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 |
|---|---|
| Enhanced PR Comments Resolver MCP Server abhinandanmishra1/pr-comments-resolver-mcp Fetches GitHub PR comments and intelligently applies fixes directly in workspace files, supporting automatic issue resolution with smart pattern recognition. | |
| dispatch-agent abhinav-mangla/dispatch-agent An MCP server that delegates filesystem operations to a specialized React agent, reducing context usage and improving accuracy for AI applications like Claude Code. | |
| MCP Think Tool Server abhinav-mangla/think-tool-mcp A Model Context Protocol server that provides Claude with a dedicated space for structured thinking during complex problem-solving tasks, helping improve its reasoning capabilities. | |
| MonkeyType MCP Server abhinav-prabhakar/monkeytypemcp A Model Context Protocol server that enables LLMs to interact with all MonkeyType API endpoints, providing access to typing test data, user profiles, leaderboards, and statistics through natural language. | |
| Unstop MCP Server abhinav-prabhakar/unstopmcp Enables users to discover and search for Unstop hackathons through features like filtering, location-based discovery, and detailed event enrichment. It provides MCP tools and prompts that allow LLMs to compare events, plan searches, and acc | |
| Banking Model Context Protocol Server abhinav-pyth/banking_assistant Implements a secure message communication protocol for handling exchanges between the banking chatbot and Azure OpenAI, providing message queuing, reliability, and detailed logging. | |
| Canvas MCP abhinav-ranish/canvas-mcp Enables interaction with Canvas LMS to access courses, modules, files, pages, assignments, submissions, announcements, upcoming deadlines, and syllabus. | |
| ashby-jobs abhinav-sriharsha/ashby-jobs-mcp Search and browse any company's public Ashby job board from Claude Code. | |
| git-remote-mcp abhinav054/git-mcp Enables MCP clients to inspect and modify local git repositories by running commands such as status, log, diff, add, commit, branch, and stash. Push operations are not performed locally; instead diffs are sent to a configurable HTTP API tha | |
| Math Operations MCP Server abhinav140203/remote-math-mcp-server Enables performing arithmetic operations (add, subtract, multiply, divide, power, modulo) via natural language through HTTP SSE transport, allowing integration with Claude or other MCP clients for AI-powered calculations. | |
| hr-assist abhinav29890/industrylevel_agenticai_mcp_hrms_system Enables HR teams to automate employee onboarding workflows through an Agentic AI system integrated with Claude Desktop. | |
| Nova MCP Server abhinav6868/nova-personal-ai-agent Exposes the Nova personal AI agent's tools (web search, notes, long-term memory) over the Model Context Protocol. Allows any MCP-compatible client to use these tools independently of the Telegram agent. | |
| ADB MCP Server abhinav7895/adb-mcp-server Inspect, manage, debug, and run commands on connected Android devices and emulators through natural language. | |
| Bolna MCP Server abhinav7895/bolna-mcp Manage voice AI agents, make calls, run campaigns, and control phone numbers through natural language. | |
| System Resource Monitor MCP Server abhinav7895/system-mcp Provides Claude with real-time system monitoring capabilities, including CPU, memory, disk, network, battery, and internet speed metrics. | |
| pyvisa-mcp abhinav937/pyvisa-mcp Puts PyVISA in front of AI tools so they can discover and drive oscilloscopes and other SCPI instruments over LAN, USB, GPIB, and serial. Builds a per-instrument local knowledge base from identity, manuals, and past commands, then exposes t | |
| tesla-wrap abhinav937/tesla-wrap-editor-mcp Provides tools to list vehicle models, fetch official UV templates, generate AI paint designs, and verify or flatten the resulting wrap files for custom vehicle styling. | |
| Apple Ecosystem MCP abhinavag-svg/apple-ecosystem-mcp Enables Claude to interact with Apple apps on macOS including Mail, Calendar, Contacts, Reminders, Notes, and iCloud Drive for personal productivity tasks like triaging email, managing calendar, and cross-app context. | |
| MCP Headless Gmail Server abhinavbansal17/mcp-headless-gmail Enables reading and sending Gmail messages in headless/remote environments without local credential storage, using OAuth tokens passed directly in API calls for containerized deployments. | |
| MCP abhinavexists/mcp_server A command-line tool that provides access to US weather data through a client-server architecture using MCP and Google's Gemini AI, allowing users to query weather alerts and forecasts using natural language. | |
| Loomline abhinavg08/loomline Enables independent agents to share persistent, project-scoped memory and coordinate work through connected records, evidence, claims, leases, and handoffs. | |
| sui-mcp-server abhinavg6/sui-mcp-server A local-first MCP server that enables AI agents to query the Sui blockchain using gRPC, GraphQL, and Archival Service, with auto-routing and LLM-friendly responses. | |
| IssueOps MCP abhinavharbola/issueops-mcp Enables Claude Desktop and other MCP clients to read GitHub issues and queue triage actions — such as labeling, commenting, closing, or assigning — as pending proposals, with no execute tool exposed to the model. Every proposed change must | |
| personal-context-mcp abhinavkalyan10/personal-context-mcp A portable, Markdown-based memory system for Claude Desktop that separates durable context, working memory, and low-trust notes so AI assistants can stay useful without trapping memory inside one product. | |
| Calculator MCP Server abhinavkannan05/nutriguideai Enables arithmetic operations and calculations through natural language, serving as a learning template for NitroStack. | |
| MCP Travel Concierge Server abhinavmathur-atlan/mcp-travel-assistant Enables comprehensive travel planning by integrating Google Travel Services and Amadeus GDS for dual flight and hotel searches, plus event discovery, weather forecasting, currency conversion, and location services. Combines consumer-friendl | |
| sqlite-reader-mcp abhinavnatarajan/sqlite-reader-mcp A lightweight MCP server that provides read-only access to SQLite databases, allowing users to execute SELECT queries, list tables, and describe table schemas. | |
| cad_mcp abhinavpathak9873/cad_mcp Lets AI clients drive a headless FreeCAD instance to build and inspect parts, check mass and interference, run finite element analyses, and produce drawings, bills of materials and export files. Every call returns numeric results and render | |
| ERPSmith abhinavprakash1992/erpsmith Connects an MCP client such as Claude to an ERPNext/Frappe site, signing in as one of your users so the assistant can read, build, debug and fix customizations like DocTypes, scripts, workflows, permissions, reports and print formats under | |
| Aura abhinavshukla152005-beep/aura-household-agent Enables an Alexa+-style assistant to run household routines with cross-session memory of members, allergies, budgets, curfews and past decisions, autonomously re-planning when new observations contradict the original plan. It also serves ca | |
| hands abhinavshyju/hands-mcp Enables MCP-capable chat clients like ChatGPT, Claude, and Cursor to read, search, edit, and run commands on a local machine, including git operations and browser automation. Runs as a local daemon with workspace path jails, safety modes, c | |
| AgentOps EvalBench MCP abhinavvarma02/agentops-evalbench-mcp Enables LLM evaluation and observability by uploading documents, building test sets, running RAG pipelines, and automatically scoring answers for groundedness, hallucination risk, retrieval quality, latency, and cost, with tools exposed to | |
| Slack MCP Server abhinay8381/slack-mcp-server Enables building AI apps in Slack using the Slack MCP server and OpenAI models. | |
| expense-tracker abhinayychaudharyy/expense-tracker-claude-connector Manages personal expenses through natural language with tools for adding, updating, searching, and summarizing expenses, backed by Supabase. | |
| Couch Call MCP Server abhinv98/couch-call Enables households to run a free, voice-driven play-along game during live sports: it detects big moments in a game feed, opens a short call window, resolves plays, and scores each player's predictions with underdog bonuses and streak multi | |
| PostgreSQL MCP Server abhinv98/postgre-mcp Enables AI agents to query, explore, and analyze PostgreSQL databases through the Model Context Protocol. It provides robust security features including read-only mode, schema restrictions, and query timeouts for safe data interaction. | |
| WiSense-MCP abhinz16/wisense Enables analysis and inference on WiFi CSI sensing data, providing multi-user presence detection and activity recognition through a Model Context Protocol interface. | |
| TravelGenie abhioriganti/travelgenie MCP server for AI-powered travel planning that coordinates flights, hotels, events, weather, currency, and traffic data to generate complete trip itineraries. | |
| Remote Calculator FastMCP Server abhiram4580/mcp-remote-server Enables remote MCP clients to connect over HTTP or SSE across a network and perform arithmetic operations such as addition, subtraction, multiplication, division, and random number generation. Supports configuration of host, port, and trans | |
| HomePilot AI MCP Server abhirammandala/homepilot-ai Enables natural-language household planning by exposing 18 stateful tools that read a household profile and pantry, fetch live weather, plan meals under diet, allergy, time, and budget constraints, compute missing ingredients, and draft sho | |
| Weather MCP abhirampai/weather-mcp-app Provides weather data from Open-Meteo with location search, current conditions, and forecasts, and can render an interactive dashboard directly in MCP hosts. | |
| mathematica-mcp abhirawat4841/mathematica-mcp Enables AI agents to run Mathematica code, control live notebooks, and verify results through natural language. | |
| AI Test Automation MCP Server abhirise1981/ai-test-automation-platform Exposes AI agents as MCP tools to fetch Jira stories, generate BRDs and Playwright test scripts, run tests, and auto-heal broken locators. Integrates with Claude Desktop and Cursor IDE for enterprise-grade test automation. | |
| TradingView MCP Bridge abhiroy17/tradingview-mcp Enables AI assistants to interact with locally running TradingView Desktop for chart analysis, Pine Script development, and workflow automation via Chrome DevTools Protocol. | |
| CodeImpact abhisavakar/codeimpact An MCP server that indexes your codebase and gives AI assistants persistent understanding of project structure, dependencies, and history across sessions, with a self-improving multi-agent system for continuous code quality enhancement. | |
| Expense Tracker Remote MCP Server abhisek0407/expense_tracker_remote_mcp_server Enables managing and analyzing personal expenses through MCP tools, including adding expense records, listing expenses within date ranges, and summarizing spending by category, with expense categories exposed as an MCP resource. | |
| MCP Test Scratch Server abhishantmoe/mcptestscratch A Flask-based MCP server designed for testing deployment on Google App Engine. Provides a deeplink checking endpoint that accepts flattened JSON parameters and forwards them as nested objects to external APIs. | |
| agnost-workers-mcp abhishek-b-r/agnost-workers-mcp Enables MCP clients to call Cloudflare Workers-hosted tools while automatically tracking events, checkpoints, and tool calls in Agnost AI analytics. | |
| flowgraf abhishek-genailytics/flowgraf-mcp AI-native architecture diagramming for MCP clients (Claude Code, Cursor, Windsurf). The calling agent authors the graph (nodes, groups, edges); Flowgraf validates it, lays it out deterministically with ELK, renders an SVG + Mermaid, and ret | |
| Swagger MCP Server abhishek-iiit/swagger-mcp-server A lightweight server that enables interaction with the Swagger Petstore API using the Model Context Protocol, allowing operations on pets, stores, and users through dynamically loaded OpenAPI specifications. |
23,101–23,150 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.