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 |
|---|---|
| @ai-solutions.ru/mikrotik-mcp-server ai-solutions-ru/mikrotik-mcp-server High-performance TypeScript MCP server for MikroTik RouterOS management, enabling Claude, GPT-4, or any MCP-compatible AI to manage routers through natural language with dynamic API discovery, VPN management, and configuration backup. | |
| DAPA MCP ai-studying-man/dapa-mcp Enables read-only search and retrieval of Korean defense acquisition statutes, administrative rules, precedents, and DAPA organizational/policy knowledge, with source verification and citation checking. | |
| Grep App MCP Server ai-tools-all/grep_app_mcp Enables powerful code search across millions of public GitHub repositories using grep.app API, with capabilities to discover code examples, retrieve specific files, and batch fetch multiple files for learning from open source projects. | |
| LLMMcp ai-v5/llmmcp Enables agents to run Google-first web searches with Bing and Google News fallbacks, and to fetch web pages as markdown, text, or raw HTML through an enterprise proxy with corporate TLS validation. Provides proxy, TLS, browser, and connecti | |
| DeepWiki MCP Server ai-vivid/deepwiki-mcp Enables Claude to explore, analyze, and answer questions about any public GitHub codebase by connecting to DeepWiki's AI-powered documentation. | |
| Symphony of One MCP ai-wes/claude-symphony-of-one-mcp A multi-agent orchestration system that enables multiple Claude instances to collaborate through a centralized hub with a shared workspace and real-time communication. It features integrated task management, role assignment, and persistent | |
| mcp-geocoder ai-workflow-automations/mcp-geocoder Enables fault-tolerant German address capture for phone agents by matching speech-recognized street names against the official directory and returning confidence scores with TTS-ready follow-up prompts. | |
| ts-backtest ai-yang/ts-backtest Enables users to prepare and validate market data, launch and control backtests, and retrieve results, causal explanations, and self-contained reports through stdio tools. It also supports polling or canceling jobs and running sweep, walk-f | |
| Filesystem MCP Server ai-yliu/filesystem-mcp-server An MCP server that allows Claude AI to perform filesystem operations including reading, writing, listing, moving files, and searching directories within specified allowed paths. | |
| odoo-sh-readonly-mcp ai-zar/odoo-sh-readonly-mcp Read-only MCP server for Odoo.sh exposing builds, environments, logs, and system status via Web API and SSH without any write capabilities. | |
| paperclip-mcp ai-zar/paperclip-mcp Enables AI assistants to manage Paperclip AI agents, issues, goals, approvals, and costs via natural language by exposing Paperclip's REST API as MCP tools. | |
| Browserbase MCP Server ai-zebra/mcp-server-browserbase Enables cloud browser automation through Browserbase and Stagehand, allowing LLMs to interact with web pages, take screenshots, extract data, and perform automated actions with support for proxies, stealth mode, and parallel sessions. | |
| pdf-parse-mcp ai-zen/pdf-parse-mcp Enables precise extraction of PDF content, including text coordinates, vector shapes, images, and on-demand raster rendering, for use cases like reconstructing design files. | |
| MCP Toolbox ai-zerolab/mcp-toolbox A comprehensive toolkit that enhances LLM capabilities through the Model Context Protocol, allowing LLMs to interact with external services including command-line operations, file management, Figma integration, and audio processing. | |
| pymupdf4llm-mcp ai-zerolab/pymupdf4llm-mcp An MCP server that exports PDF documents to markdown format optimized for LLM processing. | |
| Yourware MCP ai-zerolab/yourware-mcp An MCP server that allows users to upload projects (single files or directories) to the Yourware platform, enabling easy deployment and showcasing of projects. | |
| mihoyo-mcp ai1379/mihoyo-mcp Enables MCP clients to connect to miyoushe and HoYoLAB accounts with QR login, encrypted credential storage, multi-account and game role discovery, daily notes for Star Rail, Genshin Impact, and Zenless Zone Zero, plus stamina alert checks | |
| Cloudflare Playwright MCP ai24k/playwright-mcp-example Enables AI assistants to control a browser through a set of tools, allowing them to perform web automation tasks like navigation, typing, clicking, and taking screenshots. | |
| MCP Server with Gemini ai2enginex/python-mcp-web-search-tool Enables an LLM to dynamically discover and invoke external tools through the Model Context Protocol, using Google Gemini to select and execute the appropriate tool and generate a final response. | |
| ai2robot-mcp ai2robot-network/ai2robot-mcp MCP server that lets AI agents dispatch physical tasks to robot executors and track the task -> proof -> verify -> settle workflow, enabling task creation, executor discovery, proof submission, and verification status checks. | |
| ros2-mcp ai2robot-network/ros2-mcp ROS2 MCP server that bridges AI agents (Claude Code, OpenClaw, Cursor) to ROS2, allowing them to read topics, call services, control robots, and wrap telemetry into verifiable hash-chained proof bundles. | |
| AI2Web ai2web-foundation/ai2web-js An MCP server for Claude and ChatGPT that discovers AI-ready websites and acts on them. It fronts the AI2Web Discovery Network with three tools: find_sites, describe_site, and call_site_action. Actions are approval-gated and SSRF-guarded, a | |
| OWL-MCP ai4curation/owl-mcp A Model-Context-Protocol server that enables AI assistants to create, edit, and manage Web Ontology Language (OWL) ontologies through function calls using OWL functional syntax. | |
| lv-quickgate ai68298100/siyuan-quickgate Connects AI assistants over stdio to all 23 public SiYuan gateway operations, letting them run plugin commands, log check-ins, record contact interactions, read whitelisted events and execute confirm-gated workflows while read-only tools st | |
| Google Spark MCP Skills Registry ai7user/spark-skills-mcp Enables Google Spark to dynamically list, search, and fetch on-demand agent skills via MCP for 24/7 availability. | |
| SF-MCP aiadiguru2025/sf-mcp Enables querying SAP SuccessFactors OData API metadata and managing Role-Based Permission (RBP) configurations. It provides tools for retrieving entity metadata, listing permission roles, and inspecting user-specific access rights through M | |
| memtree aiagate/memtree Collects session JSONL from Codex and Claude Code into local SQLite memory, exposed through MCP with tools for memory context, search, get, put, forget, sleep, and status. | |
| VoiceAI-MCP-VAVicky aiagency-now/mcp-voiceai-whitelabel Best VoiceAI White Label Platform for Agencies with Full MCP Connectivity to Any Platform for Custom VoiceAi & AI Chat Integrations and You Keep 100% of the Profits | |
| AI Agent Marketplace Index Search aiagenta2z/onekey-gateway Enables searching for AI agents by keywords or categories, allowing users to discover tools like coding agents, GUI agents, or industry-specific assistants across marketplaces. | |
| llmmemory aiagentflow/llmmemory Enables AI coding agents to save, recall, read, list, and forget plain Markdown memories shared across tools and sessions, so facts are retrieved on demand instead of being repeated. | |
| accessibility-mcp-server aiagentkarl/accessibility-mcp-server Enables AI agents to perform comprehensive web accessibility checks (WCAG 2.1/2.2) including color contrast analysis, ARIA validation, and full accessibility report generation without requiring any API key. | |
| Agent Analytics MCP Server aiagentkarl/agent-analytics-mcp-server Tracks and analyzes AI agent tool calls with event logging, dashboard, per-tool and per-agent analytics, and error monitoring. | |
| Agent Audit Trail MCP Server aiagentkarl/agent-audit-trail-mcp Provides tamper-proof audit logging for AI agents using SHA-256 hash chains, integrity verification, and compliance reporting for the EU AI Act. | |
| agent-commerce-mcp-server aiagentkarl/agent-commerce-mcp-server Enables AI agents to create, compare, and track purchases with structured buying workflows, offer comparison, and merchant verification. | |
| Agent Context Optimizer MCP aiagentkarl/agent-context-optimizer-mcp Analyzes tasks to recommend the minimal set of MCP servers needed, reducing context window waste by up to 85%. | |
| agent-coordination-mcp-server aiagentkarl/agent-coordination-mcp-server Slack for AI agents — rooms, messaging and context sharing for multi-agent collaboration. | |
| Agent Directory MCP Server aiagentkarl/agent-directory-mcp-server Enables AI agents to discover, register, and rate services in a decentralized agent-to-agent directory. | |
| Agent Directory MCP Server aiagentkarl/agent-directory-mcp-server-js MCP Server for agent and service discovery — register, search, rate, and manage AI agents and services in a local directory. | |
| Agent Feedback Loop aiagentkarl/agent-feedback-mcp-server Enables agents to report and query performance metrics to build a community-driven quality database for MCP tools. This server helps agents discover and select the most reliable tools based on success rates and user-reported quality scores. | |
| Agent Identity MCP Server aiagentkarl/agent-identity-mcp-server MCP Server for AI agent identity and authorization. Create, verify, and manage agent identities with trust scores and scoped authorization tokens. | |
| agent-insurance-mcp-server aiagentkarl/agent-insurance-mcp-server MCP server for AI agent transaction insurance and escrow — protect agent-to-agent payments with smart escrow, dispute resolution, and risk scoring. | |
| Agent Memory MCP Server aiagentkarl/agent-memory-mcp-server Provides persistent key-value storage with full-text search, tags, and namespaces for AI agents to maintain context across sessions. | |
| agent-memory-mcp-server aiagentkarl/agent-memory-mcp-server-js Stores and retrieves key-value memories with metadata and namespaces for AI agents. Enables persistent, searchable memory across sessions using the Model Context Protocol. | |
| Agent Policy Gateway MCP Server aiagentkarl/agent-policy-gateway-mcp Compliance and guardrails infrastructure for AI agents, enabling safe operations within regulatory boundaries like GDPR and EU AI Act. | |
| Agent Reputation MCP Server aiagentkarl/agent-reputation-mcp-server Trust and reputation system for AI agents, enabling tracking, verifying, and building trust through scores, interactions, ratings, and reports. | |
| Agent Reputation MCP Server aiagentkarl/agent-reputation-mcp-server-js Enables AI agents to rate each other, track interaction outcomes, and compute trust scores, with features like submitting ratings, getting reputation profiles, leaderboards, and trust computation. | |
| MCP Server Cards aiagentkarl/agent-server-card-mcp Generates, validates, and discovers standardized MCP server cards for automatic agent discovery. | |
| agent-staking-mcp-server aiagentkarl/agent-staking-mcp-server MCP server for agent reputation staking — trust through skin-in-the-game. Agents deposit stakes as trust collateral, with slashing for bad behavior and reputation building over time. | |
| agent-validator-mcp-server aiagentkarl/agent-validator-mcp-server Enables testing and validation of APIs for AI agent compatibility, providing scores, grades, and actionable recommendations. | |
| Agent Workflow MCP Server aiagentkarl/agent-workflow-mcp-server Enables AI agents to create, share, discover, and execute reusable multi-step workflow templates. |
24,951–25,000 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.