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 |
|---|---|
| peptidecalc-mcp double2dev/peptidecalc-mcp Official MCP server for PeptideCalculatorOnline.com. Enables AI assistants (Claude/Cursor) to accurately calculate peptide reconstitution, molarity, and U-100 syringe units for research compounds. | |
| PindouAI MCP Server double2dev/pindou-mcp Enables AI assistants to interact with PindouAI for converting images into Perler bead patterns, pixel art blueprints, and accessing gallery creations and website URLs. | |
| srquiz-mcp double2dev/srquiz-mcp An MCP server providing science-based psychometric tools and sexual well-being assessments for AI agents. | |
| stitchmath-mcp double2dev/stitchmath-core Professional knitting and crochet math calculators that enable AI to design perfectly sized patterns. | |
| thenichegap-mcp double2dev/thenichegap-mcp Analyze real Google SERP data to uncover SEO content gaps and generate battle-ready content outlines — powered by TheNicheGap. | |
| audit-mcp-cli double527/audit-mcp-cli Lightweight Node.js dependency vulnerability audit tool with CLI and MCP Server modes. Supports npm/pnpm, full dependency chain tracing, remote GitHub repo auditing, and generates Markdown/HTML reports. | |
| Figma i18n MCP Server doublea411/figma-i18n-mcp Extracts text nodes from Figma designs and organizes them into structured JSON for internationalization workflows. It enables users to pull content from specific frames or entire files to automatically generate translation keys. | |
| Outlook MCP Server doublebash/outlook-mcp A Model Context Protocol server bridging Claude to Microsoft Outlook + Teams (email, calendar, contacts, tasks, files, Teams meeting recordings + transcripts), deployed on Cloudflare Workers. | |
| mihomo-ai-failover doublebearoliver-cyber/mihomo-ai-failover Provides AI-aware failover for Mihomo proxy on macOS by validating real OpenAI paths and switching proxy groups after verified hard failures. It offers a local stdio MCP server for diagnostics, status, and safe management of the AI proxy gr | |
| ava-mcp-server doublecore/mcp-server-ava Enables MCP clients to load and inspect datasets, run read-only SQL with DuckDB semantics, ask natural-language questions that are translated into SQL and summarized, and generate chart specs. It works with any MCP client and optionally use | |
| aiowhitebit-mcp doubledare704/aiowhitebit-mcp MCP server for WhiteBit cryptocurrency exchange API, enabling market data retrieval, order book access, and real-time WebSocket streams. | |
| potluck doublegremlin181/potluck Privacy-first personal knowledge database for your AI that ingests data exports (Google Takeout first) and exposes them via MCP tools like search and list items. Runs locally with no cloud or telemetry. | |
| zatca-mcp doubleh10/zatca-mcp An AI-native MCP server for Saudi e-invoicing that generates ZATCA-compliant invoices, QR codes, and XML from natural language, with validation and Phase 2 signing capabilities. | |
| comfyui-model-mcp doublehash/comfyui-model-mcp Enables agents to download single model weight files from Hugging Face repositories or Civitai model versions directly into allowlisted ComfyUI model folders. Source identifiers, destination categories, and file extensions are validated, an | |
| codegraph doublehead/codegraph Enables blast-radius enforcement for coding agents by building an AST call/dependency graph and injecting a symbol's callers into the agent's context at the moment it edits a file. | |
| Reel doublej/reel Enables an assistant to turn any video ffmpeg can read into a text transcript by extracting the audio, splitting it on silence, and transcribing each piece on-device through utt. Exposes tools to start a transcription job with optional hint | |
| REAL MCP doublerange/real-mcp Enables host agents to obtain authorized professional-role judgments, expressions, methods, and work results through remote or local stdio connectors, with user-approved roles, budgets, and deadlines. | |
| Typora MCP doublew2w/typora-mcp Enables inspecting, debugging, and safely automating a running Typora instance over local STDIO through an opt-in, reversible renderer bridge that exposes status and capability discovery, structured snapshots, DOM and style queries, short-l | |
| notos-mkr doubsumi/notos-mkr Enables local agents to control mouse and keyboard recording and replay over stdio, including start/stop, save/load, status, and clear operations. | |
| playwright-mcp-server doucej/playwright-mcp-server Stateful MCP server wrapping Playwright for browser automation. Provides tools to navigate, interact, and extract data from web pages via a persistent browser session. | |
| Calculator MCP Server doudou-fly/open-mcp Provides basic arithmetic operations (add, subtract, multiply, divide) through MCP, enabling AI clients to perform calculations via natural language. | |
| PT5 MCP Server doudoufu/pt5-mcp-server Enables parsing, analysis, and export of power measurement data from Monsoon Power Monitor PT5 files, including summary statistics, sample retrieval, trend analysis, and CSV export. | |
| my-portfolio-mcp doug-harrison/my-portfolio-mcp A FastMCP server packaged for easy installation into Dataiku code environments, enabling the addition and execution of MCP tools. | |
| WoW Armory MCP Server douganredhammer/wowarmorymcp Enables AI assistants to look up World of Warcraft character information and reputation from Blizzard's Armory website. | |
| binharness dougchansan/binharness Enables MCP clients to reverse-engineer binary files — hex viewing, disassembly, function/call-graph recovery, syscall and RTTI naming, string/xref search, and symbol export for Ghidra and IDA — across Switch NSO/NRO/NSP and many other form | |
| D365FO MCP Server dougdaley/d365fo-mcp Enables natural language interaction with Microsoft Dynamics 365 Finance & Operations, including entity discovery, CRUD operations, and a learning system that improves over time. | |
| Accounting Ledger MCP Server dougdaley/mcpaccountingdemo Provides double-entry accounting ledger creation, transaction recording, and financial reporting capabilities via MCP. | |
| QuantMCP dougdotcon/quantmcp A Model Context Protocol server that integrates with Amazon Braket, allowing AI assistants to access, control, and interpret results from quantum computing resources. | |
| Alexa, why? dougfirlabs/scholia-alexa-mcp Enables Alexa+ to record and verify why actions were taken, explain prior decisions, review subsequent changes, and retrieve retained tamper-evident decision chains. | |
| Luma Events MCP Server douglac/mcp-luma-events Enables users to search and discover upcoming tech events, conferences, and meetups from Luma (lu.ma) through natural language queries. Built on Cloudflare Workers for fast, global access to tech event data. | |
| footon douglance/footon Turns Claude and Codex JSONL transcripts into sanitized, unlisted links with explicit approval, exposing share management via OAuth-protected MCP endpoints. | |
| nutrs-mcp douglas-doca/nutrs-mcp MCP server for the NUTRS ecosystem, connecting Radar, Calendário, and Cardápio to Claude with tools for executive dashboards, calendar tasks, and menu proposals. | |
| Remote MCP Server for Cloudflare douglas-pc/mcp Allows deployment of a Model Context Protocol server on Cloudflare Workers without authentication requirements, enabling integration with Claude Desktop and AI Playground for tool augmentation. | |
| Turbular douglas16154/turbular Enables LLM agents to connect to and retrieve data from multiple database types through a unified API, including PostgreSQL, MySQL, SQLite, BigQuery, Oracle, MS SQL, and Redshift. It supports schema normalization and query transformation to | |
| DSH Crew douglas4958/dsh-crew Enables hosts like Claude Code, Codex, Antigravity and Grok to dispatch tasks to DeepSeek Harness agents while still showing them as native subagents with live progress, tier/effort presets, escalation, dispatch guardrails and a jobs board. | |
| Siri Shortcuts MCP Server douglas71/mcp-server-siri-shortcuts Enables LLMs to list, open, and run shortcuts from the macOS Shortcuts app, with dynamically generated per-shortcut tools and optional text or file input. | |
| mysql-mcp douglasaxel/mysql-mcp Enables AI assistants to interact with MySQL databases through a standardized interface, including executing SQL queries, listing databases and tables, and describing table structures. | |
| Calculator MCP Server douglasgbailey/claude-mcp-calculator Enables an LLM client to perform basic arithmetic on two numbers — addition, subtraction, multiplication, and division — plus reverse a supplied text string, through five simple tools exposed over stdio. Inputs and structured text results f | |
| teaching-mcp-server douglasgbailey/teaching-mcp-server Enables users to access local files, manage persistent notes via CRUD, fetch URLs, inspect system information, and analyze or transform text through MCP tools. | |
| Kabuzz MCP Server douglashardman/kabuzz-mcp-server Enables any MCP-compatible AI agent to browse, negotiate, purchase, message, and transact on the Kabuzz resale marketplace without writing REST integration code. | |
| MCP Finance Server douglashiga/mcp-finance-server Enables market data, fundamentals, screener analytics, options analytics, and Wheel strategy workflows with a local cached pipeline, defaulting to the Swedish market. | |
| secret-paste douglasjordan2/secret-paste Enables agents to request an API key or other secret from the user without the value passing through chat or tool arguments/results, storing it directly to .env, the OS keychain, or 1Password. The agent receives only metadata indicating whe | |
| Android Source Explorer douglasnascimento262/android-source-explorer-mcp Provides AI tools with on-demand, precise access to real AOSP framework and AndroidX source code, so they can search classes, extract exact method bodies with Javadoc, inspect inheritance hierarchies, and trace definitions and references ac | |
| mcp-server-http-streamable douglasqsantos/mcp-server-http-streamable A minimal Model Context Protocol server that facilitates network-based client connections using Streamable HTTP transport. It provides a greeting tool and is optimized for consistent deployment across local environments, Docker, and Kuberne | |
| wanderlog-mcp douglasreddy1991/wanderlog-mcp Enables Claude or any MCP-compatible agent to view and build Wanderlog trip itineraries through conversation, including adding and editing places, notes, hotels, transit, car rentals, checklists, expenses, sections, and guides. It also supp | |
| Email MCP Server douglasroux/email-mcp Enables AI assistants to read, search, send, reply, forward, schedule, and analyze email across multiple IMAP/SMTP accounts, with drafts, templates, provider-aware labels, bulk operations, attachment handling, calendar extraction, and real- | |
| Publer Gateway MCP dougm1966/publer-gateway-mcp One safe MCP doorway into every Publer workspace you manage. It provides workspace-aware social scheduling tools with preview and explicit approval workflows for teams managing multiple brands or clients. | |
| MegaBrain dougrn/mcp-megabrain Enables AI coding assistants to share persistent local memory across sessions and agents, so rules, mandatory specs, verified code snippets, and past mistakes are automatically surfaced before code is generated. It also lets agents log repe | |
| NotebookLM MCP Server dougrn/mcp-notebooklm Enables AI assistants and agents to connect directly to Google NotebookLM through its high-performance internal RPC calls. Provides grounded RAG chat with citations, notebook and source management (URLs, YouTube, Drive files, text), Audio O | |
| RadMail MCP dougsureel-tech/radmail-mcp An email operating system for AI agents that provides safe triage, drafting, and searching of emails with unbypassable hard-stops on money, banking changes, first-contact senders, and prompt injection. |
45,701–45,750 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.