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 |
|---|---|
| Korea Housing MCP doorijaehyuk/korea-housing-mcp This MCP server integrates South Korea's national law information, building registers from MOLIT, and KOSIS statistics for housing development research. It enables searching laws, retrieving building details, and accessing statistical data | |
| budget-aware-mcp doorman11991/budget-aware-mcp Model-agnostic code memory MCP server using budget-aware graph retrieval for AI agents, providing sub-millisecond queries, token budgeting, and deterministic results without embeddings or vector databases. | |
| Invoker MCP Server doossee/invoker-mcp Enables AI agents to create, run, and manage HTTP requests using the Invoker API client's .ivk format. It provides tools for scanning collections, executing requests, managing environments, and building documentation sites. | |
| aigc-lite dooven-prime/aigc-lite Enables a self-hosted AI workspace with persistent sessions, agent run/step execution logs, unified search across conversations and knowledge, and discovery/invocation of local and remote MCP tools. | |
| Dooza Browser dooza-ai/dooza-browser Gives AI agents a single shared, logged-in Chrome they can drive over MCP or plain HTTP: open and read tabs, click, type, upload files, run short Playwright scripts, hand off whole web tasks to a cheaper model, and keep per-site memory. Age | |
| academic-mcp dopawei/academic-mcp Unified academic search MCP server that searches open literature (arXiv, bioRxiv, medRxiv, PMC), CNKI, and Web of Science, with browser-backed authentication, local paper library, and export to multiple formats. | |
| n8n MCP Server dopehunter/n8n_mcp_server_complete Enables management of n8n workflows directly within LLMs through the Model Context Protocol, including listing, executing, and monitoring workflows. | |
| forge-x-reforger-mcp dopemodz420/forge-x-reforger-mcp Enables AI agents to build Arma Reforger mods from natural language, including API research, code generation, project scaffolding, Workbench control, and in-editor testing. | |
| dSIPRouter MCP Server dopensource/dsiprouter-mcp Enables AI assistants to manage dSIPRouter operations such as endpoint groups, carrier groups, inbound mappings, and call data retrieval through natural language. | |
| Claude Typer doperdodge/claude-typer-mcp-extention A Windows MCP extension that allows Claude to type text into any active application with human-like keystroke timing, approval mode, configurable speed, and writing style presets. | |
| Concierge Core Kit dopomogai/concierge-core-kit Enables authorized clients to invoke tenant-aware conversational assistant tools and resources over MCP, including durable conversations, agent configuration, connector policies, and PostgreSQL-backed data. | |
| flaight dopomogai/flaight Enables MCP clients to list recorded runs and read declared plan artifacts — plans, journals, and outputs — from a local runs directory over stdio, with traversal and undeclared-file protections. | |
| Context API MCP Server doppelgangersai/context-mcp-server Accesses the doppelgangers.ai Social Media Context API to provide contextualized XML renderings of Twitter/X posts including conversation summaries and metadata. It enables semantic search and comprehensive post retrieval for high-quality a | |
| ctxmem doppiag93/ctxmem Provides AI agents with persistent, local, and shareable project memory by storing decisions and code context in a searchable SQLite index, supporting keyword and semantic search via MCP. | |
| Doppler MCP Server dopplerhq/mcp-server Enables AI assistants to interact with the Doppler API for secrets management, including listing, retrieving, and updating secrets across projects and configs. Supports both read-only and full access modes with token-based authentication. | |
| BackTest_MCP dor1toes/backtest_mcp A stock backtesting engine MCP server that fetches stock data, validates and executes dynamic strategies, and generates backtest results and reports. | |
| com.browser-use/browser-use doracakess/browser-use Enables AI agents to autonomously operate web browsers through the Model Context Protocol, including navigating pages, clicking, typing, filling forms, and extracting structured data. | |
| ghost-content-mcp doradame/ghost-content-mcp Read-only MCP server for Ghost sites that enables AI assistants to search, summarize, and read content via hybrid lexical and semantic ranking. | |
| MCP Student Assistant doraitto5/mcp-student-assistant Enables querying student information such as marks, attendance, pending assignments, and timetables from a MySQL database through MCP tools. | |
| llm-skills-mcp-poc dorangao/llm-skills-mcp-poc MCP server exposing a shared pr-review skill with tools to list, get, run, and evaluate skills, enabling AI assistants to perform code review tasks. | |
| mcp-web-search doranobik/mcp-web-search Enables web searches through DuckDuckGo without an API key and extracts readable main content from web pages. | |
| dorelli dorelli-cloud/cli Enables AI tools to deploy static websites to Dorelli Hosting and check their status via MCP, using deploy_site and site_status tools. | |
| Blender MCP Server dorialn68/blender-mcp-enhanced Enables AI-powered 3D content creation in Blender through natural language, including text-to-3D, image-to-3D, animation, rigging, rendering, and export. | |
| agent-canary dorianchn/shanchuanzhi-agent-canary Registers a set of inert, tempting decoy tools with any MCP-capable client so that any call from a hijacked or prompt-injected agent instantly raises an alert with full attack context and a per-call trace token. Also plants worthless canary | |
| Claude Web Search MCP Server doriandarko/claude-search-mcp Provides web search capabilities to Claude AI using the Anthropic API, allowing LLMs to access up-to-date information from the web with customizable domain filtering. | |
| Sora MCP Server doriandarko/sora-mcp Integrates with OpenAI's Sora 2 API to generate, remix, and manage AI-generated videos from text prompts. Supports video creation, status monitoring, downloading, and remixing through natural language commands. | |
| Splytin MCP Project Generator doriandarren/splytin_mcp An MCP server that enables the automated creation and scaffolding of Python Django, React, and PHP projects. It provides tools for initializing new project structures and generating Django CRUD components. | |
| OpenZIM MCP Server doriangallo/openzim-mcp OpenZIM MCP Server | |
| Bubble MCP dorianglz/bubble_mcp Enables AI assistants to interact with Bubble.io applications through the Model Context Protocol for data discovery, CRUD operations, and workflow execution. It provides a standardized interface for managing Bubble database records while re | |
| Docs-to-AI dorianmeric/docs-to-ai Enables LLMs to query documents using semantic search, supporting PDFs, Word, Excel, and more. Organizes documents by topics from folder structure and provides advanced search features like phrase matching and date filtering. | |
| RepoMind-MCP doridoor/repomind-mcp MCP server for repository mapping, dependency analysis, and architecture diagram generation for JavaScript, TypeScript, and Python projects. | |
| remotessh-mcp dorimui/remotessh-mcp Provides local command execution, remote SSH, interactive terminals, file read/write, and source search for AI CLI through stdio, with large output pagination and safety confirmations. | |
| MCP Server Basic Example dorisashehi/mcp A basic Model Context Protocol server implementation that demonstrates core MCP functionality including tools and resources. Provides weather alerts through the Weather API and serves as a learning example for MCP development. | |
| mcp-virustotal dorisgutierrez/mcp-virustotal Enables AI agents to query the VirusTotal v3 API for detection reports on files, URLs, IPs, and domains, along with relationship pivots like contacted hosts, dropped files, resolutions, and threat actors. Also supports corpus search, sandbo | |
| MCP Memory Keeper dorisjain/mcp-memory-keeper Enables AI coding assistants to maintain persistent context across sessions by saving, searching, organizing, checkpointing, and restoring conversations, decisions, file content, and progress. | |
| slop-guard doriskowalski/slop-guard Enables agents to analyze prose by scoring text or files for formulaic AI writing patterns, returning numeric scores, band labels, specific violations, and concrete advice through MCP tools. | |
| Financial Modeling Prep MCP Server dorismenon849/financial-modeling-prep-mcp-server Provides AI assistants with 250+ tools to access and analyze financial data, including stocks, ETFs, crypto, forex, commodities, economics, and company fundamentals. | |
| RISEN Prompt Engineering MCP Tool doritoman90000/mcp-risen-prompts A Model Context Protocol server that helps users create, validate, and optimize AI prompts using the RISEN framework (Role, Instructions, Steps, Expectations, Narrowing). | |
| code-graph-mcp dorkian/code-graph-mcp Indexes a mono-repo into a knowledge graph and provides MCP tools to query code structure—packages, components, routes, HTTP calls—without file reads or grep round-trips. | |
| n8n-flow-bridge-mcp dorkian/n8n-flow-bridge-mcp Enables git-based version control for n8n workflows with automatic credential remapping, allowing AI tools to pull, push, and manage workflows across environments. | |
| siteone-mcp-server dorkside/siteone-mcp-server Enables SEO auditing and site analysis by crawling websites, identifying issues, and generating reports like sitemaps and markdown exports. | |
| Squads MCP dorkydhruv/squads-mcp Enables secure management of Squads multisig accounts on the Solana blockchain, allowing LLMs to create proposals, vote, and manage assets. It features built-in security auditing and local private key storage to ensure safe interaction with | |
| @dormon/salesforce-mcp dormonbear/salesforce-mcp Enhanced MCP server for interacting with Salesforce orgs, featuring concurrency safety, error recovery guidance, structured output, smart schema caching, and MCP Resources for AI agents. | |
| MCP Ethereum Address Info Server doronaviguy/mpc-0x Provides real-time information about Ethereum addresses across multiple chains using the Model Context Protocol, featuring a Server-Sent Events endpoint for live updates. | |
| AI Website Check dorota-galini/ai-website-check Reads a small-business website like a customer would and shows where they get stuck. Every AI answer has to quote the page, and the server checks the quote before it counts. | |
| StarRocks MCP Server dorothy4285/mcp-server-starrocks Bridges AI assistants with StarRocks databases so they can execute SQL queries and DDL/DML, explore databases, tables and schemas, inspect system metrics, pull detailed table and database overviews, and render query results as Plotly charts | |
| Agentdocs dorothyb35/python-mcp-server-client Enables users to search and retrieve up-to-date technical documentation for popular agent frameworks such as LangChain, LlamaIndex, AutoGen, Agno, OpenAI Agents SDK, MCP, Camel AI, and CrewAI. It does this by performing site-specific web se | |
| OpenClaw MCP Server dorothybarbieri53/openclaw-mcp Enables AI clients like Claude.ai and Claude Desktop to connect securely to self-hosted OpenClaw assistant gateways over OAuth 2.1, sending chat messages, monitoring gateway health, and queuing long-running tasks asynchronously. Supports or | |
| stock-mcp dorothyflores59/stock-mcp Enables AI agents and regular backends or scripts to access standardized financial market data and analysis across A-shares, US equities, ETFs, indices, and crypto, including technical indicators, fundamentals, money flow, news, filings, an | |
| MiniMax MCP JS dorothyfujita7465/minimax-mcp-js Enables MCP-compatible clients to generate images, videos, and speech, clone or design voices, and manage the resulting media through MiniMax APIs. |
45,601–45,650 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.