customizable MCP server for Zotero that enables AI research tools to access and manage references through a simple API. | |
| spriteloom-mcp alexpascu007/spriteloom-mcp Enables MCP clients to create and edit pixel-art sprites locally through a managed engine, including generation, editing, inpainting, rotation, listing outputs, and service status. | |
| NTDeliver MCP Server alexpavluck/ntdeliver-mcp Enables querying NTDeliver purchase order and milestone data (1,729 POs, 2014-2027) with tools for filtering, schema info, and summary statistics. | |
| gmail-mcp-local alexpekach/gmail-mcp-local Local-first Gmail MCP server using PKCE + loopback OAuth flow that stores refresh tokens in the OS keychain, enabling secure read/write Gmail access via MCP tools without tokens leaving the device. | |
| idiradocs-mcp alexperez7/idiradocs-mcp MCP server that gives Claude access to CyberArk/Idira official docs, enabling keyword search and live page retrieval as clean Markdown with citations, reducing hallucination. | |
| uxon-ai alexpilotto/uxon-ai MCP server and Claude skills for AI agents to build landing pages, run A/B experiments, and track first-party conversions. Lets agents onboard clients, create and publish pages, manage variants, and pull performance reports via the UXON API | |
| YouTube Search MCP alexplusplus/youtube_search_mcp_ts Enables AI assistants to run customized YouTube searches, combining relevance and view-count rankings to surface videos that are both on-topic and popular, and to fetch detailed metadata for known videos by ID or URL. Deploys as a remote St | |
| Garmin Read-Only MCP alexpomsft/garmin-readonly-mcp A read-only MCP server that synchronizes Garmin Connect summaries into a local SQLite cache and provides tools to query daily activity, recent activities, and recovery data. | |
| Roblox Studio MCP Assistant alexpoopy1/roblox-studio-mcp-server-v1 Enables AI assistants to interact with Roblox Studio in real-time, allowing creation and manipulation of game objects through natural language commands via an HTTP-based plugin system. | |
| billet-mcp alexpricedev/billet-mcp Adds a remote, OAuth 2.1-authenticated MCP endpoint to an app so Claude and ChatGPT connectors can register themselves, send a person through a consent screen, and call the app's tools as that person. It supplies discovery metadata, PKCE au | |
| apple-music-mcp alexpriest/apple-music-mcp Enables searching the Apple Music catalog, building playlists, and managing a library through the Apple Music API. | |
| swarm-mcp alexpriest/swarm-mcp An MCP server that provides access to Foursquare Swarm check-in data, enabling AI assistants to query check-in history, stats, top venues, and venue details. | |
| SAP BusinessObjects MCP Server alexraio/sap-business-objects-mcp Enables AI agents to administer, inspect, and troubleshoot BI Platform 4.3 SP5 through REST Web Services, including Web Intelligence documents, universes, CMS security, schedules, and repository hierarchy. | |
| fizzy-mcp alexrbzz/fizzy-mcp MCP server for Fizzy (Kanban tool by 37signals) that enables AI assistants to read and manage boards, cards, columns, tags, comments, and more. | |
| shopmcp alexrexby/shopmcp Turns an online store's catalog into MCP tools so agents can search products, fetch details, look up barcodes, analogs, categories, promotions and pickup points, and hand off a cart as a payment link rather than checking out. It is driven b | |
| geoanalisis-mcp alexrobl/geoanalisis-mcp Enables reading and analysis of vector spatial data through Claude Desktop, supporting formats like FileGDB, Shapefile, GeoJSON, and GeoPackage with tools for layer listing, schema inspection, field statistics, feature extraction, and inter | |
| caveman-mcp alexruco/caveman MCP server that compresses markdown files into caveman-style prose, cutting token usage by 65% while preserving code and structure. | |
| Playwright MCP Server alexrwilliam/playwright-mcp-server A minimal server that exposes Playwright browser automation capabilities through a simple API, enabling webpage interaction, DOM manipulation, and content extraction via the Model Context Protocol. | |
| jenkins-mcp-server alexsarrell/jenkins-mcp-server Provides Jenkins integration with Claude Code, enabling job management, build operations, pipeline stages, and log search via 22 tools. | |
| mcp-terraform-ls alexsavio/mcp-terraform-ls An MCP server that wraps terraform-ls to provide Terraform language intelligence as MCP tools, enabling AI assistants to understand and navigate Terraform codebases. | |
| Claude Code MCP Bridge alexscarano/claude-code-mcp Exposes Claude Code's file editing, command execution, and test running capabilities as composable MCP tools for any MCP-compatible host, enabling code operations via a stateless bridge. | |
| atlassian-readonly alexschaap-tmmc/atlassian-readonly Enables AI assistants to securely read and search Jira and Confluence Cloud content while enforcing read-only access and protecting stored credentials. | |
| JN Engine Contributor MCP alexscott2718-gif/jn-engine-contributor-mcp A read-only MCP gateway for contributors to JN Engine, exposing immutable repository snapshots via REST and Streamable HTTP for ChatGPT, Claude, and coding agents. | |
| r-coding-mcp alexseymer/r-best-practice-mcp Enables Claude to interact with R package development workflows, including CRAN metadata lookup, dependency checking, testing, documentation validation, and release automation. | |
| Synapse alexsh88/synapse A self-hosted, temporal knowledge-graph memory for AI coding agents — shared across projects, queryable across time, written and read via MCP by any Claude Code session. | |
| Tailnet MCP Server alexskorn/tailscalemcp Query devices, check connectivity, and get network status from your Tailscale tailnet directly via an AI assistant. | |
| MCP Server for continue.dev alexsmirnov/obsidian-second-brain-mcp A Python server implementing the Model Context Protocol to provide customizable prompt templates, resources, and tools that enhance LLM interactions in the continue.dev environment. | |
| better-browser-mcp alexsorokoletov/bopbop Gives any MCP-compatible AI agent control of the user's own Chrome profile with existing sign-ins, returning compact text snapshots and batched action results so browsing tasks finish in far fewer calls and tokens. Includes safety guards ag | |
| Letterboxd MCP Server alexstajos/letterboxd-mcp Enables AI models to interact with Letterboxd data and perform account actions like rating films, writing reviews, and managing watchlists. | |
| gtm-mcp-server alexstansfield/gtm-mcp-server A Model Context Protocol server for Google Tag Manager that uses service account authentication, providing tools to manage accounts, containers, workspaces, tags, triggers, variables, and versions. |
26,351–26,400 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.