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 |
|---|---|
| codeforge-mcp anketpratapsingh/codeforge-mcp Enables MCP-compatible clients to delegate senior software engineering tasks like code generation, review, Jira management, and architecture recommendations to a model with a senior engineer persona. | |
| tokencost-mcp-server ankit-aglawe/tokencost-mcp-server An MCP (Model Context Protocol) server that provides real-time LLM token pricing data for 60+ AI models across 15 providers. | |
| Pantry Pal ankit-garg2/pantry-pal-mcp Enables Alexa+ users to manage household pantry inventory by voice, including adding and using items, tracking expirations, discarding waste, generating recipes and meal plans, and maintaining shopping lists. | |
| log-reader-mcp ankit-jhajhria/log-reader-mcp MCP server to start, monitor, search, and detect errors in logs from any project, even those without log files. | |
| Media_MCP ankit-lama/media_mcp A modular MCP-style server for image and video processing, offering commands for tasks like background removal, resizing, compression, OCR, video trimming, GIF creation, and subtitle extraction via simple CLI tools. | |
| Research MCP Server ankit-lama/newspaper_mcp A local, rule-based MCP server for searching and analyzing academic papers from arXiv. Enables paper search, ranking, smart summarization, keyword extraction, and citation generation without API keys or LLM calls. | |
| ROS & LLM Integration Bridge ankit-paliwal/mcp-server-for-ros Enables large language models to interact with ROS robots seamlessly, allowing natural language control, real-time sensor monitoring, and autonomous task execution without modifying existing robot code. | |
| postman-mcp-server ankit-roy-0602/postman-mcp-server Enables AI assistants to create, manage, and interact with Postman collections, workspaces, environments, and API requests directly from conversations. | |
| android-docs-mcp ankit-verma-209171/android-docs-mcp An MCP server that gives AI agents direct access to developer.android.com — search docs, look up API references, browse packages, and check release notes. | |
| S&P 500 MCP Server ankit0489/sp500-mcp-server Enables users to query S&P 500 company fundamentals, annual financial metrics, historical OHLCV price data, news sentiment, executive officers, and SEC filings stored in Supabase through dedicated MCP tools. Also ships embedded MCP App UI r | |
| Claude Telegram Supercharged ankit59685/claude-telegram-supercharged Enables users to run and control Claude Code from Telegram around the clock, with two-way voice notes, persistent memory across restarts, scheduled reminders, and a live view of each tool call as it runs. | |
| AWS Billing MCP Server ankit8volt/aws-cloud-cost-analyser-mcp Enables users to analyze AWS costs, track spending trends, and detect anomalies directly within Claude Desktop using the AWS Cost Explorer API. It provides tools to identify major cost drivers and compare usage across different time periods | |
| Host Terminal MCP ankitaa186/host-terminal-mcp Enables AI assistants to execute terminal commands on a host machine with configurable, granular permission controls and safety protections. It features multiple security modes, including allowlists and manual approval, to ensure safe comma | |
| StockPilot-MCP-Server ankitachotaliya2310/stockpilot-ai Provides inventory analysis, risk assessment, demand forecasting, and recommendation generation tools for retail inventory optimization via a FastMCP stdio server. | |
| fraud-detection-risk-status ankitanaik13/fraud-detection-pipeline Exposes account risk status from a fraud detection pipeline, returning risk scores, flagged transaction history, and LLM-generated explanations via the get_account_risk_status tool. | |
| StudyBuddy ankitbelbase17/mcp-demo An educational MCP server demonstrating the MCP protocol with simple tools like rolling dice and returning vocabulary words. | |
| AIVA Credit Card MCP Server ankitbhatnagartech/aiva-creditcard-mcp A decoupled, stateful MCP server and HTTP REST Gateway styled as a Banking Credit Card IVR Integration, bridging core banking mainframes with conversational voice AI frameworks. | |
| Medify UCAT MCP Server ankitforcode/medify-mcp-server MCP server for Medify UCAT accounts that authenticates as a member, pulls completed mock scores and practice analytics, and exposes tools for score trends, question-type weaknesses, timing sinks, and practice recommendations. | |
| EasyPR ankith34/easypr Enables AI assistants to read-only inspect an approved repository, surface setup and test commands from project files, and rank relevant code for a given issue so beginners can understand a project and prepare a first pull request. | |
| carechronicle-mcp ankithraj-1312/carechronicle Enables LLMs to interact with clinical patient records using tools for document ingestion, structured conversion, patient profiling, record listing, search, and secure Q&A over patient documentation. | |
| Academic Paper Search MCP Server ankithughes89/academic-search-mcp-server Enables LLMs and compatible clients to search academic papers, retrieve detailed metadata and abstracts, access full-text content when available, and perform topic searches with optional date filters via MCP tools. | |
| Quant Desk TradingView MCP ankitjha67/tradingview-mcp Analyzes the instrument currently open on your TradingView chart using 311 published quantitative models and free market data, returning a confidence-scored verdict with position sizing. Supports universe scanning and verified Pine Script e | |
| engram-mcp ankitjm/engram-mcp Integrates an Engram brain with Claude Code via MCP, providing tools for searching, retrieving, and adding memories. | |
| reqlog ankitksr/reqlog Provides AI coding agents with tools to query, search, and analyze persisted HTTP request logs, enabling efficient debugging without terminal noise. | |
| Notion MCP Server V2 ankitmalik84/agentic_longterm_memory A comprehensive Model Context Protocol (MCP) server for Notion integration with enhanced functionality, robust error handling, production-ready features, and bulletproof validation. | |
| Octopus Deploy Official MCP Server ankitmoon886/mcp-server Enables AI assistants to inspect, query, and diagnose problems in a continuous delivery platform, and to perform release, deployment, runbook, task, tenant, and related operational actions with configurable read-only or write access. | |
| google-workspace-mcp-with-script ankitohlan/google-workspace-mcp-with-script MCP server for Claude Code CLI that integrates with Google Workspace, enabling management of Docs, Sheets, Drive, Gmail, Calendar, and Apps Script. | |
| packet-tracer-mcp ankitrajput07/packet-tracer-mcp Enables external control of Cisco Packet Tracer 9.0 through MCP, allowing users to create network topologies, configure routers, and launch simulations from MCP clients. | |
| slop-guard ankitramirez46/slop-guard Enables agents to analyze text or files and score prose from 0–100 for formulaic AI writing patterns using rule-based heuristics, returning violations, band labels, and concrete advice. | |
| MCP LLMS-TXT Documentation Server ankitrautela333/langchain-mcp An MCP server that enables users to fetch and audit documentation from user-defined llms.txt index files. It provides tools to list documentation sources and retrieve content from specific URLs with built-in domain access controls for secur | |
| release-doc-mcp ankitscherian/release-doc-mcp Finds version and image tag from latest successful GitHub Actions workflow run and creates a Confluence release page documenting that information. | |
| Stocker ankitsurana/stocker Enables NSE stock market research with screening, quotes, peer comparison, watchlists, alerts, and strategies using natural language. | |
| Cinema4D MCP Server ankitverma57803/cinema4d-mcp Enables users to create and manipulate Cinema 4D scenes through natural-language prompts by exposing tools for primitives, cameras, lights, materials, Redshift, MoGraph, dynamics, rendering, and custom Python execution. | |
| mcp-helmet ankitvirdi4/mcp-helmet A production middleware toolkit for MCP servers providing auth, health checks, graceful shutdown, and transport ergonomics, enabling rapid development of robust MCP servers. | |
| scrcpy-mcp ankitzhang46/scrcpy-mcp Enables AI agents to see and control Android devices over ADB and scrcpy, with image-returning screenshots, taps, swipes, typing, app and file management, UI element inspection, shell commands, and video/audio streaming or recording. It off | |
| repo-ctx ankkitraj4/repo-ctx Provides a unified context layer for LLMs by storing and retrieving repo-specific and cross-repo patterns via MCP tools, enabling instant context without re-exploring. | |
| Unity MCP Server anklebreaker-studio/unity-mcp-server Provides AI assistants with comprehensive control over Unity Hub and Unity Editor through over 200 specialized tools for project management and scene manipulation. It enables users to perform complex tasks like script creation, asset manage | |
| Math & Calculator MCP Server ankluna72/math-calculator-mcp-server- Provides advanced mathematical utilities including basic arithmetic, statistical analysis, unit conversions, quadratic equation solving, percentage calculations, and trigonometric functions for AI assistants. | |
| Agent Guard anksarvesh-lgtm/agent-guard Enables supervised, crash-resilient autonomous AI pair programming through nine MCP tools that checkpoint task progress in an atomic local DAG ledger, keep the machine awake during long runs, summarize repositories within a token budget, co | |
| Repo Analyzer MCP Server ankur-1garg/mcp An MCP server that analyzes Git repositories and provides Dockerfile creation guidance, running locally using stdio transport. | |
| OmniForge MCP ankur-gaurav161418/omniforge An enterprise-grade MCP server that enables AI coding assistants to securely connect with external tools, APIs, databases, and cloud services through a unified interface, offering structured engineering workflows and multi-client support. | |
| MCP LLDB Server ankur106/lldb_mcp Enables AI assistants to start and manage LLDB debugging sessions, including loading programs, setting breakpoints, stepping through code, and examining memory. | |
| HAR-MCP ankurkumar3012/har-mcp Captures website HAR data via headless Chromium and provides 20 tools for performance/security auditing, API reverse engineering, and code generation. | |
| Google Workspace MCP for Cursor ankush-sw/gdrive-mcp Enables editing existing Docs, Sheets, and Slides in place, plus commenting, sharing, moving, and exporting files with native Google URLs returned. Provides 29 tools across Drive, Docs, Sheets, and Slides, using OAuth keys kept locally in ~ | |
| StoryForge MCP Server ankushchaudhari203-commits/storyforge Enables AI clients to create and manage Jira tickets for Agile backlog items through natural language commands, integrating structured backlog generation with Jira board actions. | |
| github-mcp-server ankushdas1124/github-mcp-1 Enables remote MCP connections to GitHub, allowing users to list repositories, inspect repository details, manage issues, and read file contents via natural language or MCP clients. | |
| HomeOps MCP Server ankushh0027/homeops-ai Enables AI agents to correlate smart-home sensor events into risk-assessed incidents and retrieve deterministic safety-policy decisions through MCP tools, without autonomous physical actions. | |
| Echo MCP ankushsrivastava0626/echo-realtime-gateway Exposes the rooted Amazon Echo Dot's hardware controls, including LED ring, volume, microphone, speaker, and music playback, as MCP tools for local agents to drive. | |
| Katherine Communication MCP anlimi555s/katherine-comm-mcp Enables privacy-preserving detection of content manipulation in AI model providers via cross-lingual self-consistency, with tools for pipeline checks, status monitoring, and cumulative toxicity tracking. | |
| Colab MCP anluin/colab-mcp A Model Context Protocol server that gives Codex and other MCP clients access to Google Colab runtimes—allowing session allocation, command execution, notebook management, file operations, and data transfers. |
29,251–29,300 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.