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 |
|---|---|
| merlonix-mcp cmhenry79/merlonix-mcp Provides live infrastructure monitoring for AI agents, including domain health checks, MCP server security posture, email blacklists, broken-link scans, and cloud vendor status. No signup or API key needed for public tools. | |
| Basalt MCP cmillstead/basalt-mcp A security-hardened MCP server that enables AI models to safely interact with Obsidian vaults through sandboxed file operations and todo tracking. It implements strict validation layers and resource limits to protect the local filesystem fr | |
| Algorate MCP Server cmiretf/algorate-mcp Enables comprehensive algorithm benchmarking, performance analysis, and optimization across JavaScript, TypeScript, and Python code, with AI-powered insights and automated comparisons. | |
| maketka-mcp cmit-ru/maketka-mcp Enables MCP-capable AI clients to act as a teacher's assistant for the Maketka 3D modeling service: read anonymized student work, draft lesson reviews, create assignments, and build 3D models and circuits in the open editor. | |
| job-tracker-mcp cmixiv/job-tracker-mcp Enables AI assistants to query a job-search tracker read-only for roles, due dates, individual company records, and status summaries. | |
| betterkey-mcp cmlabsllc/betterkey-mcp Enables AI agents to inspect connected vehicles and issue lock/unlock commands through a scoped, authenticated vehicle API, with telemetry, capability, location access, and explicit confirmation for destructive actions. | |
| Margin cmlkevin/margin Enables agents to query a self-hosted research inbox, search and retrieve collected sources and posts, inspect source health, and refresh source collection through authenticated MCP tools. | |
| asana-mcp cmloegcmluin-org/asana-mcp An MCP server for Asana that accesses every workspace using a personal access token, enabling task and project management through integrated tools like list, create, and complete tasks. | |
| Universal Roblox AI Studio cmmdx256/roblox-studio-mcp Provides an MCP runtime that turns Roblox Studio into an AI-native, autonomous, bidirectional development platform, letting AI assistants create and edit scenes, models, animations, scripts, and game systems through 63+ tools. It integrates | |
| cmmv-mcp cmmvio/cmmv-mcp Enables standardized interactions between LLMs and CMMV applications using the Model Context Protocol, with decorator-based tool registration and flexible transport options. | |
| Mingdao MCP Relay (Node.js) cmmzxx/mcp-relay-node Proxies MCP tools from Mingdao cloud, enabling Coze to use them securely without exposing Mingdao tokens. | |
| tiime-mcp cmoi936/tiime-mcp Enables MCP clients to authenticate against an internal accounting web API, list companies, categories, bank transactions and documents, upload or batch-deposit receipts (idempotent, dry-run by default), set accounting metadata, and link do | |
| vocce cmoonagent/vocce-agent Transcribe local audio/video to text + SRT/VTT with hosted Whisper large-v3, plus summaries, study notes, flashcards, document Q&A, and PDF compression. No API key required — runs via npx -y vocce-transcribe-mcp. | |
| loci cmoraes10/loci Enables MCP clients to give agents durable long-term memory by exposing remember, recall and forget tools backed by a typed SQLite store, so facts about a user can be written deliberately and the most important ones retrieved on request. | |
| pi-exec-mcp cms19859230182-lang/pi-exec-mcp Enables an assistant to run pi coding-agent tasks in the background: dispatching a task, polling its status and tool trace, reading the final result, and cancelling it when no longer needed, all without pulling the delegate's context into i | |
| Claude + Notion MCP Demo cms19859230182-lang/upwork-notion-mcp-claude-demo Runs an offline MCP server over a synthetic two-client workspace, enabling safe page searches and table edits while refusing ambiguous requests. | |
| Appian MCP Server cmsappian123-bit/mcp-appian Enables interaction with Appian applications through the Model Context Protocol, allowing querying and managing records, executing processes, and querying reports via natural language. | |
| CardOS MCP Server cmscardos/cardos-mcp Enables AI assistants to issue and manage virtual cards, check balances, pull transactions, file disputes, and start KYC via the CardOS API. | |
| mcp-pje-trf1 cmsdutra/trf1-pje-mcp-bridge MCP server for automating consultation and download of documents from Brazil's TRF1 PJe system through authenticated sessions. It uses Playwright for authenticated navigation, providing tools to query process metadata, list documents, and d | |
| pycycle-mcp cmudrc/pycycle-mcp Model Context Protocol server for pyCycle/OpenMDAO engine-cycle workflows, enabling lifecycle management, variable inspection, execution, sweeps, and integration with CPACS aircraft analysis pipelines. | |
| su2-mcp cmudrc/su2-mcp Enables interaction with SU2 CFD solver for session lifecycle management, config editing, solver execution, and results inspection, with optional CPACS integration for aircraft analysis. | |
| tigl-mcp cmudrc/tigl-mcp Provides MCP tools for CPACS-oriented TiGL workflows, enabling lifecycle management, inspection, export, and parameter manipulation of aircraft geometry models without native geometry runtimes. | |
| epochcalc cmunkres/epochcalc-mcp Epoch Calculator
Time and date math that language models get wrong on their own: Unix timestamps, daylight-saving offsets, calendar arithmetic, and cron schedules. Every calculation uses the IANA time zone database, the same engine behind | |
| dev-env-setup cmwen/mcp-dev-env-setup Automates setup of local development environments for Python, Node.js, Flutter, Android, and more on macOS and Linux. Can be used as a standalone CLI or as an MCP server for AI assistant integration. | |
| Minimalist Knowledge Base MCP cmwen/min-kb-mcp Enables LLMs to manage file-based knowledge bases with dual storage (Markdown + SQLite). Supports creating, searching, and organizing articles across multiple knowledge bases with full-text search capabilities. | |
| alpha-library cmxms/alpha-library MCP server for searching and retrieving trading knowledge from a centralized SQLite library of book summaries, strategies, and document chunks. | |
| Unified Search MCP Server cn-hash/unified-search-mcp-server Enables AI agents to perform multi-platform searches (Douyin, Xiaohongshu, Zhihu, CSDN) and reverse-engineer arbitrary websites using browser automation and CDP. | |
| Social Media Scraper - Custom MCP Server cnam7549/custom-mcp-server Enables AI assistants to retrieve public LinkedIn, Facebook, and Instagram profile data and perform Google web searches through MCP tools. | |
| Sprint MCP Server cnavta/sprint-mcp Enables LLM agents to manage structured sprint-based development workflows following the Sprint Protocol, including sprint initialization, status checking, and manifest generation. | |
| CNBizAPI MCP Server cnbizapi/cnbizapi-mcp Enables AI agents to query detailed information on 77M+ Chinese companies, including basic data, shareholders, legal risks, and more, through a pay-per-query MCP server. | |
| mcp-library-search cnderrick/mcp_library_search Enables users to find books by keyword, ISBN, or author and check which branches hold copies of them and whether those copies are currently available for loan or when they are due back. Currently covers Shanghai's interlinked public library | |
| SeekFleet cndoin/seekfleet Cross-platform control plane for DeepSeek Harness agent fleets with MCP, durable sessions, adaptive routing, policy gates, token budgets, and a phone-friendly LAN dashboard. | |
| pfSense MCP Server cnelson016/pfsense-mcp-server Enables natural-language control of pfSense firewalls from Claude Desktop, Claude Code, or any MCP client, covering firewall rules, NAT, VPN, DNS, DHCP, routing, certificates, users, and diagnostics through 332 wire-format-verified REST API | |
| Rohlik MCP Server cneumann6281/rohlik-mcp Enables AI assistants to shop for groceries across the Rohlik Group's online delivery platforms by searching products, managing shopping carts, tracking orders and delivery slots, and surfacing personalized meal suggestions, frequent items, | |
| PhoneLCDParts MCP Server cnguyen14/plp-mcpserver A web scraping server that retrieves product information (name, price, URL, image) from phonelcdparts.com for any search query. | |
| t-pane MCP Server cni-locates-rumen/t-pane Enables Claude to execute commands and manage directory-aware panes within tmux sessions for a shared terminal experience. It features smart output capture, interactive prompt detection, and background task management. | |
| mnemo cniackz/mnemo Provides portable memory for AI agents using plain Markdown files. Enables storing, recalling, and managing memories via MCP tools like recall, remember, forget, list, and get. | |
| timemap-mcp cnick26/timemap-mcp Enables AI agents to perform Chinese metaphysics calculations including BaZi charts, Tong Shu indicators, solar terms, and more, using a verified engine with 740+ tests. | |
| lsd-mcp cnielsen94/lsd-mcp Enables agents to inspect, edit, compile, and run LSD simulation models headless, and to create and analyze sensitivity-analysis designs with Sobol indices or elementary effects. | |
| Headless IDA MCP Server cnitlrt/headless-ida-mcp-server A server that provides remote binary analysis capabilities through IDA Pro's headless mode, allowing users to manage and manipulate functions, variables, and other binary elements via the Multi-Client Protocol. | |
| pygdbmi-mcp-server cnitlrt/pygdbmi-mcp-server Enables dynamic debugging with GDB via the MCP protocol, allowing LLMs to execute GDB commands, manage breakpoints, control execution, and inspect program state. | |
| Claude Patent Creator cniuftvcyj/claude-patent-creator Exposes 20+ tools that let any MCP-compatible client answer patent-rule questions from MPEP/USC/CFR via hybrid vector, lexical, and reranked search, hunt prior art across 100M+ patents through Google BigQuery, run automated 35 USC 112 compl | |
| MCP Jenkins cniuftvcyj/mcp-jenkins Enables AI assistants to interact with Jenkins through secure, contextual tools for querying and managing jobs, builds, nodes, queues, views, plugins, artifacts, and Groovy scripts, with configurable authentication and read-only safety. | |
| droidasc-mcp cnlnn/droidasc-mcp Enables safe, read-only analysis of Android APKs through six typed MCP tools, including manifest decoding, class listing, source decompilation, and reference searching, with paginated structured output and strict path/timeout limits. | |
| wp-mcp cnmbdb/wp-mcp MCP server for WordPress content management via REST API, supporting posts, pages, media, comments, and terms through natural language interfaces like Cursor, ChatGPT, Codex, and Claude. | |
| polaris-audit cnohall/polaris-audit-mcp Audit any website for privacy, security, accessibility, and performance issues — with scores, grades, and actionable fix instructions. No account required. | |
| CnosDB MCP Server cnosdb/cnosdb-mcp-server An MCP server that enables interacting with CnosDB databases through Claude, supporting SQL queries, database listing, table listing, and schema descriptions. | |
| ledgerline cnpierrepapi/ledgerline-ai An MCP server that integrates with DataHub to track and score the reliability of AI agent actions. It provides a trust gateway that stamps every piece of context with its author's settled trust score. | |
| cnpjaberto cnpjaberto/cnpjaberto-py MCP server for querying Brazilian CNPJ company data, including partner graphs, address/contact joins, CNAE statistics, and national/annual overviews. | |
| accio-work-export-kb-suite cnproduct/accio-work-export-kb-suite Enables evidence-first, tenant-isolated knowledge management and business-scenario execution for Accio Work foreign trade, with honest unavailable responses when connectors or approvals are missing. |
39,501–39,550 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.