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 |
|---|---|
| civnode-mcp christerso/civnode-mcp An MCP server for the CivNode 'slow web' social platform that enables interaction with monuments, forums, and creative writing. It allows users to manage their profiles, send private or anonymous messages, and engage with the community's un | |
| ios-device-mcp christhoma/ios-device-mcp Enables controlling a real iPhone or iPad over USB for app development testing, including building and installing apps, launching with console logs, inspecting the accessibility tree, tapping, swiping, typing, taking screenshots, managing a | |
| Kleinanzeigen MCP christi-ko/kleinanzeigen-mcp Enables read-only access to Kleinanzeigen.de listings, including compact search, listing details, availability checks, and route calculations with optional distance and driving information. | |
| Receipts Compliance MCP christiaan839-beep/receipts-compliance-mcp Enables offline verification of Ed25519-signed AI-agent receipt bundles and turns them into auditor-ready Markdown evidence reports covering EU AI Act Annex IV, ISO/IEC 42001, ISO/IEC 23894, NIST AI RMF, SOC 2, GDPR, HIPAA and the EU CRA. A | |
| receipts-compliance-mcp-mit christiaan839-beep/receipts-compliance-mcp-mit Enables offline verification of signed AI-agent receipt bundles and generation of auditor-ready Markdown compliance reports for frameworks including EU AI Act Annex IV, ISO/IEC 42001, NIST AI RMF, SOC 2, GDPR, HIPAA, and EU CRA. | |
| CarryFeed christian-beep383/carryfeed-agent-tools CarryFeed lets AI agents resolve public X/Twitter profiles, posts, article-style links, and media metadata without browser login flows. It exposes source-preserving tools for public post text, author context, image/video/GIF candidates, pro | |
| ComfyUI MCP Server christian-byrne/comfy-mcp Enables AI agents to manage ComfyUI workflows using a human-readable Domain Specific Language (DSL), with automatic conversion to/from JSON format. Supports workflow creation, validation, execution, and monitoring through natural language i | |
| MCP Maven Server christian-carminati/mcp-maven-server Wraps Maven and Spring Boot operations for Claude Code, providing structured JSON output instead of raw build logs to save tokens and focus on code fixes. | |
| FastAPI MCP Application christian-felipe9/mcp-api A REST API built with FastAPI that exposes endpoints via Model Context Protocol (MCP), allowing clients to interact with CRUD operations through MCP interfaces. | |
| obsidian-mcp-pro christian-german/obsidian-mcp-pro Provides AI agents with comprehensive access to Obsidian vaults, enabling reading, writing, searching, tagging, linking, canvas manipulation, and semantic search through 41 tools. | |
| scb-mcp christian-gregorcik/scb-mcp Enables assistants to search, count, and read Swedish workplaces and legal entities from Statistics Sweden's business register, handling pagination, filters, and API authentication transparently. | |
| MCP Auth Server christian-posta/mcp-auth-step-by-step A Model Context Protocol (MCP) server with HTTP transport that implements JWT authentication, allowing secure tool execution and prompt handling with role-based access control. | |
| mcp-amazon-sp-api christian-ramos/mcp-amazon-sp-api MCP server that exposes the Amazon Selling Partner API to Claude Desktop and any other MCP client. It wraps the python-amazon-sp-api SDK and ships 55+ tools across 19 SP-API scopes with automatic pagination, throttle-aware retry and multi-m | |
| daylens-mcp christian-tonny/daylens-mcp Connects AI assistants like Cursor and Claude to your local Daylens timeline so they can answer questions about your past work sessions, no cloud or API keys needed. | |
| agent-invariants christian140903-sudo/agent-invariants A deterministic behavior-compatibility layer for AI agents that checks normalized event traces against operating contracts and compares baselines with candidates to catch regressions in approval, stop, scope, recovery, and completion rules. | |
| behaviorlock christian140903-sudo/behaviorlock Behaviorlock is a deterministic compatibility gate for observable AI-agent behavior, enabling comparison of baseline and candidate traces to enforce declared behavior contracts. | |
| Postcondition christian140903-sudo/postcondition-mcp An MCP server that checks whether the world changed after a tool call by declaring observable outcomes, verifying them with read-only verifiers, and keeping hash-chained receipts. | |
| proofspec christian140903-sudo/proofspec Enables defining and verifying evidence contracts for claims in READMEs, releases, or product pages using constrained verifiers and generating hash-chained receipts and reports. | |
| Gel Database MCP Server christian561/gel-mcp-server A TypeScript-based MCP server that enables LLM agents to interact with Gel databases through natural language, providing tools to learn database schemas, validate and execute EdgeQL queries. | |
| nextmove-mcp christianalares/nextmove-mcp Analyzes your repository and suggests the next tasks to work on, presented as numbered options with context, enabling immediate action. | |
| horizon-mcp-demo christianashworth/horizon-mcp-demo Exposes a governed semantic layer built on dbt Core and DuckDB, enabling AI agents to query predefined metric definitions for a P&C insurance dataset. Prevents metric hallucination by restricting agents to governed tools and read-only data | |
| horizon-predictive-model-mcp christianashworth/horizon-mcp-demo-extended Exposes a professional services pipeline prediction model with tools to score opportunities, validate inputs, and retrieve model metadata such as win probability, fees, and margin. | |
| horizon-mcp-demo-extended-v2 christianashworth/horizon-mcp-demo-extended-v2 A demo MCP server with two governed systems (pipeline semantic layer and predictive model) for querying and scoring professional services opportunities with cross-system governance. | |
| imessage christianblandford/imbridge Enables MCP clients to send, receive, and react to iMessage texts on macOS, including inline replies and any-emoji tapbacks, with per-chat allowlisting and rate limits. | |
| label-printer-mcp christianblandford/label-printer-mcp Enables an assistant to locate a 4x6 shipping label within a PDF, crop to it losslessly without resampling, verify its true size, preview it, list print queues, and send it to a thermal printer at exactly 100%. All printing stays a dry run | |
| geonode-mcp christianbraun/geonode-mcp Enables AI assistants to search and manage GeoNode resources via natural language, including metadata editing, permission changes, uploads, and ownership transfers, all under the acting user's own permissions. | |
| Remote MCP Server on Cloudflare christianchiarulli/remote-mcp-server A template for deploying secure Model Context Protocol servers to Cloudflare Workers with built-in OAuth authentication. It enables hosting and connecting remote tools to Claude Desktop using SSE transport and a local proxy. | |
| snowflake-mcp-server christianclaudio/mcp-server-snowflake Enables AI agents to connect to Snowflake Data Cloud and Cortex AI for executing SQL, managing warehouses, tables, pipelines, governance, and AI-powered operations through a comprehensive set of enterprise-grade tools. | |
| onenote-mcp christiancruger/onenote-mcp Enables Claude to read local OneNote notebooks via the Windows desktop COM API, including text from pasted screenshots, while keeping all data on the machine. | |
| requ christiandrochon/requ-mcp Gives AI agents structured tools to maintain a living requirements traceability graph — requirements to user stories, cucumber scenarios, screens and phase results — so coverage and its trend across releases can be queried on demand and exp | |
| org-roam-mcp christiangeng/org-roam-mcp Enables AI agents to search notes, read full node files, trace backlinks, shortest paths and shared neighbours, and rank importance or topic clusters with graph algorithms, all by querying the knowledge graph's SQLite database directly with | |
| yahoo-finance-mcp-server christiangrogers/yahoo-finance-mcp-server An MCP server that exposes comprehensive Yahoo Finance data (quotes, financials, options, news, and more) to AI agents via the yfinance library, requiring no API key. | |
| kicktipp-agent christianheidorn/kicktipp-agent MCP server for kicktipp.com that enables AI assistants to view match data, leaderboards, and place bets through natural language. | |
| state-blueprint-mcp christianhohlfeld/digitalisierungsplanung.de Enables automation and external tool interaction with a digital business process model through structured API tools for model editing, validation, and export. | |
| Sector Pulse christianhonap7-sys/sector-pulse-mcp Live US sector rotation for agents: 30 US equity sector baskets ranked by average move every session, versioned basket rosters, and a daily close record since July 2026 that is never backfilled. Hosted MCP server (Streamable HTTP); this rep | |
| schema-viz christianhoustonfloyd/schema-viz-mcp A local MCP server that renders a database schema as an interactive, dbdiagram.io-style ER diagram in your browser. | |
| Weather MCP Server christiankowalczyk/weather-mcp Provides real-time weather updates and city geocoding by integrating the Nominatim and Open-Meteo APIs. It enables users to retrieve current weather conditions for any location through natural language queries in MCP-compatible clients. | |
| mcp-image christiankumar0483/mcp-image Enables AI assistants in any MCP client to generate new images or edit existing ones by turning short requests into detailed prompts with configurable quality presets. Supports Gemini, OpenAI GPT Image, and BytePlus Seedream providers, savi | |
| MiniMax Coding Plan MCP christianli2964/minimax-coding-plan-mcp Enables MCP clients such as Claude Desktop, Cursor, and Windsurf to run AI-powered web searches and analyze images from URLs or local files through MiniMax's coding-plan APIs. It exposes web_search and understand_image tools to support code | |
| eval-mcp-server christianmacion/eval-mcp-server Exposes a deterministic AI-slop scanner and RAG grounding grader as MCP Tools, Resource, and Prompt, enabling any MCP client to evaluate text quality and context faithfulness. | |
| remus-mcp christianmz565/remus-mcp Enables interaction with REMUS Jet databases through the MCP protocol, supporting local stdio and remote HTTP/SSE transports for database operations and project management. | |
| Octopus Deploy MCP Server christiannakamura/mcp-server Connects AI assistants to an Octopus instance so they can inspect, query, and diagnose deployments, projects, releases, runbooks, tasks, tenants, targets, and other resources, and optionally create releases, trigger deployments, run runbook | |
| threatintel-mcp christianpresley/threatintel-mcp An MCP server wrapping urlscan.io and VirusTotal APIs to enable AI agents to pivot on threat indicators during investigations, with compact structured output and defanged results. | |
| starc-mcp christianrhf/starc-mcp Enables LLM agents to read and write Story Architect (.starc) project files, including scripts, scenes, statistics, and character/location data. | |
| mellos-mapping christianrobinson31/mellos-mapping Enables an AI coding agent to declare a layered dependency structure as ghost nodes and then turn those nodes solid as they are built and verified, keeping the design, current attention, and any cracked foundations visible in a live termina | |
| CyberChef MCP Server christianwengert/mcp_cyberchef Enables AI agents to discover, execute, and validate CyberChef operations for data encoding, decoding, encryption, and transformation tasks. Provides structured access to CyberChef's extensive catalog of data manipulation tools through natu | |
| gdocs-mcp-server christinak44/gdocs-mcp-server Enables reading, editing, and rewriting Google Docs documents with tools that support full content replacement, appending, heading-based insertion, and style-preserving rewrites. | |
| S&P 500 MCP Server christinam269/sp500-mcp-server Enables querying of S&P 500 company data from Supabase, including fundamentals, annual financial metrics, historical price data, news sentiment, executive officers, and SEC filings. Also supports ambiguous-symbol resolution through elicitat | |
| Stock SDK MCP Server christinam55551/stock-sdk-mcp Enables AI assistants to retrieve and analyze multi-market stock data, including real-time quotes, K-lines, technical indicators, sector and futures/options information, and to perform screening, comparison, and market overview workflows th | |
| mcp-image christinarodriguez016/mcp-image Enables generating and editing images from MCP clients with automatic prompt optimization and quality presets, using Gemini, OpenAI, or BytePlus Seedream and saving results to disk. |
38,701–38,750 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.