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 |
|---|---|
| DART-MCP 2geonhyup/dart-mcp-test An MCP server that enables Claude to perform financial analysis and visualization of Korean listed companies using the DART API. It supports detailed financial metrics, business unit sales breakdowns, and company comparisons for KOSPI and K | |
| evidence-sieve 2gg-bit/evidence-sieve Provides MCP tools to search local document corpora with conservative semantic deduplication, source retention, and version/scope filtering, returning compact evidence packets with original passages and source IDs for agents. | |
| 2hr-jobs-mcp-server 2hr-pl/2hr-jobs-mcp-server MCP server for Polish IT job board 2hr.pl, enabling job search, salary analysis, and market analytics via natural language. | |
| MCP Server Template (Python) 2k92gzzsyc-hash/mcp-server-python-mtef0f9z This template enables developers to quickly scaffold, deploy, and extend a Model Context Protocol server on Render, with bearer-token authentication and a streamable HTTP endpoint, by adding custom tools via Python. | |
| MCP Server Template (Python) 2k92gzzsyc-hash/mcp-server-python-mtef1ly7 Enables deploying a minimal MCP server on Render with Streamable HTTP transport, bearer-token authentication, a health check endpoint, and a sample tool. | |
| Claude MCP Server 2lab-ai/claude-mcp-server A Model Context Protocol (MCP) server that provides a bridge to Anthropic's Claude CLI. It allows MCP-compliant clients like Claude Desktop or Gemini to start new chat sessions or continue existing ones. | |
| @mempalace/mcp-dev 2loch-ness6/mempalace-mcp-dev Enables AI coding assistants to access grounded, branch-scoped codebase context via semantic search, git tracking, change ledger, and structured feature management with Project Tracks. | |
| loop-mcp 2mattias/loop-mcp Enables reading, listing, creating, and editing Microsoft Loop pages as Markdown through browser automation. | |
| mcp-ops 2moulin/mcp-ops Provides read-only access to multiple production services with unified status and timeline tools for cross-service monitoring and diagnostics. | |
| qrcode generator 2niuhe/qrcode_mcp mcp tool to generate qrcode | |
| Pigeon MCP Server 2nspired/pigeon A kanban board MCP server that enables AI agents to read and write project boards through session loops, with built-in cost tracking and local-first storage. | |
| Planslurpen MCP Server 2re1million/planslurpen_mcp Enables interaction with Planslurpen, a Norwegian service that uses AI to interpret zoning and regulation plans. Supports retrieving plan data, looking up plans by property address, downloading plan provisions, and filtering structured plan | |
| 2slides MCP Server 2slides/mcp-2slides Enables users to generate presentation slides using 2slides.com's API through Claude Desktop. Supports searching for slide themes, generating slides from text input, and monitoring job status for slide creation. | |
| brain-mcp 2soum/brain-blueprint Enables coding agents to keep durable long-term memory in a folder of human-readable Markdown notes: search and read notes by ranked recall, encode new ones, link related ideas, retire contradicted notes in favor of replacements, and re-val | |
| Enhanced Image Analysis MCP Server 2squirrelsai/local-mcp-image-analysis-server Enables intelligent analysis and organization of image collections with smart filename generation, metadata extraction, and automated folder organization. Supports batch processing, color analysis, EXIF data extraction, and multiple naming | |
| dev-chrome-monitor 2sslgetlool/-dev-chrome-monitor Enables interaction with Chromium browser instances through Puppeteer for inspecting dev builds, capturing screenshots, and automating UI interactions. Features permission-gated tools for secure browser navigation, DOM manipulation, and Jav | |
| TrueSearchMCP 2sulraw/truesearchmcp Enables Google and YouTube search and YouTube video data extraction using real browser cookies, with no API keys required. | |
| Agent Hub 2tees-cloud/agent-hub-mcp Enables AI sessions like Claude, Cowork, and Claude Code to pass tasks and replies between each other through per-session mailboxes, and to keep a shared knowledge base of notes that every session can read, search, and update. Runs as a sel | |
| 2Xapi.com GPT-image MCP Server 2xapi/2xapi.com-gpt-image-mcp-server Wraps OpenAI-compatible text-to-image APIs as MCP tools, enabling image generation directly from conversations in Claude Code, Codex, Cursor, or Claude Desktop using the user's own API key. | |
| Islamic Content MCP Server 2yousefreda/islamic-content-mcp Connects AI assistants to authentic Islamic content including Qur'an, Hadith, and resources in multiple languages via over 80 tools. | |
| exec-mcp 3011/exec-mcp Enables executing a single bounded remote shell command on a configured host, returning truncated stdout/stderr tails and an authoritative exec summary. | |
| ipynb-mcp 3021244161/ipynb-mcp Enables AI agents to safely read, edit, and execute local Jupyter notebooks without running a separate service. Edits are guarded by compare-and-swap hashes and execution resumes or replays kernel state, so long-running cells aren't needles | |
| 302AI BrowserUse MCP Server 302ai/302_browser_use_mcp A Model Context Protocol server that enables Claude Desktop to browse the web, likely allowing the AI to access and interact with web content. | |
| 302AI File Parser MCP Server 302ai/302_file_parser_mcp An MCP server that parses files for Claude Desktop, requiring a 302AI API key for operation. | |
| 302AI Sandbox MCP Server 302ai/302_sandbox_mcp A Model Context Protocol (MCP) server for Claude Desktop that connects to 302AI's API services, allowing users to integrate and leverage 302AI capabilities through a structured communication interface. | |
| 302AI Web Search MCP 302ai/302_web_search_mcp Enables web search functionality via the 302AI API. | |
| knowledgine 3062-in-zamud/knowledgine Local-first MCP server that extracts structured knowledge from markdown notes into SQLite with full-text search, enabling AI coding tools to retrieve relevant context offline at zero cost. | |
| Canvas AIGC 3108482409song-commits/canvas-aigc-mcp A MCP server that bridges web canvas with local Codex/Claude, exposing 23 tools for reading, creating, modifying, connecting, and generating canvas content via local HTTP bridge and stdio MCP. | |
| isaac-wiki-mcp 3113y/isaac-wiki-mcp Provides full class documentation for the Binding of Isaac modding API, enabling AI assistants to access complete class pages with methods, enums, and tutorials to avoid hallucination. | |
| arena-mcp 312-dev/arena-mcp MCP server for Are.na that lets AI assistants create channels, save blocks from any URL or markdown, browse channels, and search content. | |
| navidrome-mcp 312-dev/navidrome-mcp Enables building mood-based playlists for Navidrome by joining your library, listen history, and personal playlist labels from Navidrome, ListenBrainz, and Last.fm. | |
| rocketmoney-mcp 312-dev/rocketmoney-mcp Read-only MCP server for Rocket Money that lets you browse your accounts, transactions, spending, budgets, net worth, and subscriptions through natural language. | |
| sophtron-mcp 312-dev/sophtron-mcp Query bank accounts, credit cards, and transactions via Sophtron's financial data API. Works with Claude Desktop and any MCP-compatible client. | |
| steam-mcp 312-dev/steam-mcp Enables personalized Steam game discovery by ranking the store against a player's playtime history and stated preferences, with tools to search games, inspect details and reviews, and explore taste profiles. | |
| xbox-mcp 312-dev/xbox-mcp Enables to query Xbox Live profiles, current games, recent games, and activity for any Xbox player using the OpenXBL API. Supports gamertag resolution and provides rich presence details. | |
| deepseek-agents 3132882323-cyber/codex-deepseek-collab Enables Codex to delegate separable work to DeepSeek Flash/Pro agents through start, continue, status, and cancel tools, while Codex retains tool execution, authorization, and final verification. | |
| Codex Agent Orchestrator MCP 3135804887-ops/codex-agent-orchestrator-mcp A local MCP control plane for Codex that manages task queues, dynamic roles, and side-panel team collaboration with persistence, dependency gating, and structured reporting. | |
| corporate-mcp-system-inspector 313on/corporatemcp Enables observation-only system inspection through MCP, exposing system identity, resources, process summary, and network summary without any mutation or command execution. | |
| proton-read-mcp 314159dd/proton-read-mcp Enables Claude to read-only browse, search, and fetch emails from a Proton Mail inbox through Proton Bridge IMAP, with no capabilities to send, move, flag, or delete. | |
| prompt-to-scene 316sandon12/prompt-to-scene Enables an MCP-compatible AI client to author Blender Python, run Blender, import the resulting asset into Unity with materials and a prefab, place it in the active scene, verify the import, and revise the same asset using stable IDs. | |
| 3dsmax-mcp 317431629/3dsmaxmcp Enables AI assistants to directly control Autodesk 3ds Max through natural language to create models, set materials, adjust lighting, and automate animations. It bridges the Model Context Protocol with 3ds Max via a TCP socket to execute Py | |
| deepseek-local-harness 3192673546/deepseek-local-harness Enables supervised PowerShell execution on Windows, allowing the DeepSeek agent to run local commands and manage files safely through a single tool. | |
| IDA Pro MCP Server 31benzi/ida-pro-mcp Bridges Claude Code with IDA Pro 9.0+ to provide 87 tools for AI-assisted reverse engineering, including decompilation, navigation, debugging, and patching. | |
| inventory-mcp 320432893-cell/inventory-mcp Enables agents to query and manage inventory data from Feishu source tables, providing tools for stock checks, distribution analysis, alternatives, and weekly ledger updates. | |
| WhatConverts MCP Server 321webmarketing/whatconverts-mcp-server Connects Claude to the WhatConverts API, enabling management of leads, accounts, profiles, tracking numbers, and recordings through natural language. | |
| local-agent-mcp 3230390742/local-agent-mcp A local MCP server that lets Claude Code orchestrate Codex CLI and OpenCode CLI as sub-agents with strict security, concurrency, and output limits. | |
| Enterprise-MCP 3237160043lzy-sudo/mcp An MCP server providing calculator and file system tools, enabling AI agents to perform mathematical calculations and file operations. | |
| mcp-mysql-apifox 327100395/mcp-mysql-apifox MCP server for executing MySQL SQL, managing Apifox API documentation, and parsing/executing curl commands. | |
| cubrid-mcp-server 3281831403/gsb_cubrid_config_sql_01 Enables LLMs to safely inspect CUBRID database schemas and execute read-only queries, with opt-in support for single-statement writes. | |
| Israeli Weather MCP Agent 328gili/weather-chat-mcp Enables LLMs to retrieve Israeli weather forecasts by controlling a browser via Playwright and scraping data from an Israeli weather website. |
22,051–22,100 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.