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 |
|---|---|
| playstore-release beydemirfurkan/playstore-release Enables end-to-end Android app publishing to Google Play via the Developer API, including readiness checks, releases, promotions, reviews, and subscriptions. | |
| tweetly beydemirfurkan/tweetly An MCP server that enables AI agents to automate actions on X (Twitter) through a real browser session, including posting, engaging, and reading via over 40 tools. It supports self-hosting and provides a panel for API key management. | |
| Hiworks Mail MCP beylessai/hiworks-mcp A Model Context Protocol server that allows integration with Hiworks mail system to search, read, and send emails with support for text, HTML, and attachments. | |
| Beyond MCP Server beyond-network-ai/beyond-mcp-server An extensible Model Context Protocol server that provides standardized access to social platform data (currently Farcaster) and onchain data for LLMs. | |
| foundry-maf-custom-mcp beyondelastic/foundry-maf-custom-cert-mcp Enables testing of secure MCP connections with custom CA certificates and verified TLS. | |
| sens beyondhumane/sens-ai Provides MCP tools for Claude Code to query a project's codebase via a compact index, reducing token usage and context bloat by enabling symbol lookup, usage tracking, and dead-code detection. | |
| flow-mcp beyondmrk/flow-mcp Enables Claude to drive Google Flow in a dedicated Microsoft Edge window over CDP, firing stills and clips, tracking attempts, and downloading results. | |
| never4ga-mcp bezacore-labs/never4ga Enables AI agents and MCP clients to start each session with a pre-assembled context pack of the project's Markdown notes, decisions, rules, Git and tracker state, and to write progress and decisions back as dated logs. Context is gathered | |
| Google Calendar MCP Server bezael/mcp-calendar Enables language models to interact with Google Calendar through OAuth2 authentication, allowing creation, retrieval, listing, updating, and deletion of calendar events. | |
| eea-climate-data-mcp bezilaszlo/eea-climate-data-mcp Schema-aware, read-only access to European climate data from the EEA Discodata service, supporting GHG inventory and policies and measures databases. | |
| ovf-data-mcp bezilaszlo/ovf-data-mcp Provides agent-friendly, read-only access to public Hungarian water-management data from the Országos Vízügyi Főigazgatóság (OVF), enabling station discovery, measurement catalog inspection, and time series retrieval and aggregation. | |
| taskfleet-mcp bfai-1/taskfleet-mcp Exposes TaskFleet's pay-per-call AI task APIs as MCP tools, including web search, scraping, extraction, translation, code review, summarization, and wallet intelligence. Payments are handled via x402 (USDC on Base) with no accounts or API k | |
| mcp-copilot bfarhad/copilot-bridge-mcp Enables MCP clients such as Kiro, VS Code, and Claude Code to send prompts and code snippets to a signed-in Microsoft Copilot session running in the user's own Edge browser and receive the replies as Markdown, with no API key or separate lo | |
| Apple Notes MCP Server bfeeny/apple-notes-mcp Enables Claude to read, write, search, and manage Apple Notes on macOS via AppleScript automation. | |
| ios-instruments-mcp bfernandesbfs/ios-instruments-mcp Enables natural language profiling of iOS apps using xctrace (Instruments) for performance analysis like launch time, memory leaks, CPU usage, and network requests. | |
| ccv2-logs-mcp bfernandez2-seidor/ccv2-logs-mcp Enables AI agents to search and analyze SAP Commerce Cloud (CCv2) runtime logs via OpenSearch Dashboards using a session cookie, providing read-only tools for full-text search and error aggregation. | |
| LINDAS MCP Server bfh-jtf/lindas-mcp Enables LLMs to query structured statistical data from the Swiss Federal Archives' Linked Data platform (LINDAS) by translating natural language questions into SPARQL queries against RDF data cubes. | |
| RentCast MCP Server bfhayes/rentcastmcp Wraps the RentCast API to search houses for sale, get valuations, rent estimates, and market statistics. | |
| ClawMem MCP Server bflabsai/clawmem-bf Enables AI agents to maintain persistent, local memory with retrieval-augmented search, knowledge graphs, and context surfacing, without any cloud dependencies. | |
| signal402-mcp bflynn4141/signal402-mcp Enables AI agents to discover, evaluate, and call any x402 API service with automatic USDC payment, including tools for wallet setup, service catalog browsing, recommendations, health checks, and direct API calls. | |
| Academic Paper Search MCP Server bfreitas7739/academic-search-mcp-server Enables LLMs and compatible clients to query Semantic Scholar and Crossref for papers, retrieve metadata, abstracts, and available full-text content, and filter topic searches by date range through MCP tools. | |
| Shiprocket MCP Integration bfrs/shiprocket-mcp Enables interaction with Shiprocket shipping services to check courier rates and delivery times, create and manage orders, ship packages, track shipments, and schedule pickups through natural language commands. | |
| AgentAM bfujah/agentam Enables an LLM client to query CFD-trained surrogates for SS316L laser powder bed fusion, predict spatter and melt pool geometry, classify defect regimes, scan power–velocity windows, and search for low-spatter, margin-aware process paramet | |
| arch-optimize bfxh/arch-optimize MCP server that provides tools for architecture analysis, risk diagnosis, quality metrics, and regression guarding to support AI-driven code review and incremental refactoring workflows. | |
| searxng-mcp bg-titan/searxng-mcp Enables MCP clients to perform web searches through a self-hosted SearXNG instance, offering privacy-focused metasearch without API keys or vendor lock-in. | |
| mcp-search-server bg1avd/mcp-search-server Enables MCP clients to perform web searches through a self-hosted SearXNG backend with automatic Bing fallback, protected by API key authentication. | |
| GitOps Safe MCP bgauger/gitops-safe-mcp Enables read-only inspection of Git repository status and diff summaries, along with validation of OpenTofu and Ansible configurations, through a strictly limited, non-mutating toolset. | |
| Prometheus Safe MCP bgauger/prometheus-safe-mcp Executes constrained, read-only Prometheus queries for instant metrics, active alerts, and target health, with bounded resource usage and audit records. | |
| proxmox-safe-mcp bgauger/proxmox-safe-mcp Enables safe, confirmable Proxmox operations: read-only cluster/guest status and bounded power actions and snapshot creation, with explicit byte-for-byte approval for each mutation. | |
| Technitium Safe MCP bgauger/technitium-safe-mcp Enables bounded, read-only DNS lookups and health checks against allowlisted Technitium servers with strict safety constraints. | |
| unifi-safe-mcp bgauger/unifi-safe-mcp Enables read-only, bounded access to UniFi Network appliance health, devices, and active clients through three safe MCP tools with TLS verification and redirect rejection. | |
| Local Explorer MCP bgauryy/local-explorer-mcp Enables AI assistants to intelligently search and explore local file systems using native Unix commands (ripgrep, find, ls) with token-optimized output, automatic pagination, and multi-layer security validation. | |
| Octocode MCP bgauryy/octocode AI-powered code assistant that provides advanced search and discovery capabilities across GitHub and NPM ecosystems, helping users understand code patterns, implementations, and connections between repositories. | |
| bg-server-mcp-shell bgbruno/bg-server-mcp-shell MCP server for running long-running processes in PTY with real-time output streaming, enabling interactive dev servers, watch modes, and CLI tools. | |
| agent-antigravity-mcp bgembalczyk/agent-antigravity-mcp MCP server for Google Gemini Antigravity Agent, enabling autonomous code execution, web browsing, and GitHub PR workflows in remote sandboxes. | |
| Amazing Marvin MCP bgheneti/amazing-marvin-mcp Integrates the Amazing Marvin productivity system with AI assistants to manage tasks, projects, and time tracking. It enables users to query their workload, receive personalized productivity coaching, and update their schedule through natur | |
| aegis-mcp bgigurtsis/aegis-mcp Provides AI coding agents with deterministic security requirements, approved patterns, and anti-patterns based on a project's threat model defined in security-context.yaml, enabling secure code generation without relying on LLMs for securit | |
| wordpress-mcp-server bgildea/wordpress-mcp-server Enables Claude and other MCP-capable agents to read a WordPress site and draft new posts through the WordPress REST API, with a read-only mode that disables write tools. | |
| RappiMCP bgirardi99/rappimcp Enables Claude to browse stores, search products, manage the cart, and open checkout on Rappi Chile through natural language, automating grocery and delivery purchases. | |
| Flick bgivenb/flick-computer-use Enables MCP agents to execute whole browser and macOS goals locally, supplying goals, exact values, and completion conditions while Jev handles the observe-decide-act loop. | |
| musescore bgng-co-jp/musescore-mcp Drives MuseScore Studio 4.7.6 headlessly to inspect and repair score layout — breaks, measure stretch, styles, element offsets, fitting to N pages, overlap detection, plus PNG/PDF export — while working on versioned copies so the original s | |
| aipulse MCP Server bgomes878/awesome-ai-pulse-georgia Lets MCP-compatible clients and coding agents search, list, filter, and retrieve details from a curated catalog of 378 AI agent frameworks, developer tools, and automation repositories using natural language, with bilingual (English/Georgia | |
| wechat bgonzalez86498/wechat-decrypt Enables Claude Code to query locally decrypted WeChat 4.0 databases through tools for listing recent sessions, retrieving chat history, searching messages across the whole database, looking up contacts, and fetching messages that arrived si | |
| bgphorizon-mcp bgphorizon/bgphorizon-mcp Enables AI assistants to query global BGP routing intelligence, including network investigation, origin history, reachability, and health checks, with 15 tools plus resources and prompts for incident triage and reporting. | |
| sonos-mcp bgrgicak/sonos-mcp MCP server for controlling Sonos speakers. Currently early scaffolding with a temporary discover tool. | |
| datadog-logs-mcp bgrgndzz/datadog-mcp Enables querying and analyzing Datadog logs through search, aggregation, and index listing. | |
| gong-mcp bgrgndzz/gong-mcp MCP server for the Gong API, enabling search and retrieval of calls, transcripts, attendees, next steps, and more. | |
| Huly MCP Server bgx4k3p/huly-mcp-server MCP server providing full coverage of the Huly SDK — issues, projects, workspaces, members, and account management. | |
| hx-multianim-mcp bh213/hx-multianim-mcp Connects MCP clients to a running hx-multianim game via DevBridge for scene inspection, state manipulation, input injection, and diagnostics. | |
| bharosa-docs-mcp bhafin/plugin Provides read-only MCP tools that let coding agents search and read bundled Bharosa documentation, API operation details, and SDK/cURL examples. It enables retrieving a contract, selecting grounded examples, and planning integrations withou |
33,901–33,950 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.