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 |
|---|---|
| LinkWatch cnpt9db5gp-cpu/linkwatch Enables local Linux network diagnostics through MCP tools for status checks, device discovery, reachability tests, topology inspection, incident review, monitoring status, and label or declared-link management. | |
| xueqiu cnqqc/xueqiu-mcp Enables AI clients to access Xueqiu's real-time quotes, financial statements, capital flows, and community discussions for A-shares, HK, and US stocks, with 22 tools requiring no setup. | |
| MAL-MCP-Worker cnr-daily/mal-mcp-worker-v2 MCP server that exposes MyAnimeList v2 API with OAuth authentication, enabling anime and manga search, rankings, seasonal charts, and user list management through natural language. | |
| mcp-bridge cnrpot/mcp-bridge A Windows MCP workspace control center that manages connections, permissions, running tasks, and file change history, offering tools for file operations, command execution, screenshots, .NET and Godot workflows. | |
| Case Tools MCP cnvxstudio/case-tools-mcp Enables MCP-compatible assistants to perform deterministic local Unicode lowercase, uppercase, and inverse-case conversion on plain text without network requests or a language model. | |
| Pronunciation Practice MCP cnvxstudio/pronunciation-practice-mcp Enables an MCP client to turn a sentence and optional feedback into a timed, repeatable rehearsal plan with four concrete steps and a blank comparison log, without audio processing, scoring, network calls, or API keys. | |
| deskpet-guard cny1230/deskpet-guard Enables other agents to query guardian status, events, and scan results, and to request human-confirmed termination of suspicious agent processes via MCP stdio. | |
| RCSB PDB MCP Server cnyambura/rcsb-mcp Provides tools to query, retrieve, and download protein structure data from the RCSB Protein Data Bank via the MCP protocol. | |
| Backlinks MCP cnych/seo-mcp A MCP server for retrieving backlink information for any domain(SEO). | |
| Slack MCP Server cnye36/slack-mcp-server Enables AI assistants to interact with Slack workspaces through secure OAuth 2.0 authentication. Supports posting messages, reading channel history, and listing channels across multiple workspaces with production-ready security features. | |
| remote-mcp-server-authless cnyjh/remote-mcp-server-authless Deploys a remote MCP server on Cloudflare Workers without authentication, enabling custom tool integration and connection to AI Playground or Claude Desktop. | |
| File Manager MCP Server cnyui/mcpdevelop Provides secure file system operations for AI assistants including directory listing, file reading/writing, deletion, searching, and copying. Features safety controls like path validation, permission checks, and file size limits. | |
| MCP-Artisan cnzhihao/mcp-artisan A secure MCP server with a workspace sandbox for AI agents to manage prompts, save HTML, and render HTML to images. | |
| synapse-mcp cnzhihao/synapse-mcp An intelligent memory and knowledge retrieval server that helps AI programming assistants remember and reuse solutions from previous conversations. | |
| Hilo MCP cnzontle/hilo-mcp MCP server for integrating with Hilo, the WhatsApp messaging platform. It provides API contracts, verification tools, and a guided plan for agents to build the integration. | |
| AgentCowork co-index/agentcowork Enables coding agents from different repositories to join shared rooms over MCP, discuss requirements, align API contracts, and debug together while keeping code on developer machines and using their own LLMs. | |
| graphdo-ts co-native-ab/graphdo-ts Enables AI agents to send emails and manage tasks in Microsoft To Do with scoped, low-risk access to Microsoft Graph. | |
| mcp-server-boilerplate co-ventech/mcp-server-boilerplate A local stdio-based MCP server starter with example tools, a resource, and a prompt, enabling developers to build and end-to-end test Model Context Protocol servers. | |
| Chaitin IP Intelligence Search Tool co0ontty/chaitin-ip-intelligence-search-tool Enables checking IP reputations and threat intelligence by querying Chaitin's global honeypot network and millions of defense nodes. Provides real-time IP profiling, malicious behavior detection, and threat alerts based on aggregated securi | |
| jushuitan-mcp co2t5zn/jushuitan-mcp Enables AI agents to search, browse, and retrieve Jushuitan Open Platform API documentation—including categories, parameters, error codes, and request/response examples—without manual lookup. | |
| Sequential Thinking MCP Server coachgruden/sequential-thinking-mcp-sse Enables AI agents to perform dynamic and reflective problem-solving through a chain of thoughts, allowing them to break down complex problems, revise past thoughts, and explore logic branches before reaching a conclusion. | |
| Freyja coadan/freyja Enables coding agents to scaffold, preview, inspect, navigate, capture, and build interactive HTML presentations authored as React/TSX source files. It operates the local presenter—keys, step tabs, URLs, and tools share one position—while a | |
| agent-kudos-mcp coaden/agent-kudos Enables AI agents to record, retrieve, and manage kudos for concrete accomplishments in a local-first, append-only store, with fixed actor identities and no cloud dependency. | |
| youtube-mcp coah80/youtube-mcp Enables AI assistants to watch YouTube videos by extracting frames at scene changes and visual references, pairing each frame with the exact words spoken at that timestamp. Provides dense frame-transcript interleaving for any model. | |
| fisc coalesc/fisc An open-source MCP server that enables AI agents to read, populate, and manage tax returns in Canadian professional tax software like Taxprep and DT Max through a vendor-neutral concept layer. | |
| papers coalesc/papers Enables software and AI to work with accounting engagements through portable concepts such as trial balances, adjustments, working papers, and review notes, with declared adapter capabilities and validate-before-commit mutations. | |
| Bazi MCP coastli/bazi-mcp Provides accurate Chinese Bazi (八字) fortune-telling calculations including birth chart analysis, destiny forecasting, and Chinese calendar information. Addresses inaccuracies in existing AI fortune-telling tools by delivering precise Bazi d | |
| amazon-mcp coaxon/amazon-mcp MCP server for Amazon Selling Partner API and Advertising API, enabling access to orders, inventory, pricing, ads, and reports via natural language. | |
| Cobalt Strike MCP Server cobalt-strike/cobaltstrike-mcp-server Bridges large language models with the Cobalt Strike C2 framework, enabling AI assistants to control adversary simulation workflows through natural language. | |
| MySQL MCP Server cobaltblue3699/mysql-mcp-server A Model Context Protocol server for MySQL databases that enables AI assistants to query schemas, execute SQL with permission controls, and manage databases through standardized tools. | |
| ECOUNT MCP Server cobbleai/mcp-server-ecount Enables AI assistants to interact with ECOUNT ERP through natural language, providing tools for products, inventory, sales, purchases, and more. | |
| freecad-mcp coben-3d/freecad-mcp MCP server for FreeCAD that enables AI assistants to create and manipulate 3D models via natural language. | |
| Shared Skills Registry MCP cobibean/shared-skills-registry-mcp A self-hosted registry and MCP server for reusable AI-agent skills that enables agents to discover, retrieve, and install skills with guardrails. | |
| GitLab MCP coboljunkie/gitlab-mcp Harness-neutral MCP server enabling GitLab repository workflows—merge requests, CI diagnosis, publishing, and variable management—through shared Agent Skills for Codex, Claude Code, Cline, Pi, and ChatGPT. | |
| ideahub_mcp cobrachickenai/ideahub_mcp An MCP server for capturing and recalling ideas, designed for both agents and humans. It provides tools for durable ideas, checkpoints, search, and deduplication. | |
| vndly-mcp coburn2716/vndly-mcp MCP server for VNDLY inventory and order management, enabling AI assistants to search products, list orders, and get low stock alerts. | |
| table-mountain-mcp cobus-meyer/table-mountain-mcp Enables agents to answer whether it's a good day to go up, hike, or take the cable car, and to rank the best day in the seven-day forecast using live weather, summit conditions, cable car status, and hours. It adds freshness warnings, out-o | |
| business-card-watchdog cochranresearchgroup/business-card-watchdog Business Card Watchdog is an installable, user-scoped service for processing large batches of business card images from watched folders. It exposes CLI, API, MCP, and watched-folder surfaces for deterministic orchestration and routing to Go | |
| mcp-binance-futures cociugv/mcp-binance-futures A Model Context Protocol (MCP) server that enables any compatible AI model to autonomously trade Binance USDT-margined perpetual futures. Includes a separate paper-trading strategy lab that requires no credentials. | |
| MCP Gateway cociweb/mcp-gateway Aggregates multiple upstream MCP servers (stdio, streamable-http, sse, websocket) behind a single streamable-HTTP endpoint with declarative configuration, namespacing, filtering, and auto-reload. | |
| AI OS MCP Server cockimitu-ops/ai-os-mcp1.0 Exposes a Notion-synced AI OS as read-only MCP tools, enabling MCP-compatible AI clients to search the vault, fetch page contents, list projects, and check project statuses without scraping public links. | |
| RunbookBridge coco-ari/runbook-bridge Enables AI assistants to perform operations on remote servers by reusing SSH sessions from a local desktop app, including command execution, file upload/download, and project document management with security controls. | |
| claude-discord-mcp coco-famihiro/claude-discord-mcp Enables Claude Code to interact with Discord servers, including sending messages, reading channels, managing threads, and adding reactions via natural language commands. | |
| mcp-context-hub coco4atjp/mcp-context-hub Enables managing multiple MCP servers through a fixed set of hub tools, with on-demand server startup, tool discovery, and skill retrieval. | |
| RuvLTRA MCP Server coco4atjp/ruvltra-mcp-server Enables parallel code generation and review via MCP with fault-tolerant worker pool, auto-scaling, and SONA self-improvement for robust LLM orchestration. | |
| worldmodel-mcp cocoabeans/worldmodel-mcp Provides an external, validated state database for LLM agents to manage long-horizon tasks, with tools for defining schemas, invariants, actions, procedures, and branching, preventing state drift and compounding errors. | |
| radio-browser-mcp cococolanosugar/radio-browser-mcp MCP server that enables natural language control of internet radio from Claude Code, with access to 30,000+ global stations, auto-playback via mpv, and a real-time status line with audio spectrum visualization. | |
| codescan cocodedk/codescan Enables querying a Neo4j-based code graph for Python projects, providing tools for code structure, call graph, and test coverage analysis. | |
| Microsoft Planner Task Creator MCP Server cocodedk/planner-task-creator-cli-mcp Enables AI assistants to create and manage Microsoft Planner tasks, including comments, subtasks, and bucket operations, via a Node.js MCP server wrapping a Python CLI. | |
| wechat-local-mcp cocohahaha/wechat-local-mcp A read-only MCP server that enables searching and extracting to-dos from local macOS WeChat chat databases. It decrypts and queries local WeChat data without sending messages or modifying databases. |
39,551–39,600 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.