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 |
|---|---|
| GitHub Issues MCP Server bhagwatak29/secure-mcp-gateway-for-autonomous-ai-actions An MCP server that enables AI models to securely read and manage GitHub issues with authenticated access, confirmation prompts for write operations, and metrics tracking for tool-call reliability. | |
| MCP PDF Server bhagyeshrashinkar/mcp-pdf-server Enables AI assistants to query PDF documents by ingesting them into a vector database and generating answers grounded in the actual documents. | |
| remote-mcp-server-authless bhailu261/remote-mcp-server-authless Enables deploying a stateless remote MCP server on Cloudflare Workers without authentication, allowing MCP clients like Cloudflare AI Playground and Claude Desktop to connect and use registered tools. | |
| Local MCP CRM bhairavaa/local-mcp-crm A local-first CRM that exposes customer and project management tools via the Model Context Protocol (MCP), including an analytics server. It integrates seamlessly with Claude Code or a custom LlamaIndex ReAct agent. | |
| ChurnCue bhaktabahadurthapa/churncue Production-oriented customer-retention intelligence that uses deterministic machine learning to predict churn and generate prioritized rescue reports, governed through MCP tools. | |
| unipile-linkedin-mcp bhaktatejas922/unipile-linkedin-mcp Enables AI assistants to interact with LinkedIn for search, messaging, connections, and Sales Navigator features via the Unipile API. | |
| diffsorted bhakti0725/diffsorted Splits messy, multi-concern git diffs into focused groups and generates a clear, accurate commit message for each, exposed as an MCP server for use with MCP-compatible clients. | |
| Expense Tracker MCP Proxy bhakti259/-expense-tracker-mcp-proxy A proxy server that connects to a remote FastMCP expense tracker, enabling users to add, list, update, delete, and summarize expenses with categories and date ranges through natural language. | |
| expense-tracker-mcp-server bhakti259/expense-tracker-mcp-server Enables natural language expense tracking and management via Claude Desktop, supporting adding, listing, summarizing, updating, and deleting expenses with flexible date parsing and category filtering. | |
| Ops Copilot MCP Server bhaktofmahakal/ops-copilot-mcp Enables AI assistants to detect and investigate e-commerce payment-fulfillment discrepancies, create durable escalation tickets, and track resolution status. | |
| frontend-dev-mcp bhaltair/frontend-dev-mcp An MCP server that provides tools for frontend development, including i18n issue detection, OpenAPI type generation, and project structure analysis. | |
| MCPOSprint bhandzo/mcposprint An MCP server that enables users to print markdown tasklists, Notion tasks with QR codes, and arbitrary images directly to ESC/POS thermal printers over USB. It includes specialized tools for task processing, automated card generation, and | |
| mcp-server-groq bhanu-teja-vce/mcp-server-groq Enables AI tools to route high-speed inference and code analysis to Groq's LLaMA 3.3 70B engine via fast chat and code summarization tools. | |
| DarkLens Compliance & Dark Pattern Auditor bhanu403/darklens-mcp Autonomous dark pattern detection and GDPR, CCPA, EU DSA, and FTC compliance auditor for AI coding agents in Cursor, Windsurf, Claude, and Cline. | |
| Nexla MCP Document Q&A Server bhanunikhil/mcp-server_nexla Enables querying PDF documents using natural language with grounded answers and source citations via a local RAG pipeline. | |
| MCPServer bhanuprakashdadi145/mcp-server A production-ready MCP server built with Python, exposing 17 tools to manage users, products, and orders via a JSON-backed REST API, ready for Claude Desktop and any MCP client. | |
| mcp_filesystem_server bhanuprasadpudi/mcp-integration Enables agents to read, search, batch process, and watch directories of resume files via JSON-RPC MCP methods and resource discovery. | |
| Platform MCP Server bhanushakya2004/rivalscope Enables AI assistants to access competitive-intelligence signals, reports, and memory through a tenant-scoped MCP endpoint with security controls. | |
| code-knowledge bhanutejai4e/code-knowledge Drops two local, zero-egress MCP servers (Serena for LSP and CodeGraph for call/import graph) into Claude Code, enabling code navigation and analysis without API keys or data leaving the machine. | |
| Playwright MCP Server bhanutj93/mcp A Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, generate test code, scrape web content, and execute JavaScript in real browser envir | |
| AI Cost Lab MCP Server bhanuvadlakonda/ai-cost-lab Enables clients to run read-only, deterministic tool calls that compare text-model API costs, estimate workflow costs with retries and escalations, and retrieve synthetic workflow and infrastructure examples. | |
| cubebench bharat2808/cubebench Enables agent harnesses to participate in deterministic Rubik's Cube benchmark matches, including creating, starting, and solving runs with authoritative timing and result verification. | |
| CubeBench bharat2808/rubiks-cube-bench Enables external agent harnesses to connect over MCP to a deterministic Rubik's Cube benchmark arena, start and submit timed Sprint or Live solving runs, and retrieve rules, scrambles, results, and signed leaderboard records without calling | |
| mcp-registry-finder bharat3645/mcp-registry-finder Enables searching the official MCP Registry for servers, inspecting details, and generating install commands directly from within an agent session. | |
| Voraxx MCP Server bharat3645/voraxx-mcp-server A minimal, dependency-free MCP server that gives AI agents three real, read-only security-orchestration tools: cve_lookup, shodan_host_lookup, and nuclei_scan. | |
| Concur Expense MCP Server bharath2020/concur-mcp An MCP server for managing SAP Concur expense reports, allowing AI agents to create and update expenses, attach receipts and attendees, and read report data, while leaving submission and approval to humans. | |
| houdini-mcp bharathadolf/houdini-mcp An MCP server for SideFX Houdini that enables AI assistants to interactively control, construct, inspect, and visually verify 3D procedural scenes through tools like node creation, parameter editing, viewport capture, and rendering. | |
| Storywriting-MCP bharathadolf/storywriting-mcp An MCP server providing 67 tools for AI-assisted storywriting, world-building, character development, screenplay generation in industry formats (Fountain, FDX, PDF), storyboards, and production analytics. | |
| Intermcp bharathcoorg/intermcp Ultra-fast, safe Model Context Protocol (MCP) engine and multiplexing hub in pure Rust, built for Interlayer Blockchain and open for all. | |
| archdiagram bharathgnana/archdiagram MCP server for generating architecture diagrams with official vendor icons from natural language descriptions. Provides tools to validate specs, render diagrams, search icon catalog, and list available services. | |
| knowledge-forge-mcp bharathgnana/knowledge-forge Enables AI coding tools to turn a list of links into a verified, browsable knowledge base with grounded summaries via MCP tools for update, validation, and enrichment. | |
| Financial Intelligence MCP Server bharathid9/mcp-server A production-grade MCP server that provides financial ML tools including RAG search, anomaly detection, contract summarization, vendor graph analysis, and model drift monitoring using entirely free, open-source components. | |
| Kubernetes MCP Server bharathmadvar123/kubernetes-mcp-server Enables secure Kubernetes operations with configurable security modes, supporting core Kubernetes resources, Istio service mesh, and Helm chart management through natural language. | |
| Whois MCP bharathvaj-ganesan/whois-mcp A Model Context Protocol server that allows AI agents to perform WHOIS lookups, enabling users to directly ask the AI about domain availability, ownership, registration details, and other domain information. | |
| Climate MCP Server bharathvardhan/climate-funds-update-integration-for-climategpt-using-structured-mcp-tools Exposes 26 structured analytical tools over Climate Finance Update datasets, enabling fund-level financial analysis, portfolio aggregations, and data quality diagnostics without requiring the client to write data access code. | |
| Canvas-MCP bharathvyaas/canvas-mcp Relays a locally running Microsoft Canvas Authoring MCP server to remote MCP clients, enabling natural language editing and control of Power Apps Canvas apps through a WebSocket bridge. | |
| TradingView MCP Bridge bharatjaiytugan/trade-mcp Enables an AI assistant to interact with a locally running TradingView Desktop app for chart navigation, indicator and price analysis, Pine Script development, drawing, alerts, replay practice, screenshots, and workflow automation via Chrom | |
| TradingView MCP Bridge bharatjaiytugan/tradeview-mcp Enables AI assistants to interact with a locally running TradingView Desktop app via Chrome DevTools Protocol for chart analysis, Pine Script development, drawing, alerts, replay, and workflow automation. | |
| Legal AI MCP Server bharatlt727/legal-ai-mcp Provides AI-powered legal tools including contract review, drafting, legal research, document summarization, and compliance checks via OpenRouter. | |
| mcp-nvidia bharatr21/mcp-nvidia MCP server to search across NVIDIA blogs and releases to empower LLMs to better answer NVIDIA-specific queries. | |
| gemini-deep-research-mcp bharatvansh/gemini-deep-research-mcp An MCP server that exposes Gemini's Deep Research Agent for comprehensive web research. | |
| marketing-data-hub bhargava-r-dev/marketing-data-hub Enables querying and analyzing marketing data from Google Analytics 4, Search Console, YouTube, and optionally Google Ads and Meta Ads, stored in a unified DuckDB database, via natural language in Claude. | |
| SQLite MCP Server bhargava2019/fastmcp-sql-server Implements a Model Context Protocol server that enables natural language interactions with SQLite databases, providing tools to list tables, retrieve schemas, count rows, and execute read-only SQL queries. | |
| Needle Extract MCP bhargavgadekar/needle-extract-mcp Enables small local models to persist and retrieve long-term user facts through remember and recall tools, using SQLite FTS5 keyword search for lightweight memory without external vector databases or heavy VRAM. | |
| PoetryQuill Analytics MCP bhargavi-hash/rhyme-mcp An MCP server that connects Claude Desktop to PoetryQuill's live Supabase database. Ask Claude natural language questions about your platform data. | |
| Weather MCP Server bhargavkahar-pcom/mcp-wheather-server Provides global real-time weather, hourly and daily forecasts, and air quality information via natural language, with no API keys required. | |
| SecureAgentServer bhargavlukka/secure-mcp-agent Enables secure support-ticket and customer-account operations with signed JWT authentication, prompt-injection and tool-poisoning guardrails, and human-in-the-loop confirmation for destructive actions. | |
| TicketDesk MCP bhargavlukka/ticketdesk-mcp Enables AI assistants to search and retrieve support tickets, add notes, close tickets, and access SLA policies through MCP tools, resources, and prompts over Streamable HTTP. | |
| InfraLens MCP bharisagar/infralens-mcp Read-only MCP server for investigating AWS ECS deployment and runtime issues, focusing on ECS Fargate services behind an Application Load Balancer. | |
| Stateful MCP Server on ECS Fargate bharisagar/mcp Enables MCP sessions to survive ECS Fargate deployments by using Redis-backed tool state and stateless Streamable HTTP transport. |
33,951–34,000 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.