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 |
|---|---|
| Backbone.js Documentation MCP Server elegroag/backbone-mcp-server Provides access to Backbone.js documentation chapters as readable resources and enables full-text search across all chapters. Users can browse documentation content and search for specific topics within the Backbone.js framework materials. | |
| waste-for-agents elekli/waste-for-agents MCP server that silently monitors state changes in structured data sources (e.g., government open data) and provides a pull-based channel for AI agents to retrieve real mutations since their last cursor. | |
| Renderoni elemarin/renderoni A batteries-included 3D engine for Three.js and Rapier that enables AI agents and humans to build, inspect, and control deterministic game simulations through a built-in Model Context Protocol (MCP) server. | |
| GraphMemory-IDE elementalcollision/graphmemory-ide An AI-assisted, long-term memory system for IDEs, powered by Kuzu graph database. GraphMemory-IDE is an MCP server that provides semantic vector search, graph-based knowledge storage, and real-time analytics. | |
| VAST DB MCP Server elementalcollision/vast-db-mcp Enables AI agents to securely query VAST Data databases for schema, metadata, and sample data via read-only SQL and MCP resources. | |
| Elementify MCP elementeer/elementeer-mcp An MCP server and WordPress plugin that enables AI assistants to manage Elementor template libraries through a secure REST API. It allows users to read, create, update, and organize templates directly through natural language interfaces. | |
| mcp-feedback-pipe elemtran/mcp-feedback-pipe Web-based feedback collection tool for MCP environments with Markdown, Mermaid charts, and image upload support. | |
| MCP Athena Analytics Server elena-kuznetsova-wh/warehouse-athena-mcp Enables secure querying of analytics data stored in AWS Athena/S3 through natural language, with multiple security layers including query validation, resource limits, and automatic PII redaction to prevent data breaches and destructive oper | |
| StarRocks MCP Server elena0355/mcp-server-starrocks Enables AI assistants to execute SQL, explore schemas, retrieve internal metrics, generate Plotly charts, and obtain table/database overviews from a connected data warehouse. | |
| Frappe MCP elena24120/mcp Enables Frappe Framework apps to function as Streamable HTTP MCP servers, exposing registered Python tools to MCP clients over an API endpoint. It supports tool registration via decorators or manual definitions, with authentication and Werk | |
| codebadger elena73626/codebadger This MCP server builds Joern Code Property Graphs from a Git repository, local path, or pasted snippet and exposes them over MCP, letting AI agents run CPGQL queries, trace data flow and taint, slice programs, and hunt for vulnerabilities a | |
| ScrapeGraph MCP Server elena85534/scrapegraph-mcp Enables AI assistants to scrape, extract, and search web content, run asynchronous multi-page crawls, generate JSON schemas, and schedule monitors against the ScrapeGraph API. It also exposes account credits and job history, and can be run | |
| mcp-server-atlassian-bitbucket elena9263/mcp-server-atlassian-bitbucket Enables AI assistants and LLMs to interact with Bitbucket Cloud workspaces, repositories, pull requests, branches, commits, and other resources through generic API tools for listing, retrieving, creating, commenting, searching, updating, de | |
| Taskade MCP Server elenaali44336/mcp Enables AI clients to manage workspaces, projects, tasks, and AI agents through natural language, with hosted or local connection options and OpenAPI-to-MCP tool generation. | |
| vpf08-library-mcp elenabelyasnik/vpf08-library-mcp An MCP server for managing a book catalog, enabling listing, searching by title, author, or genre, adding books, and evaluating arithmetic expressions. | |
| LunchMoney MCP Server elenac449/lunchmoney-mcp Enables AI assistants and MCP clients to access and manage personal finance data through LunchMoney's API, including transactions, budgets, categories, tags, accounts, recurring items, and crypto holdings. | |
| Z-Image Studio MCP Server elenagreco1445/z-image-studio Exposes tools for image generation, model listing, and history viewing over Model Context Protocol, supporting stdio, SSE, and Streamable HTTP transports for use by AI agents. | |
| Snippy elenahu695/snippy Enables AI assistants to save, retrieve, and semantically search code snippets, generate code style guides and deep wiki documentation, and orchestrate multi-agent documentation workflows through MCP tools. | |
| Android Source Explorer MCP Server elenahuang04002/android-source-explorer-mcp Enables AI assistants to query real AOSP and AndroidX source code on demand, offering class and method lookup, class member and hierarchy inspection, source-wide text/regex search, and optional LSP-powered cross-file definition, reference, | |
| swissdevjobs elenakarabacak162/swissdevjobs-cli Lets AI agents search, filter, and apply to salary-transparent tech job postings across nine boards in eight countries, returning duplicates and errors as structured data and remembering which roles were already applied to. | |
| pfSense MCP Server elenakelly4531/pfsense-mcp-server Enables natural-language management of a pfSense firewall from Claude Desktop, Claude Code, or any MCP client, covering firewall rules, NAT, VPNs, routing, DNS, DHCP, certificates, users, interfaces, services, logs, packages, and diagnostic | |
| caldav-mcp elenalawson/caldav-mcp Enables AI assistants to connect to CalDAV servers to list calendars and events, create, update, and delete calendar events, and manage tasks (VTODOs) including listing, creating, updating, completing, and deleting them. | |
| mcp-virustotal elenalemoine924/mcp-virustotal Enables AI agents to look up VirusTotal v3 reports for files, URLs, IPs, and domains, including the pivoting relationships analysts use: contacted hosts, dropped files, resolutions, threat actors, and malware families. Also supports corpus | |
| kali-mcps elenalin76/awsome_kali_mcpservers Enables users to perform network scanning, symbol and binary analysis, string extraction, live packet capture, and isolated Docker command execution through the Model Context Protocol. | |
| Basecamp MCP Server elenam47/basecamp-mcp-server Enables MCP-capable clients such as Codex, Cursor, and Claude Desktop to read and manage Basecamp 3 projects through OAuth-authenticated API calls. Covers projects, todolists and todos, message boards, campfires, card tables, inbox forwards | |
| StarRocks MCP Server elenaroussel62/mcp-server-starrocks Enables AI assistants to connect to StarRocks databases for direct SQL execution (queries and DDL/DML), database and table exploration, schema and data overviews, and Plotly chart visualization of query results. It also exposes internal Sta | |
| IMAP MCP Server elenat648/imap-mcp-server Enables AI assistants to work with multiple email accounts over IMAP and SMTP: search, read, send, reply, forward, move, mark, and bulk-delete messages, plus list folders and check unread counts. Credentials are stored with AES-256 encrypti | |
| Niblet elenatanaka/niblet-skill-mcp Enables coding agents to find real product-screen references, fonts, icons, and design references so UI work is grounded in existing tokens, components, states, and rendered-screen checks. | |
| zotero-mcp elenaweiss78579/zotero-mcp Enables MCP clients and AI assistants to search a Zotero library, retrieve complete item metadata, and access full text such as PDF contents through the Zotero API. | |
| Mithwire MCP elendil-tech/mithwire-mcp An MCP server that gives AI clients direct control over driverless Chromium browsers through the Chrome DevTools Protocol, enabling agents to navigate pages, click, type, inspect the DOM, capture console and network traces, and manage tabs, | |
| Perforce P4 MCP Server eleni058/p4mcp-server Integrates with Perforce P4 version control to expose safe, structured read/write tools for changelists, files, shelves, workspaces, jobs, reviews, and server metadata, with optional P4 DAM asset management. | |
| multiCAD-mcp eleni1381/multicad-mcp Enables AI assistants to control CAD applications such as AutoCAD, ZWCAD, GstarCAD, and BricsCAD through natural language or direct tool calls. Supports drawing shapes, managing layers, entities and blocks, extracting or exporting data, and | |
| Ombre Brain eleni32687/ombre-brain Gives Claude persistent cross-conversation memory: it stores what happened over time as Obsidian-compatible Markdown tagged with Russell's valence/arousal coordinates, decays and archives inactive memories along a forgetting curve, and surf | |
| Zendesk MCP Server eleni47/zendesk-mcp-server Enables AI assistants to retrieve, create, and manage Zendesk tickets, comments, and attachments, with prompts for ticket analysis and response drafting plus access to Help Center articles as a knowledge base. Supports per-operator OAuth au | |
| SerpApi MCP Server elenibayrak3891/serpapi-mcp Enables querying multiple search engines such as Google, Bing, Yahoo, DuckDuckGo, YouTube, and eBay to retrieve real-time results, including answer boxes, organic results, news, images, shopping, weather, and stock data. Responses can be re | |
| Vectorize MCP Server elenibayrak3891/vectorize-mcp-server Enables vector search and document retrieval, extraction and chunking of files into Markdown, and private deep research generation from a configured pipeline. Users can query knowledge bases, convert documents, and produce reports through n | |
| Claude IPC MCP eleniford97759/claude-ipc-mcp Enables AI assistants across different platforms and sessions to communicate with each other through persistent, natural-language messaging commands like register, send, and check. Messages survive restarts, allowing Claude, Gemini, and oth | |
| Perforce P4 MCP Server eleniinoue274/p4mcp-server Enables AI assistants to read and write Perforce P4 version control resources — files, changelists, shelves, workspaces, jobs, reviews, streams, and server metadata — through safe, structured tools. Also connects to P4 DAM via its REST API | |
| Agentdocs elenikaramanlis49/python-mcp-server-client Enables AI models to search and retrieve the latest technical documentation for mainstream agent frameworks such as langchain, llama-index, autogen, agno, openai-agents-sdk, mcp-doc, camel-ai, and crew-ai by running site-restricted Google s | |
| Piia Engram eleniortiz31553/piia-engram Enables coding agents to start from one local, user-owned identity and knowledge store, so preferences, quality bars, lessons, decisions, and project context carry across sessions and MCP-compatible clients. Everything stored is inspectable | |
| flameox elenipelletier34371/flameox Enables coding agents to run bounded analysis and capture operations against explicit artifacts or commands, returning typed evidence, provenance, coverage, limitations, and optional preserved evidence through MCP tools. | |
| codebadger elenivandermeer/codebadger Enables AI agents and LLMs to build Joern Code Property Graphs from Git repositories, local paths, or snippets and query code structure, data flow, taint, program slices, and vulnerabilities over MCP across many languages. | |
| Elephant MCP Server elephant-xyz/elephant-mcp Connects Claude-compatible clients to the Elephant data graph, enabling discovery of data groups, classes, and property schemas. Supports semantic code search for verified script examples via OpenAI or AWS Bedrock embeddings. | |
| mydatavalue-mcp elev8-os/mydatavalue-mcp MCP server for querying MyDataValue's Booking.com and Airbnb property data, including pricing, promotions, reviews, and performance metrics, via a read-only connector with automatic OAuth token rotation. | |
| air-mcp-server eleva/air-stefauto-mcp MCP server for booking and date-utility tools, deployed on AWS Lambda, supporting DynamoDB storage and optional WhatsApp notifications. | |
| cdk-serverless-mcp-server eleva/cdk-serverless-mcp-server A minimal MCP server deployed on AWS Lambda and API Gateway using AWS CDK, enabling tool execution via JSON-RPC (e.g., an add tool). | |
| serverless-mcp-server eleva/serverless-mcp-server A minimal MCP server deployed on AWS Lambda and exposed via API Gateway, enabling tools like addition through JSON-RPC interactions. | |
| debate-hall-mcp elevanaltd/debate-hall-mcp Enables structured multi-perspective debates with Wind (explore), Wall (constrain), and Door (synthesize) roles, featuring deterministic state, hash chains, GitHub integration, and auto-orchestration for decision-making. | |
| HestAI-MCP elevanaltd/hestai-mcp Governance and session management layer for AI-assisted software development; enables agent binding, session tracking, and structured code review within the HestAI ecosystem. | |
| octave-mcp elevanaltd/octave-mcp MCP server for deterministic document infrastructure, enabling canonical normalization, schema validation, and grammar compilation for structured AI artifacts. |
47,501–47,550 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.