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 |
|---|---|
| WinWright civyk-official/civyk-winwright civyk-winwright is a Playwright-style MCP server for Windows desktop and browser automation. It provides 59 tools for controlling WPF, WinForms, Win32 apps, and Chrome/Edge via the Model Context Protocol. A unified automation layer connecti | |
| jiminy cizambra/jiminy Serves a versioned constitution (mission and principles) over MCP as a coherence control plane for multi-agent systems, enabling agents to fetch the current direction and receive change notifications. | |
| Kyno cizambra/kyno A coherence control plane that provides a versioned source of truth for an agent system's mission and principles over MCP, enabling agents to pull the current direction and receive change notifications. | |
| tasks-mcp-poc cizar/tasks-mcp-poc A generic task manager (like Monday, Jira, Trello) with MCP as its only interface, enabling task and user management via natural language through Claude. | |
| claude-swarm cj-vana/claude-swarm Orchestrates parallel Claude Code worker swarms with protocol-based behavioral governance for multi-hour autonomous coding sessions. | |
| Discord Server Setup MCP cj-vana/discord-setup-mcp An automation tool for macOS that uses AppleScript and JXA to manage Discord server setups through AI assistants. It enables the creation and configuration of servers, channels, roles, and settings using pre-built templates or custom comman | |
| Langfuse Prompt Management MCP Server cjackson732/mcp-server-langfuse Enables users to list and retrieve Langfuse prompts, compile them with supplied variables, and expose prompt management capabilities to MCP clients. | |
| Project Manager MCP Server cjafet/mcp-project-manager Enables project management through natural language, allowing users to create, list, and update tasks with SQLite persistence, integrated with Claude Code and deployable over SSE. | |
| Snowflake Stored Procedure Integration cjaimesg/snowflake-mcp-sp-integration Enables execution of Snowflake stored procedures through the MCP server by providing a framework to define, manage, and call procedures from specific schemas or individual procedures. | |
| airlock cjaston/airlock MCP server that vets package installations and shell commands to block dangerous actions by AI coding agents. | |
| MCP Ask-to-Code cjaviersaldana/mcp-ask-to-code An autonomous MCP server that uses the Claude Code CLI to solve coding problems without permission prompts. | |
| Tic-tac-toe MCP Server cjayasur/mcp-tictactoe Enables ChatGPT and Claude users to play a turn-based game through an interactive board widget, with the server enforcing rules, validating moves, and tracking game state. | |
| Scalogy Real Estate Deals MCP Server cjcxyz/scalogy-real-estate-deals-mcp Enables AI agents to find vetted, daily-scored US residential real-estate investment deals with pay-per-request via USDC on Base. | |
| video2gif cjh0509code-png/mcp Enables users to convert video URLs into GIF images with customizable size, frame rate, time range, and looping, returning the GIF and a text summary to MCP clients. | |
| Mac MCP Bridge cjh1594/mac-mcp-bridge Enables MCP clients such as ChatGPT to execute shell commands, manage files, and view or capture images on Mac and Linux hosts. Supports terminal-based connection approval, time-limited access, and output controls. | |
| Aegis MCP Server cjh91577/enterprise-rag-agent Exposes standard MCP tools for secure calculation, knowledge-base retrieval, document statistics, and sensitive operations like email, export, and deletion with human-in-the-loop approval. | |
| clinicaltrialsgov-mcp-server cjimenez982/clinicaltrialsgov-mcp-server Enables searching the ClinicalTrials.gov registry of 600K+ studies, fetching full study records and posted results, discovering API field names and values, and matching patient demographics and conditions to candidate recruiting trials. Run | |
| coreldraw-vectorize-mcp cjjjqxx/coreldraw-vectorize-mcp Converts raster drawings such as diagrams, maps, charts, and scans into editable CorelDRAW vector files in a single call, with automatic self-checking that reports uncertain elements back to the calling AI for correction and rebuild. | |
| X(Twitter) MCP Server cjkcr/x-mcp Enables creating, managing, and publishing X/Twitter posts, threads, and replies directly through Claude chat. Supports draft management with the ability to create, list, publish, and delete tweet drafts. | |
| RateMySupervisor_MCP cjl196/ratemysupervisor_mcp An MCP server that provides access to supervisor evaluations and ratings from urfire.com, allowing users to query academic advisors by name, university, or department. It features intelligent fuzzy matching for supervisor names in both Chin | |
| jun-skills-hwpx-v2 cjlee-cmd/jun-skills-hwpx-v2 Unified MCP server for converting Markdown to HWPX documents or generating new HWPX files from templates while preserving formatting. | |
| OpenCTI MCP Server cjmateoo0221/opencti-campaign-indicator-automation-using-mcp Provides tools to interact with the OpenCTI platform, including checking if a campaign exists. | |
| Task Manager MCP Server cjmontgom/todo-mcp-server Enables local task management through the Model Context Protocol with tools for creating, updating, and deleting tasks. It also provides read-only resources for viewing task summaries and full task lists. | |
| detection-enabler cjohnston33/detection-enabler-mcp Enables AI agents to check whether Elastic Security detection rules will actually work in an environment by verifying data source, data freshness, field mappings, and alert volume, then filing enable requests. Requests take effect only afte | |
| open-db-mcp cjp1016/open-db-mcp A multi-database MCP server that enables LLM agents to safely access MySQL, Oracle, DM, PostgreSQL, and SQLite databases with security features like whitelist, row count pre-check, and audit logging. | |
| open-ssh-mcp cjp1016/open-ssh-mcp An MCP server for managing remote SSH servers, enabling AI agents to execute commands, transfer files, and perform deployment operations securely. | |
| power-db-mcp cjp1016/power-db-mcp A multi-database MCP tool that enables LLM agents to securely query and write to databases via local stdio, supporting MySQL, Oracle, PostgreSQL, DM, SQLite and more. | |
| cc-agent-router cjqkj/cc-agent-router Routes Claude Code tasks to different AI roles with separate APIs, keys, and models while preserving existing MCP, skills, and project settings. | |
| TaskPreset MCP cjsong97/taskpreset-mcp Enables AI assistants to apply productivity-system presets such as GTD, Kanban, Scrum, PARA, and OKR by capturing, querying, updating, completing, and planning tasks with enforced workflows, stored locally in a SQLite file the user owns. It | |
| MD-DOCX Converter cjwpenner/md-docx-converter Bidirectional Markdown ↔ Word (.docx) converter. Read Word documents directly into Claude as Markdown, or save Claude's output as a properly formatted .docx with heading styles (Title, Heading 1–9), bold, italic, tables, lists, code blocks, | |
| smart-hardware-bridge cjx0712/smart-hardware-bridge A unified MCP bridge server that lets WorkBuddy and any MCP client control real-world hardware over MQTT and HTTP — reading device state and sending commands through natural language, with a pluggable adapter layer for adding new protocols. | |
| AgentChat cjznb/agentchat Enables AI coding agents to join a chat-software-style collaboration hub as a hierarchy tree, where agent nodes exchange messages with blocking sends and four-level read receipts, pull inboxes, acknowledge reads, inspect the roster and conv | |
| hashline-mcp ck0i/hashline-mcp An MCP server for precise, hash-referenced file editing that enables atomic edits using line:hash references instead of fragile line numbers or full content reproduction. | |
| @cap-js/mcp-server ck1sap/mcp-server An MCP server for SAP CAP that provides fuzzy search over compiled CDS models and semantic search over CAP documentation, enabling AI-assisted development of CAP applications. | |
| AnJian Agent ck3938700-ship-it/anjian-agent A local-first, authorization-gated MCP server for web security assessment that transforms URLs into traceable, reviewable reports and integrates with Claude Code and local LLMs. | |
| kinqimen-mcp cka4913/qimen-mcp A deterministic MCP facts engine for Qimen Dunjia (奇門遁甲), providing 時家, 刻家, and 金函玉鏡 chart computation tools for AI agents. | |
| Archery MCP Server ckall/archery-mcp-server Enables AI agents to interact with the Archery SQL audit and query platform for submitting and managing SQL tickets, executing queries, and administering instances. | |
| PoomSchool MCP Server ckalswl26/poomschool-mcp Helps parents of multicultural or North Korean background primary school children translate and understand school notices, converting them into actionable tasks like preparing items and meeting deadlines. | |
| MCP Test DB Server ckamilokoo/mcp_template Enables interaction with a PostgreSQL database through MCP tools for employee management. Supports listing and adding employees via natural language chat interface with LLM integration. | |
| pycti-mcp ckane/pycti-mcp MCP server that provides condensed and normalized data from OpenCTI to LLMs, enabling lookup of observables, adversaries, and reports with enriched context. | |
| fake-store-mcp ckaraca/fake-store-mcp Provides AI assistants with access to the Fake Store API for e-commerce prototyping and testing, enabling queries on products, carts, and users. | |
| Korean DART MCP ckarlsson087/korean-dart-mcp Enables AI assistants to query Korea's OpenDART electronic disclosure system through 15 consolidated tools covering filings, financials, shareholding, and XBRL, with automatic full-statement parsing and calculation checks. It also converts | |
| pw-mcp ckarnell/pw-pool It enables each agent session to have its own isolated Chrome browser with a persistent profile, avoiding profile-lock conflicts and shared tab spaces, while resumed sessions reattach to the same browser and tabs. It can also seed new sessi | |
| portfolio-mcp ckc5800/portfolio-mcp Enables AI assistants to query the author's career, projects, publications, and technical documents through read-only MCP tools. | |
| solve-it cke-proto/mcp_solve-it MCP server that provides programmatic access to the SOLVE-IT digital forensics knowledge base, enabling LLMs to query, navigate, and search forensic techniques, weaknesses, mitigations, objectives, and citations. | |
| SOLVE-IT MCP Server cke-proto/solve_it_mcp Provides LLM access to the SOLVE-IT Digital Forensics Knowledge Base, enabling natural language exploration of investigation techniques, weaknesses, and mitigations. | |
| web-mcp-relay ckfun0skf/web-mcp-relay Bridges a selected browser tab's native WebMCP tools to remote MCP clients through a self-hosted Cloudflare Worker, enabling tool discovery and invocation with session-scoped authentication and per-page trust controls. | |
| cinii-mcp ckgerteis/cinii-mcp Enables querying Japan's national academic database, CiNii Research, for articles, books, dissertations, KAKEN projects, and researcher profiles via seven MCP tools. | |
| jstage-mcp ckgerteis/jstage-mcp Exposes J-STAGE WebAPI as four tools for searching articles, issues, journals, and resolving DOIs, returning bilingual JSON with attribution. | |
| korea-scholarship-mcp ckgerteis/korea-scholarship-mcp Exposes KCI and OAK Korean bibliographic services as MCP tools for searching, harvesting, and retrieving articles, references, and journal metrics. |
39,051–39,100 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.