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 |
|---|---|
| Baton MCP Server euuuuuuan/baton-public Enables bounded agent authority over a macOS workstation via 63 MCP tools with policy, approval, and audit. | |
| crm-mcp-agent euuuuuuan/crm-mcp-agent-public An MCP server that allows agents to perform CRM segment and campaign queries, with a governance kernel controlling write operations for safety. | |
| mcp-server-starter euuuuuuan/mcp-server-starter A minimal MCP server template exposing echo and word_count tools, serving as a scaffold for building custom MCP tools. | |
| ReasonForge euuuuuuan/reasonforge-public Provides 8 MCP tools for deterministic, read-only reasoning: intake, routing, planning, rubric, sweep checklist, verdict gate, reflection, and evaluation. It forces scope locks, disconfirmation-first plans, blind-spot sweeps, and evidence-g | |
| mcp-shellcheck ev3lynx727/mcp-shellcheck MCP server that provides shell script linting via ShellCheck. Allows AI agents to analyze shell scripts for common errors, stylistic issues, and potential bugs. | |
| server-commands-rtk ev3lynx727/server-commands-rtk MCP server for executing shell commands with automatic RTK token reduction, persistent caching, and execution logging. | |
| MCP ETC Nomad eva-akselrad/mcp-etc-nomad Enables LLM control of ETC Eos Family lighting consoles via OSC, allowing operation of cues, levels, subs, macros, and the full Eos command line. | |
| Windows Automation MCP Server eva-wanxin-git/windows-automation-mcp Provides comprehensive Windows system control including file operations, process management, window control, screenshots, clipboard access, PowerShell/CMD execution, and optional mouse/keyboard automation and browser control capabilities. | |
| Joplin MCP Server eva042/joplin-mcp Enables AI assistants to browse, search, create, edit, tag, organize, import, and restore notes and notebooks in a Joplin note-taking app via a standardized MCP interface, with optional notebook allowlisting. | |
| Gate22 eva32413/gate22 Enables teams to govern agent tool access with function-level allow-lists, credential modes, and audited execution, while exposing permitted MCP tools through a unified endpoint with search and execute functions. | |
| faststack-mcp evaan-devlops/faststack-mcp Local-first, read-only MCP server for Claude Code that indexes and searches full-stack projects (FastAPI + React + PostgreSQL) with SQLite-backed FTS, cross-reference graph, and file-watcher auto-reload. | |
| BigQuery MCP server evaaraujo329/mcp-server-bigquery Enables LLMs to inspect schemas, list and describe tables, and execute SQL queries against configured datasets. | |
| onemap8-mcp evallgar/onemap8-mcp MCP server that exposes OneMap8 fleet tracking to AI clients, enabling natural-language queries about devices, positions, reports, geofences, drivers, and more. Includes 32 tools, permission scoping, and safety guardrails. | |
| Deliberate Reasoning Engine evalops/deliberate-reasoning-engine An MCP server that structures AI reasoning as directed acyclic graphs of semantic thoughts, enabling explicit dependencies, assumption tracking, and cascade invalidation for transparent decision-making. | |
| MCP Webcam Server evalstate/mcp-webcam Enables users to send live webcam images to Claude Desktop or other MCP clients, facilitating interaction through capturing images, screenshots, and providing a webcam view for visual input. | |
| WebRead MCP evalvis/webreadmcp Enables AI assistants to read webpages and perform web searches using DuckDuckGo. | |
| Langfuse MCP Server evam6662/langfuse-mcp Enables AI agents to query and debug Langfuse traces, sessions, and exceptions locally, with route-decision tools, metrics, prompt and dataset access, plus compact or file-dump output for token control. | |
| Universal Email MCP Server evamardin/email-mcp Enables AI to send and receive emails via SMTP/IMAP, supporting auto-configuration for major email providers like QQ, 163, Gmail, Outlook, and enterprise mail. | |
| Igloo MCP evan-kim2028/igloo-mcp Enables AI assistants to interact with Snowflake databases through SQL queries, table previews, and metadata operations. Features built-in safety checks that block destructive operations and intelligent error handling optimized for AI workf | |
| preset-mcp evan-kim2028/preset-mcp MCP server for Preset (managed Apache Superset). Manage dashboards, charts, and datasets from Claude Code and other LLM agents. | |
| Spice MCP evan-kim2028/spice-mcp Enables querying and analyzing blockchain data from Dune Analytics with Polars-optimized workflows, including schema discovery, Sui package exploration, and query management through natural language. | |
| skope evan-moon/skope A personal news lens MCP server that uses Claude's web search to find articles relevant to your life, scoring them by causal reachability and providing a brief while tracking your attention concentration. | |
| kalshi evan-thedev/kalshi Enables AI agents to read Kalshi prediction market data, manage portfolios, and place or cancel trades only with explicit user approval. | |
| eyebrowse evan108108/eyebrowse Eyebrowse is an MCP server that gives AI agents eyes and hands in your real Chrome browser, allowing them to see screenshots, read page structure, and interact with pages like clicking, typing, scrolling, and navigating. | |
| PCILeech MCP Server evan7198/mcp_server_pcileech Enables AI assistants to perform DMA-based memory operations through PCILeech hardware using natural language commands, supporting memory reading, writing, and multi-format visualization for debugging and security research. | |
| Canvas LMS MCP Server evanap003300/canvas-mcp Connects Claude to Canvas LMS accounts, enabling natural language queries about courses, assignments, grades, and files. Supports content search, file downloads, syllabus retrieval, and bulk course exports via 13 integrated tools. | |
| MCP OpenAI Tools evandavid1/mcp-openai-tools Provides access to OpenAI's advanced models (including o3) with integrated web search, Python code interpreter, and combined analysis capabilities. Enables users to perform web searches, execute code in sandboxed environments, and combine s | |
| WhatsApp Business MCP Server evandroschechtel/mcp-whatsapp Connects AI agents to the WhatsApp Business Cloud API, allowing them to send messages, manage templates, and retrieve account analytics. It facilitates automated customer interaction and marketing campaign management through the Model Conte | |
| Beach Safety MCP evanfoglia/beach-safety-mcp Beach Safety MCP — comprehensive beach and surf conditions for any beach worldwide: waves, swell, wind, air and water temperature, UV index, rip current risk, and a 1-10 safety score. No API keys needed. Python, stdio transport. | |
| Wikipedia MCP evanfoglia/wikipedia-mcp Wikipedia MCP server (read-only): search articles, read plain-language summaries or full text, follow links, browse categories, pull references with source URLs, flag missing citations, resolve disambiguation pages, and check revision histo | |
| Personal MCP Server evangstav/personal-mcp A Model Context Protocol server for tracking personal health and well-being, offering tools for workout logging, nutrition management, and daily journaling with AI-assisted analysis integration. | |
| Memory MCP Server evangstav/python-memory-mcp-server Provides knowledge graph functionality for managing entities, relations, and observations in memory with strict validation rules to maintain data consistency. | |
| IB MCP Server evanikolaidis/ib_mcp Enables MCP clients such as VS Code Copilot to interact with Interactive Brokers' official Web API through a self-hosted, containerized streamable-HTTP endpoint, covering brokerage session authentication, account management, and trading end | |
| AetherEdge evanl1/aetheredge Exposes a deterministic IoT edge runtime — Modbus/CAN/J1939 acquisition, local rules, alarms, and history — to AI assistants as typed, governed MCP tools. Reads are safe by default; device control stays deny-by-default, explicitly confirmed | |
| Fetch MCP Server evanlouie/mcp-fetch Enables LLMs to fetch and extract web content as markdown with browser impersonation to bypass basic bot detection. | |
| Music MCP Server evanmyt/xiaozhi-music-mcp Provides music search, playback control, volume adjustment, and playlist management for XiaoZhi AI through MCP protocol. | |
| readwise-mcp evanoman/readwise-mcp Exposes Readwise and Reader operations as MCP tools, enabling AI agents to save URLs, search documents, retrieve full content and highlights, and manage tags and locations. | |
| fireflies-mcp evans-sam/fireflies-mcp MCP server and CLI for Fireflies.ai API to retrieve transcripts, search meetings, and generate summaries. | |
| urban-forestry-mcp evans885-forester/urban-forestry-mcp Enables municipal tree inventory management, work order tracking, canopy analysis, and GIS boundary queries via 15 MCP tools. | |
| snw-derived-mcp evansener/snw-derived-mcp Enables external agents to define and execute read-only derived properties over an ontology by analyzing field requests, validating link cardinality, and generating Semantic Join SQL within a three-hop neighborhood. | |
| OpenFGA MCP evansims/openfga-mcp An experimental Model Context Protocol server that enables Large Language Models to read, search, and manipulate OpenFGA authorization stores, unlocking fine-grained access control for agentic AI and natural language interactions. | |
| Spotify MCP Server evanslr/spotify-mcp Enables control of Spotify playback through OAuth authentication, including play/pause, track navigation, volume control, device management, and searching/playing songs by artist or track name. | |
| picoclaw-mcp-server evansxm/picoclaw-mcp-server Enables browser automation with stealth features, GitHub integration, and persistent opencode repository access through MCP tools. | |
| membot evantahler/membot Provides a persistent, versioned, and searchable context store for AI agents with local embedding and hybrid search. | |
| thirsty-tokens evanwang810/thirsty-tokens Estimates data-center water consumption from local Claude Code transcripts, providing water usage summaries, breakdowns by model/project, and a compact HTML widget. | |
| clio-mcp evanwillistech/clio-mcp A Model Context Protocol server that enables Claude (or any MCP client) to read and write Clio Manage data—contacts, matters, activities—directly from chat, with flat-fee billing support in one call. | |
| iris-weather-mcp evarness-ai/evarness-weather-mcp Serves Open-Meteo weather forecasts from a standalone stdio MCP process, letting any MCP client fetch forecast data without importing the harness into the plugin process. It pairs this with a comparison suite that measures in-process plugin | |
| Outlook Classic MCP server evarnild/outlook-classic-mcp-server Enables Claude to read and search mail in local Outlook classic via COM, and to create new draft, reply, and reply-all drafts for the user to review and send. It exposes no send, delete, or move capability, so messages can only be examined | |
| evav-gateway evavai/evav-gateway Governed MCP gateway that lets AI agents call tools with policy enforcement, prompt-injection screening, a kill-switch, and tamper-evident signed audit logs. | |
| cf-agent-mail evcatalyst/cf-agent-mail Enables software agents to read and manage their own mailboxes, inspect inbound messages, and request outbound email that remains pending until an owner approves it. Exposes these agent mail operations as remote MCP tools alongside a REST A |
48,901–48,950 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.