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 |
|---|---|
| Concordium MCP Server developerayo/concordium-mcp-server Concordium mcp-sever for interacting with the concordium chain | |
| debug-mcp-server developerlabsai/debug-mcp-server Bridges web browsers and Claude Code for seamless debugging workflows by receiving debug data from browser widgets and exposing it to Claude Code via MCP protocol. | |
| mcp-job-tracker developermaroof/mcp-job-tracker Enables Claude to record job applications in a local JSON file and then list them, change their status (applied, replied, interview, rejected, offer), and surface stale applications that need a follow-up. Requires no database or account, an | |
| onboard-mcp developerpankajdixit/onboard-mcp Checks your local development environment for common issues like wrong Node version, missing Docker, missing git config, missing .env keys, and busy ports, and provides fixes. | |
| mcp-file-system-lmstudio developersorli/mcp-file-system-lmstudio Exposes local LM Studio language models as MCP tools, enabling chat completions and model listing through a local OpenAI-compatible API without requiring API keys. | |
| AI Gaming Agent MCP Server developerz-ai/ai-gaming-agent-mcp Enables AI agents to remotely control gaming PCs for automated gameplay with tools for screen capture, mouse/keyboard control, workflows, and system operations. | |
| universal-lsp developerz-ai/universal-lsp Enables AI agents to query language intelligence over MCP, including definitions, references, symbols, and code relationship graphs across many languages, all in one native process with no external language servers. | |
| MCP Audio Inspector developerzo/mcp-audio-inspector Enables comprehensive audio file analysis and metadata extraction with specialized game audio development features, supporting batch processing of multiple formats and providing platform-specific optimization recommendations. | |
| MCP Audio Tweaker developerzo/mcp-audio-tweaker Enables batch audio processing and optimization using FFmpeg with preset configurations for game audio, voice processing, and music mastering, including specialized optimization for ElevenLabs AI voice output. | |
| Modular MCP Server developkariyer/mcp A scalable, auto-discovering Model Context Protocol server that dynamically loads tools from the tools directory, enabling LLMs to access various capabilities through a standardized interface. | |
| @developkiko/desktop-commander developkiko/dsktpcmndr MCP server for terminal operations and file editing, enabling AI assistants to manage files, run commands, and process large content with auto-chunking. | |
| opencode-jira-mcp developmentagentsdd/mcp-jiracloud MCP server that connects opencode with Jira Cloud, exposing issue tracking, project management, and agile features as structured tools for AI agents. | |
| MCP Toolsets Runtime developmentseed/mcp-toolsets-runtime A shared runtime that discovers LangChain tools from a toolset package and serves them as an MCP server, with optional UI views and a CLI for managing tools. | |
| GEPA MCP Server developzir/gepa-mcp Implements the Genetic-Evolutionary Prompt Architecture for automatic prompt optimization, providing tools to optimize, quickly improve, and contextually adapt prompts. | |
| Strapi MCP Server devels-ai/strapi-mcp-server Enables AI assistants to connect to Strapi CMS for browsing, creating, editing, publishing, and managing content through natural language. | |
| MCP-Render devemree/mcp-render MCP server deployed on Render using SSE transport, providing tools for user management, ERP operations, SQLite database interaction, and server stats. | |
| Turkish-Sentiment-Anlaysis devemree/mcp-turkish-sentiment-analysis Turkish sentiment anlaysis with MCP | |
| hubspot-multi-mcp devender/hubspot-multi-mcp Enables Claude Desktop to connect to multiple HubSpot portals simultaneously with read-only access, allowing users to query, search, and retrieve CRM data from any named portal, including searching every portal at once. | |
| engagelab-sms-mcp devengagelab/engagelab-sms-mcp Enables AI assistants to send template-based SMS messages through EngageLab. Supports multiple recipients and template parameters via a single tool. | |
| ScrAPI MCP Server deventerprisesoftware/scrapi-mcp A server that enables web scraping of difficult-to-access websites affected by bot detection, captchas, or geolocation restrictions, returning results in either HTML or Markdown format. | |
| boris-mcp devenv/boris-mcp A public MCP server about Boris Churzin's builds, decisions, and ops doctrine, allowing agents to interrogate his judgment instead of parsing a PDF. | |
| NYC Property Data MCP Server deverseli800/cre-public-data-mcp Provides Claude with access to NYC public property data including property details, sales history, comparable sales, tax benefits, and rent stabilization analysis using natural language. | |
| ProductNerveCenter devesh-gg/productnervecenter An MCP server that exposes product-management tools for AI agents, including backlog prioritization, feedback analysis, capacity assessment, and dependency mapping. | |
| docverity deveshagarwal/docverity MCP server that enables coding agents to check documentation claims against source code, detecting drift and suggesting fixes. | |
| cmcp deveshb-1/collection-mcp-check Turns a Postman collection into a set of MCP tools served over stdio, so an AI agent can invoke the underlying HTTP API with resolved variables, inherited auth, and per-tool safety hints. It also lints the collection for agent-readiness and | |
| hostproof-mcp deveshb-1/hostproof Enables agents to run read-only Linux and Kubernetes compliance checks, bundle SOC 2 and ISO 27001 evidence, preview Sprinto monitor uploads, and confirm submission through Sprinto's Upload Evidence API. | |
| nowcoder-mcp-server deveverything01/newcoder-mcp-server Enables AI to search and retrieve programming problems, interview experiences, and solutions from Nowcoder (牛客网) via the Model Context Protocol. | |
| Qdrant MCP Server deveyus/qdrant-mcp-server Provides semantic search capabilities using Qdrant vector database with multiple embedding providers, including hybrid search, code indexing, and git history search. Adds optional time-based recency scoring to search results. | |
| skills-mcp devfellowship/skills-mcp Enables Claude/MCP agents to search, list, get details, and generate install commands for skills, MCP servers, and connections from the DFL Forge skills registry. | |
| GAS MCP Server Advanced devfinprojects/gas_mcpserver_adavanced An enterprise-grade MCP server that integrates AI agents with Google Sheets and Apps Script using over 100 specialized tools for automation and data analysis. It features a self-healing architecture with advanced security and observability | |
| pt.flatin/property-taxes devflatinpt/mcp Enables users to calculate Portuguese property purchase costs (IMT, stamp duty, deed/registration) and query annual IMI rates and costs for all 308 municipalities, with sourced figures. | |
| bullet-mcp-server devgabrielsborges/bullet-mcp-server Provides physics simulation capabilities using PyBullet, enabling 3D physics world creation, object loading, force application, and state monitoring through MCP protocol. | |
| mcp-weather-api devgrunge/mcp-weather-api Provides weather forecasts and alerts for US locations via the National Weather Service API, enabling AI assistants to deliver real-time weather information. | |
| se-check devhardesian/se-check Enables AI coding agents to audit Supabase or Postgres databases for Row Level Security and multi-tenant isolation holes, reading tables, grants, policies and functions for static findings and optionally probing those policies inside a roll | |
| Azure DevOps MCP Server devhaydon/azure-devops-mcp Enables AI agents to interact with Azure DevOps resources such as projects, builds, repositories, work items, test plans, and wikis through natural language using the Model Context Protocol. | |
| stcc-mcp devhc123/stcc-mcp Deterministic rule-based medical triage with citations, using a 0.6B LLM only to check criteria (yes/no/unknown). | |
| my-obsidian-mcp devheedoo/my-obsidian-mcp Enables AI assistants to read, search, create, and modify Obsidian notes via the Model Context Protocol, supporting tasks like daily notes, backlinks, and project management. | |
| DevHelm MCP Server devhelmhq/devhelm-mcp A public, stateless MCP server designed to demonstrate recording, replaying, and verifying MCP interactions via mcp-recorder. It offers utility tools for tasks such as math operations, text summarization, and service status lookups. | |
| umeng-openapi-mcp-server devhuang0714/umeng-openapi-mcp-server MCP server for 友盟 U-App mobile analytics, enabling AI agents to query app statistics, retention, channels, versions, custom events, and more via the OpenAPI. | |
| KnowledgeRail deviank88/knowledgerail Local-first MCP server that turns project documentation and source code into durable, evidence-backed context for AI agents, with bounded retrieval and explicit gap reporting. | |
| Salesforce MCP UI Automation deviank88/salesforce-mcp-ui-automation Automates Salesforce via browser using Playwright with persistent session. Supports Data Cloud, Setup, and other UI-only areas through generic tools. | |
| la-caja-mcp deviceargent/la-caja-mcp Enables structured debates with agent-agent-human interaction and access to persistent contextual memory (La Caja) through MCP tools. | |
| Devicebase MCP Server devicebase/devicebase-mcp Enables remote control of mobile devices via the Devicebase API, including touch gestures, app management, and UI inspection. | |
| MCP-Based Enterprise Knowledge Search Assistant devidas-07/mcp-based-rag Enables enterprise knowledge search through a chat interface, comparing traditional RAG with MCP-driven retrieval using hybrid BM25 and dense vector search, Ollama-powered answer generation, and question routing to domain-specific retrieval | |
| Devil MCP Server devil-imps/devil-mcp An MCP server that provides programmatic access to devil hosting platform management tools, enabling AI assistants to manage websites, databases, DNS, SSL, email, and more via a secure REST API. | |
| agent-vm-mcp deviltea/agent-vm-mcp Provides an MCP control plane for a dedicated Linux VM, enabling shell-equivalent command execution, bounded filesystem and Git workspace operations, persistent process and coding-agent orchestration, artifact presentation, and optional ups | |
| SQL MCP devimfaheem/relationaldb-mcp Enables defining SQL queries as callable tools for Claude, supporting MySQL, PostgreSQL, and SQL Server with parameterized queries, read-only/write modes, and a web admin UI for managing connections and tools. | |
| mcp-ai-workforce devimperatore/mcp-ai-workforce Enables primary AI orchestrators to delegate token-heavy coding tasks to economical models via OpenRouter, running sandboxed autonomous ReAct loops with filesystem operations and git audit tools while reducing token costs. | |
| Skillify devinat1/skillify Turns public websites into portable SKILL.md files via MCP using Firecrawl. | |
| SocialDataX Bilibili MCP devinchen2014/bilibili-mcp Bilibili MCP by SocialDataX for video, article, and dynamic search and details, comments and replies, likes and reposts, creator data, download links, and transcripts. |
44,001–44,050 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.