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 |
|---|---|
| pingpong ajaxdude/pingpong Pingpong is an MCP server for oh-my-pi that gives your AI agent a local code reviewer using a local LLM (llama.cpp) for automated code reviews after task completion. | |
| Agentic Financial Research MCP Server ajay-kumar64/agentic-financial-research-assistant Provides tools for RAG-based financial document retrieval, financial calculations, Yahoo Finance stock data, and portfolio analysis via JSON-RPC 2.0 protocol. | |
| ProductPilot MCP ajay66-sketch/productpilot-mcp An MCP server that helps digital product creators go from idea to a zipped, listing-ready product — including market research, product generation, SEO, listing copy, pricing, and Gumroad/Etsy preparation. | |
| askdocs ajay7605/askdocs Enables MCP clients such as Claude Code and Cursor to search a documentation corpus, read specific pages, and locally ask grounded questions with verified citations over stdio or Streamable HTTP. | |
| MCP Hospital Assistant ajay800800/doc_mcp An intelligent hospital appointment management system that allows users to add doctors/patients, book appointments, and view medical schedules through both a manual UI and an LLM-powered assistant interface. | |
| Weather MCP Server ajayamal/mcp-server Provides weather forecasts and active alerts for US locations using the National Weather Service API. It supports both local stdio and remote HTTP/SSE transport modes for flexible integration with MCP clients. | |
| expense-tracker ajayanta/expense-tracker-mcp-server Enables personal expense management via natural language, including logging, listing, summarizing, and removing expenses, with data stored locally in SQLite. | |
| Aegis MCP ajaybe-ops/aegis-mcp Connects AI agents to structured vulnerability intelligence from NVD, EPSS, KEV, and OSV, enabling deterministic, policy-scored incident triage, CVE lookup, vulnerability search, and package scanning through auditable MCP tools. | |
| PR Sentinel MCP Server ajaychauhan29dev-cell/pr-sentinel Enables MCP clients and LLM agents to fetch pull-request diffs, map changed files to tests, run affected tests in a sandboxed workspace, and post review comments or labels to GitHub, with dry-run and fixture demo modes. | |
| GitHub Webhooks MCP Server ajaychinthapalli/github-webhooks-mcp-server A Model Context Protocol (MCP) server for managing GitHub webhooks at both organization and repository levels. | |
| Jenkins to GitHub Actions MCP Server ajaychinthapalli/jenkins-to-github-actions-mcp-server Converts Jenkins declarative pipelines into GitHub Actions workflow YAML files, facilitating migration from Jenkins to GitHub Actions CI/CD. | |
| Apple Calendar MCP Server ajayjohn/mcp-server-apple-calendar Connects to Apple Calendar via Eventlink to fetch and create events with natural language date support. | |
| Grocery Search MCP Server ajaykallepalli/mcp_food_search Provides grocery price and nutritional information search capabilities, allowing AI agents to search for food products, compare prices, and analyze nutritional content across different grocery stores. | |
| TravelGenie ajaykumarbalakannan/travelgenie Coordinates flights, hotels, events, weather, currency, and traffic data through a single MCP server, enabling comprehensive trip planning via natural language prompts. | |
| tradingview-mcp ajaymojo21/tradingview-mcp Personal AI assistant for your TradingView Desktop charts. Connects Claude Code to your locally running TradingView app via Chrome DevTools Protocol for AI-assisted chart analysis, Pine Script development, and workflow automation. | |
| Job Outreach MCP Server ajayranwa/job-outreach-mcp-server Automates job outreach by finding companies, discovering contacts, generating personalized emails with AI, and tracking campaigns. | |
| Transcriptor ajaysharmadeveloper/transcriptor-mcp-public Enables local, on-device transcription of local files or URLs, returning a job ID and making transcripts, segments, and full-text search available as processing completes. Uses Whisper large-v3 with SQLite storage and stdio transport, so au | |
| communication-mcp-server ajaysingh16601/communication-mcp-server MCP server that provides email communication tools (send email, health check, list providers) via SMTP, accessible over HTTP/SSE for remote AI clients like Claude Desktop. | |
| Gmail MCP Server ajaysmb/gmail-mcp Provides MCP clients with safe local access to read, search, and send Gmail messages using token-efficient outputs and explicit permissions. | |
| Elevance MCP Atlassian Server ajaysonicarelon/atlassian-mcp Provides Jira and Confluence integration for AI assistants, enabling natural language management of issues, projects, sprints, pages, comments, attachments, and more with 72 tools. | |
| HubSpot MCP Server ajaystream/hubspot-mcp-custom Enables AI clients to seamlessly take HubSpot actions and interact with HubSpot data, allowing users to create/update CRM records, manage associations, and gain insights through natural language. | |
| sqlite-mcp-local ajaytechgenius/sqlite-mcp-local Enables read-only querying of a local SQLite database via MCP, with tools to list tables, retrieve schema, and execute SELECT/WITH/EXPLAIN queries. | |
| PM Release Notes MCP ajayvancouver/pm-release-notes-mcp Enables AI assistants to draft customer-ready or internal release notes from work closed in GitHub, Jira, or Linear, using deterministic fetching and rule-based categorization that flags uncertain items in a review list instead of guessing. | |
| kryonex-mcp ajayvtl/kryonex-mcp A TypeScript-based MCP server implementing a simple notes system with resources, tools for creating notes, and prompts for summarization. | |
| ScrapeForge MCP Server ajazhussainsiddiqui/scrapeforge Enables MCP clients like Claude and Cursor to perform zero-config structured web scraping, generating and caching LLM-built CSS extraction schemas per page template and reusing them across similar URLs. | |
| OpenCodeMode ajbisht/open-codemode-gateway Enables an LLM to orchestrate multiple downstream MCP tools inside one isolated sandbox in a single turn, filtering intermediate results in memory and returning only the final output to cut context tokens. | |
| sonic-mcp ajbogo9/sonic-mcp MCP server that connects Claude Code to Sonic Pi for AI-assisted beat making, enabling live code execution and pattern management. | |
| supercollider-mcp ajbogo9/supercollider-mcp Connects Claude Code to SuperCollider for AI-driven music composition, supporting real-time playback and non-realtime audio rendering at 50-150x realtime speed. | |
| Gmail MCP Server ajbr0wn/gmail-mcp-server An integration server that provides Claude Desktop access to Gmail, enabling users to view recent emails and search their Gmail inbox using natural language commands. | |
| Momentum MCP Server ajc308/momentum Enables AI assistants to read and log Peloton workouts, Apple Health metrics, and weigh-ins, view an adaptive training plan, search and stack Peloton classes, and manage goals through natural language. | |
| MCP Venezuela FakeNews ajcastrob/mcp-venezuela-fakenews A Model Context Protocol server for combating disinformation about Venezuela, integrating real fake news patterns with optional web search. | |
| token-shrink ajdev0/token-shrink Enables AI agents to obtain a compressed code context where the active file is fully included and dependency files are reduced to type signatures, interfaces, and exports, cutting token usage while preserving code shape. | |
| dbt MCP Server ajdoyl2/claude-data-stack-mcp Provides intelligent dbt assistance through Claude Code integration, enabling users to perform dbt CLI operations, explore project metadata, and execute SQL queries against DuckDB warehouse with context-aware support. | |
| Bangalore BMTC Mobility Connectivity Platform ajeetraina/bengaluru-bmtc-mcp Provides real-time access to Bangalore's public transportation information including bus tracking, schedules, routes, and service updates to improve passenger experience. | |
| JetsonMCP ajeetraina/jetsonmcp Connects AI assistants to NVIDIA Jetson Nano systems for edge computing management, enabling natural language control of AI workloads, hardware optimization, and system administration tasks. | |
| Meetup MCP Server ajeetraina/meetup-mcp-server A Model Context Protocol implementation for managing context, prompts, and model interactions in Meetup applications. | |
| marimo-inspect ajegorovs/marimo-mcp-cowork Enables inspecting and editing live marimo notebooks via a FastMCP server, offering tools for managing cells, variables, and execution. | |
| AJEMS MCP Connector ajemssolutions/mcp Enables AI assistants to query and optionally modify AJEMS workspaces, including apps, forms, and records, without requiring user login. | |
| LLM Radar ajentsor/llm-radar MCP server that provides AI assistants with real-time, current information about AI models from OpenAI, Anthropic, and Google, including pricing, capabilities, and context windows. | |
| Amazon Rainforest Travel Guide ajey95/mcp An AI-powered travel assistant connected to Claude via MCP that helps users plan Amazon Rainforest trips by providing directions, hotel recommendations, adventure spots, cultural sites, and travel precautions. | |
| Ping Host MCP ajezziriglos-bot/prueba_mcp Minimal MCP server that enables network connectivity testing via ping commands from VS Code Chat. Features cross-platform support and secure execution using execFile with input validation to prevent command injection. | |
| mcp-qr-business-card ajfrai/qr-business-cards-mcp Create public profiles and make business cards | |
| Anatomy Engine ajfutures/anatomy-engine Provides a 3D full-body anatomy and biomechanics engine with 22 MCP tools for querying anatomical structures, connections, and clinical information, plus an interactive 3D viewer. | |
| cursor-doctor ajgreyling/cursor-doctor An MCP server that audits a project for documentation, rules, skills, and knowledge artifacts, compares against a reference concept catalog, and generates a prescription plan with frontmatter todos to guide creation of missing or incomplete | |
| LevelField MCP Server aji-q/levelfield Enables agents to assess structural information-asymmetry risk in prediction-market event contracts from contract text alone, with deterministic scoring and no LLM API dependency. | |
| Remote MCP Server ajiadiyudha/remote-mcp-server Enables deploying a remote MCP server on Cloudflare Workers with OAuth, allowing MCP clients like Claude Desktop to call tools over the internet. | |
| Sub-Agents MCP Server ajimenez15629/sub-agents-mcp Enables running reusable Markdown-defined coding agents from any MCP-compatible client through a selected coding CLI backend and returning results to the same conversation. It supports delegating code review, test writing, investigation, an | |
| catalog-context-graph ajinb/catalog-context-graph Enables AI agents to query Backstage catalog data as a typed graph over MCP, answering blast-radius, ownership and escalation, dependency, path, change-risk, and catalog-drift questions through bounded read-only tools. | |
| rs-radar ajinkya-cs/rs-radar Enables AI assistants to scan crypto and US stocks for beta-adjusted relative strength, momentum signals, RSI readings, and entry/stop/target trade plans, with watchlists validated against live data. Also lets users start a persistent backg | |
| markproof-mcp ajinkya710/markproof-mcp Lets AI agents mark the images and audio they generate, as the EU AI Act's Article 50 requires: an invisible watermark (TrustMark for images, AudioSeal for audio) plus a signed C2PA manifest (Content Credentials), in one tool call. Tools: m |
25,351–25,400 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.