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 |
|---|---|
| Chinese Fortune Analysis System (BaZi) deeppath-ai/mcp-chinese-fortune Enables traditional Chinese fortune-telling through BaZi (Four Pillars) analysis, including solar/lunar date conversion, Five Element balance calculations, Ten Gods deduction, and destiny interpretation for metaphysics applications. | |
| mcp-crew-risk deeppath-ai/mcp-crew-risk Performs comprehensive crawler compliance risk assessment for webpages, evaluating legal, ethical, and technical risks including robots.txt rules, anti-crawling mechanisms, sensitive data detection, and providing crawl permissibility rating | |
| Marketing Master – Landing Page Evaluator deeppath-ai/mcp-marketing-site Enables rapid analysis of landing pages for SEO compliance, conversion structure, color contrast accessibility, and performance metrics with automated optimization suggestions and code snippets. | |
| Intelligent Architecture Recommendation Engine deeppath-ai/mcp-system-infra Generates tailored system architecture recommendations based on business parameters like QPS, concurrent users, database type, and AI model size, providing resource allocation plans, middleware suggestions, and exportable architecture diagr | |
| PromptX deepractice/promptx Transforms AI agents into industry experts through natural conversation, enabling role creation (Nuwa), tool integration (Luban), and professional content generation (Writer) with cognitive memory capabilities. | |
| RoleX deepractice/rolex Provides AI agents with persistent identity, social organization, and experience-based growth, modeled on human societies, via MCP tools for goal management, learning, and resource sharing. | |
| mcp-guide deeprave/mcp-guide Enables AI agents to access and manage project guidelines, documentation, and context through a structured content system with template support and workflow management. | |
| search-mcp deeprave/mcp-websearch Enables web search capabilities using DuckDuckGo's free API without requiring authentication or API keys. | |
| deeprecall-mcp deeprecall-io/deeprecall-mcp Search 120,000+ recalled products from CPSC, FDA, EU Safety Gate, and other global agencies via MCP. Enables AI agents to check product safety by text or image. | |
| GPT Researcher MCP Server deepresearch329-debug/gptr-mcp Enables deep web research and report generation through an MCP interface, providing tools for comprehensive research, quick search, and source management. | |
| Odoo MCP Server deeprunnerai/odoo-mcp-server An MCP server that enables AI assistants to interact with Odoo ERP apps like Inventory, CRM, Sales, and Manufacturing. It allows users to read, create, and manage Odoo records and workflows using natural language commands. | |
| MCP PDF Server deepseekmine/mcp-pdf-reader A PDF processing server that extracts text via normal parsing or OCR, and retrieves images from PDF files through the MCP protocol with a built-in web debugger. | |
| ArenaPro-MCP deepseekv5/arenapro-kit Enables AI agents in IDEs to operate a local dao3 editor instance through its HTTP API, providing tools for project, map, file, and component management while explicitly refusing account-related operations and contacting no remote services. | |
| deepset-mcp deepset-ai/deepset-mcp-server Enables AI agents to build and debug pipelines on the Haystack Enterprise AI platform through 30+ specialized tools, and provides a Python SDK for programmatic access. | |
| Hayhooks deepset-ai/hayhooks Deploys and serves Haystack Pipelines and Agents as REST APIs and MCP tools, enabling AI assistants to interact with custom NLP pipelines for tasks like RAG, document processing, and intelligent agents through natural language. | |
| parquet mcp server deepspringai/search_mcp_server A powerful MCP (Model Control Protocol) server that provides tools for manipulating and analyzing Parquet files. This server is designed to work with Claude Desktop and offers four main functionalities: | |
| DeepSRT MCP Server deepsrt/deepsrt-mcp An MCP server that enables users to generate summaries of YouTube videos in multiple languages and formats through integration with DeepSRT's API. | |
| Alpha Vantage MCP Server deepsuthar496/alpha-ventage-mcp An MCP server that provides real-time financial data integration with Alpha Vantage's API, enabling access to stock market data, cryptocurrency prices, forex rates, and technical indicators. | |
| Figma MCP Server deepsuthar496/figma-mcp-server A Model Context Protocol server that integrates with Figma's API, allowing interaction with Figma files, comments, components, projects, and webhook management. | |
| Remote Command MCP Server deepsuthar496/remote-command-mcp A Model Context Protocol server that enables remote execution of shell commands across different operating systems, automatically handling platform-specific differences between Windows and Unix-like systems. | |
| mydy-lms deeptanshuu/mydy-lms-helper An MCP server for interacting with the MyDy (Moodle-based) LMS, enabling attendance viewing, course browsing, assignment and grade checking, announcement reading, and material downloading. | |
| deeptempo-mcp-servers deeptempo/deeptempo-mcp-servers Provides tools for DeepTempo AI SOC including findings and case management, investigation workflow orchestration, action approval workflows, and MITRE ATT&CK layer generation. | |
| Splunk MCP for SOC Operations deeptempo/splunk-mcp-soc Enables AI-driven SOC investigations by providing automated Splunk querying, threat intelligence enrichment, and response actions through natural language. Includes tools for IP pivoting, lateral movement detection, and label harvesting. | |
| Gmail MCP Connector deepthi-vimal/gmail_mcp_coonector Enables reading, searching, sending, and drafting Gmail emails via MCP tools, with support for multiple accounts and background notifications. | |
| ebay-mcp deepujain/ebay-mcp Enables searching eBay listings, inspecting item details, monitoring price drops, placing auction bids, and buying fixed-price items via guest checkout through eBay's Buy APIs. | |
| MCP Document & Task Server deepujain/mcp-doc-server Provides a document database with search, retrieval, and creation tools, and a task tracker with search and status filtering, enabling AI agents to manage documents and tasks via natural language. | |
| YouTube MCP Connector deepujain/youtube-mcp Enables MCP-compatible clients to search YouTube videos, read subscriptions and playlists, generate catch-up digests of recent uploads, and manage playlists with approval-gated writes via the YouTube Data API v3. | |
| poe2-mcp deepwa7er/poe2-mcp An MCP server for Path of Exile 2 build analysis that loads builds from Path of Building export codes and allows natural language interrogation via any MCP-compatible client. | |
| DeepWriter MCP Server deepwriter-ai/deepwriter-mcp Provides tools for creating, managing, and generating content for DeepWriter projects through a standardized Model Context Protocol interface. | |
| mcp-knowledge-assistant deepxk2403/mcp-knowledge-assistant A custom MCP server providing semantic note memory (Qdrant + FastEmbed) and optional web search (Tavily) tools for a LangGraph ReAct agent. | |
| Deepy MCP Server deepy-to/deepy-mcp-server Thin MCP server that enables AI agents to generate video, image, and audio content via the Deepy API using a personal API key, with safe generation flow and no business logic. | |
| DeepSeek MCP Server deepzhun/deepseek-mcp-server Connects MCP clients to DeepSeek API, including DeepSeek-R1 reasoning with visible chain-of-thought. Provides four tools: generate, chat, reason, and list models. | |
| Gemini MCP Server deepzhun/gemini-mcp-server Connects any MCP client to the Google Gemini API, providing tools for text generation, chat, vision analysis, embeddings, token counting, and model listing. | |
| OmniBrowse-Agent deer-001/omnibrowse-agent A browser research MCP server that emphasizes evidence-centric workflows, secure browser automation, and deterministic data extraction, with structured responses and artifact-based screenshots. | |
| fic-mcp-payments-patch deer412090/fic-mcp-payments-patch Enables natural-language management of FattureInCloud invoicing, clients, suppliers, and e-invoice workflows, with extensions for marking invoices as paid and caching payment accounts/VAT types. | |
| CryptoPriceTracker-MCP deerajd/cryptopricetracker-mcp Enables LLM agents to fetch real-time cryptocurrency prices using the CoinGecko API, supporting multiple cryptocurrencies and fiat currencies. | |
| MCP Duplicate File Manager Server deerajd/duplicatefileremover-mcp Enables LLM agents to find and safely delete duplicate files using content-based detection, with smart copy prioritization and dry-run mode. | |
| JSON Path MCP Server deermakov/mcp-jsonpath-server MCP server that provides tools to read JSON files and query data using jsonPath expressions. | |
| gameLLM deese/gamellm An MCP server that provides structured game data and scraped guides for video games, enabling natural language queries via Claude Code skills. Currently supports Clair Obscur: Expedition 33 with tools to search pictos, weapons, bosses, and | |
| Odoo 18 MCP Server deevando/odoo18-mcp-server Connects AI assistants to Odoo 18 to create and manage sales quotations, including listing, retrieving, and updating quotes, using the external API with user-provided credentials. | |
| moodle-mcp deeznust42/nutslms-mcp Enables agents to interact with a university Moodle LMS via MCP, surfacing deadlines hidden inside course documents along with grades, assignments, and submission capabilities. | |
| learn-corpus-retrieval def-a-name/learn-corpus Enables AI clients to search a personal corpus, read relevant source passages, and answer questions with traceable evidence from imported sessions, notes, and articles. | |
| DeFade defadeltd/defade-sdk Rug pull risk scores and on-chain forensics for memecoins on Solana, Ethereum, Base and Robinhood Chain - launch-bundle detection, funding-origin tracing, deployer history, insider networks and whale flow. 15 read-only tools. | |
| @defarm/mcp defarm-repo/defarm-mcp Enables AI agents to seal, open, verify, and ingest verifiable agri-traceability data by description, with credentials and private keys kept out of the model's flow. | |
| scratchpad-tool default-anton/scratchpad-tool A Model Context Protocol server that provides a scratchpad tool for LLMs to organize thoughts, take notes, and plan approaches to complex problems. | |
| defeatbeta-api defeat-beta/defeatbeta-api Defeatbeta API is an open-source alternative to Yahoo Finance's market data APIs, designed to provide reliable and high-performance financial data. | |
| courtlistener-mcp defendthedisabled/courtlistener-mcp An MCP server providing AI agents access to CourtListener's comprehensive legal database, featuring semantic search, hybrid search, citation verification, and research tools. | |
| Defense MCP defensedotcom/defense-mcp-claude-extension Provides Claude Desktop access to Defense.com threat intelligence data for risk assessment, threat analysis, and workload management. It also features interactive security training tools and supports over 200 source type aliases for simplif | |
| mountainproject defevan/mp-mcp Enables searching routes and areas on Mountain Project, applying route-finder filters, and querying personal tick lists live. | |
| Archon-KB defexnn/archon-kb Enables AI agents to look up exact technical identifiers and retrieve verified, line-cited knowledge across kernel, firmware, WMI, API, driver, and reverse-engineering documentation using hybrid lexical/vector search and graph traversal. |
43,401–43,450 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.