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 |
|---|---|
| TrainingPeaks MCP Server campos21861/trainingpeaks-mcp Enables athletes and coaches to query workouts, build structured intervals, manage calendars, events, health metrics and multi-week plans, and track CTL/ATL/TSB fitness and power PRs through natural language. Uses secure cookie-based authen | |
| google-workspace-mcp camposdelima/google-workspace-mcp A unified MCP server for Google Workspace APIs providing tools for Chat, Gmail, and Calendar operations including messaging, email management, and event scheduling. | |
| mcp-cybersec-server camr8989/mcp-cybersec-server MCP server that supports cybersecurity operations by providing CVE lookup, risk summarization, and playbook resources through CIRCL Vulnerability-Lookup API. | |
| outlook-rag camucamulemon7/outlook-rag Enables local semantic and Japanese keyword search over Outlook Classic mail through MCP, including indexing connected mail folders and reading cached messages. It supports OpenAI-compatible embeddings, incremental sync, and metadata-filter | |
| Fusion Compiler Session MCP camucamulemon7/test_mcp2 Manages a persistent Fusion Compiler session via PTY, enabling Tcl command execution and common EDA queries through an MCP interface. | |
| Fusion Compiler Session MCP camucamulemon7/test_mcp3 Enables starting and managing named independent PTY sessions for Synopsys Fusion Compiler, sending arbitrary Tcl commands, and listing/interrupting sessions via MCP. | |
| uptime-kuma-mcp-server camusama/uptime-kuma-mcp-server Enables managing Uptime Kuma monitors via MCP protocol, supporting batch add, list, and delete operations. | |
| xilinx-rag can-y/doc_search An MCP server for AI-driven hybrid search over Xilinx/AMD FPGA documentation, enabling assistants to retrieve datasheets, user guides, and application notes through tools like search_docs. | |
| PDM MCP Server can-y/pdm_mcp AI-powered FPGA power estimation assistant that wraps Xilinx PDM API as MCP services for natural language power modeling and analysis. | |
| PlayCanvas Editor MCP Server can3021/editor-mcp-server Enables AI agents to automate the PlayCanvas Editor by managing projects, entities, assets, scripts, scenes, builds, and runtime sessions, and by verifying scenes through launching and capturing screenshots. | |
| ombre-brain can947/ombre-brain Gives Claude persistent cross-conversation memory by storing and retrieving memories tagged with Russell's valence/arousal coordinates as Obsidian-compatible Markdown files. Memories decay on a forgetting curve, and unresolved or emotionall | |
| mcp-mgba canadadry/mcp-mgba A headless MCP server that lets an LLM load Game Boy Advance ROMs, step through instructions, read and write memory, and manage breakpoints, watchpoints, and registers. | |
| Guia da Maquininha MCP Server canalthailexa-lgtm/mcp-guiamaquininha-repo Enables AI models to query and compare Brazilian card machine MDR rates and monthly costs across brands and business profiles, including tools for listing brands and tiers, calculating costs, and ranking options. | |
| AddressPenny MCP Server canalweststudio/addresspenny-mcp An MCP server for AddressPenny address validation that enables users to validate postal addresses, bulk-clean address lists, and extract addresses from unstructured text through Claude Desktop, Cursor, and other MCP-compatible agents. | |
| Eplan-mcp canary-ecad/eplan-mcp MCP server for EPLAN Electric P8: ~200 tools to drive EPLAN from Claude Code, Codex, Cursor or any MCP client (actions, scripts, live DataModel, exports). | |
| Supabase MCP Server canbolayir/self-hosted-supabase-mcp Enables Claude to fully manage self-hosted Supabase instances, covering authentication, database, storage, edge functions, and more. | |
| Niblet canc3831/niblet-skill-mcp Gives coding agents real product screen references, design-system sections, and font/icon materials as inline images and typed structured content, so unresolved layout, state, or typography questions can be grounded in screens that already | |
| mcp-gateway cancychen/mcp-gateway AI gateway to unify authentication and expose internal APIs as MCP tools. Supports SSO, JWT, and basic auth with auto-refresh. | |
| university-quiz-mcp-app candacezcc/university-quiz-mcp-app Enables ChatGPT to turn uploaded course materials into interactive quizzes with multiple question types, in-chat answering, automated grading, and results analysis. | |
| semaphore candelitekey/semaphore Reads login-walled web pages by replaying cookies from your browser, returning clean markdown via MCP tools. | |
| Research Papers MCP Server candenizkocak/research-papers-mcp-server Enables LLMs to search and retrieve academic papers from arXiv by topic, author, category, or ID. | |
| DSH Computer MCP cander0815/dsh-computer-mcp Enables DeepSeek Harness to operate files on another computer over MCP, including browsing, reading, writing, editing, searching, moving, and recoverable deletion, with optional command execution. It supports Windows and macOS via LAN or Ta | |
| remote-mcp-server-authless candiceroberts-gif/remote-mcp-server-authless A remote MCP server deployed on Cloudflare Workers without authentication, allowing users to create custom tools and connect to MCP clients like Cloudflare AI Playground and Claude Desktop. | |
| Zeus Mobile MCP candraprasetya/zeus-mobile-mcp Enables local, air-gapped automation of Android and iOS devices and emulators, letting AI agents inspect UI hierarchies, tap, swipe, type, manage apps, capture screenshots, and pull device logs and crash reports. Bundles banking-grade safeg | |
| CodeBrain MCP Server candrle20/codebrain Enables semantic code search across codebases using AI embeddings and vector similarity, integrated with Claude Desktop and Cursor. | |
| Tracora MCP Server canerdem1234/tracora-mcp Connects Tracora brand and query data to MCP assistants, enabling listing of active brands and AI visibility queries via two read-only tools. | |
| VSCode MCP canesposito/vscode-mcp Enables MCP clients and AI coding agents to query a running VSCode instance for real-time LSP diagnostics, hover/definition/signature info, symbol references, and workspace-wide renames instead of waiting on slow tsc or eslint runs. It also | |
| canforge-mcp canforge/canforge-mcp Local, read-only MCP server for inspecting DBC files and decoding CAN capture logs, with bounded and composable tools. | |
| CrossBorder Copilot MCP cang-ge/crossborder-copilot-mcp Enables cross-border ecommerce support teams to analyze logistics exceptions, retrieve citable policies, draft bilingual customer replies, and create idempotent tickets under human confirmation. | |
| Stock Trade MCP Server cang13/stock-trade-finance-api Exposes Tiingo API endpoints as MCP tools so users can programmatically retrieve end-of-day and intraday prices, forex quotes, news articles, fundamentals and corporate actions like dividends and splits for given tickers. | |
| kali-mcps cangarnier773/awsome_kali_mcpservers Provides MCP clients with Kali Linux security and reverse-engineering capabilities, including Nmap scanning, nm/objdump binary analysis, strings extraction, tshark traffic capture, and Docker-based sandboxed command execution. | |
| figma-developer-mcp cangnt5/windsurf-figma-context-mcp Enables coding agents like Cursor to access Figma design data, fetch layout and styling information, and implement designs in any framework. | |
| tv-buying cangyuyi/tv-buying-copilot Enables MCP-compatible clients to search TV products and knowledge, retrieve promotions, check fulfillment details, and look up after-sales policies while flagging high-risk cases for human transfer. | |
| Tho Social Publisher canhanmvp/tho-social-publisher Enables AI agents and MCP clients to connect their own social accounts via OAuth and publish or schedule posts through a small provider-agnostic interface using official platform APIs. | |
| rekabet-karar-mcp cankilercioglu99-sudo/rekabet-karar-mcp Enables searching and retrieving US federal antitrust decisions from the CourtListener API, providing verified citations and full text for competition law research. | |
| Change Trace MCP canlendula/change-trace-mcp A local-first, model-neutral MCP server for collecting and normalizing change-scoped release evidence. It provides deterministic Git change summaries, evidence collection, and review bundles for agent review. | |
| MarkItDown MCP Server canlgz/markitdown_mcp_server A Model Context Protocol server that converts various file formats (PDF, PowerPoint, Word, Excel, Images, etc.) to Markdown to make them accessible to LLMs. | |
| Claude Telegram Supercharged canm20/claude-telegram-supercharged Enables driving Claude Code entirely from a Telegram chat, with voice messages transcribed both ways, memory that survives restarts, live visibility into each tool call as it runs, and scheduling plus Google Calendar access. It also keeps a | |
| Gitingest-MCP canmichel82/gitingest-mcp Enables MCP clients to extract GitHub repository information, including repository summaries, project directory structure, and file contents. | |
| imessage-rich-search cannavis/imessage-rich-search Enables full-text search of macOS iMessages including link preview metadata. Works as an MCP server for Claude Desktop to search your messages locally. | |
| @cano721/mysql-mcp-server cano721/mysql-mcp-server Enables read-only MySQL database access, allowing listing databases, tables, describing schemas, and executing SELECT/SHOW/DESCRIBE/EXPLAIN queries. | |
| clermes-mcp canopy-workshop/clermes-mcp Exposes a Clermes worker fleet as typed tools over HTTP and stdio, enabling a coordinator to drive the fleet with structured tool calls. | |
| Searchfox MCP Server canova/searchfox-mcp Provides access to Mozilla's Searchfox code search service, enabling AI assistants to search through Mozilla's codebases and retrieve file contents from repositories like mozilla-central, autoland, and ESR branches. | |
| Bitbucket MCP canpalmer26935/bitbucket-mcp Enables AI assistants to interact with Bitbucket Cloud and Server APIs, including listing and retrieving repositories, fetching pull requests, creating pull requests, and managing related resources safely without DELETE operations. | |
| MCP Jenkins canscholz/mcp-jenkins Enables AI assistants to securely interact with Jenkins through the Model Context Protocol, providing tools for querying, building, monitoring, and managing Jenkins items, builds, nodes, queues, plugins, artifacts, and scripts. | |
| webuntis-mcp cansde/webuntis-mcp Enables AI clients to access and query WebUntis school data, including timetables, homework, exams, absences, and more via MCP tools. | |
| bilibili cansiny0320/bili-agent-kit Enables AI assistants to read videos, official subtitles, comments, private messages, and live room/danmaku data, plus scan-QR login and admin-approved sending of replies, comments, and danmaku with writes disabled by default. | |
| MCP Red Team Server canstralian/mcpserverforredteamagenticworkflowszip A Model Context Protocol server for orchestrating red team security assessments, enabling LLMs to manage agents, targets, operations, and findings aligned with MITRE ATT&CK framework. | |
| Canuckduck MCP canuckduckdevops/canuckduck-mcp Canadian Civic Intelligence | |
| canvas-teacher-mcp canvas-lms-mcp/canvas-teacher-mcp An MCP server for Canvas LMS that enables assistants to read course content, create assignments and pages, set due dates, and post announcements via the Canvas REST API. |
36,651–36,700 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.