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 |
|---|---|
| ReproGate adimalkar/mcp-repro-gate Enables action-bound authorization and verifiable evidence contracts for MCP tool execution, offering deterministic action planning, policy decisions, and one-use capability tokens tied to exact action envelopes. | |
| Apple RAG MCP adimowis/appler Provides AI agents with instant access to official Apple developer documentation, Swift docs, design guidelines, and Apple Developer YouTube content through advanced semantic and hybrid search capabilities. Features AI-powered reranking for | |
| ableton-mcp adindotdev/ableton-mcp An MCP server that enables Claude to control Ableton Live in real-time via the AbletonOSC bridge. It allows users to manage playback, create tracks, write MIDI, and adjust mixer or device parameters using natural language commands. | |
| fastmail-mcp adinschmidt/fastmail-mcp Unified MCP server for Fastmail email (JMAP), calendar (CalDAV), and contacts (CardDAV). Enables sending emails, managing events, and syncing contacts through natural language. | |
| splitwise-mcp adinschmidt/splitwise-mcp MCP server that exposes every endpoint from Splitwise's public self-serve API docs as MCP tools, covering 27 operations for managing expenses, users, and groups. | |
| grpcmcp adiom-data/grpcmcp MCP server that will proxy to your gRPC backends via reflection or descriptors file. | |
| mcp-lancedb adiom-data/lance-mcp A Model Context Protocol (MCP) server that enables LLMs to interact directly the documents that they have on-disk through agentic RAG and hybrid search in LanceDB. Ask LLMs questions about the dataset as a whole or about specific documents. | |
| MCP-IT Fastify adiramsalem/mcp-it A Fastify plugin that automatically converts API routes into Model Context Protocol tools, enabling AI assistants to directly interact with your API. | |
| AI-Project-Planner-Agent adiratnam/ai-project-planner-agent Enables AI project feasibility evaluation and solution planning through structured reasoning stages, using Gemini API and web search for up-to-date research. | |
| AI Research Agent adiratnam/ai-research-agent Enables autonomous web research, file management, and dynamic UI dashboard generation through Gemini LLM and FastMCP. | |
| Hilanet MCP adird/hilanet-mcp A satirical MCP server providing HR-related tools that simulate actions in a corporate dystopia, such as increasing salaries, scheduling mandatory fun events, and generating corporate jargon. | |
| ScholarOCR adiroy911/scholarocr Enables AI chat clients to extract exam papers and academic documents into a structured, source-traceable representation once, then retrieve, verify and export it as JSON, Markdown, searchable PDF, DOCX, LaTeX or CSV/XLSX without re-running | |
| MCP Datadog Playcourt adisaputra10/mcp-datadog Enables monitoring and querying of Datadog metrics for Kubernetes clusters, APM traces, infrastructure hosts, and databases through a unified interface. | |
| Trello MCP Server adise211/trello-mcp-server A Model Context Protocol (MCP) server that provides AI assistants with access to Trello's functionality. This server enables AI models to interact with Trello boards, lists, and cards programmatically. | |
| zepp-mcp adisudirta/zepp-mcp Enables MCP clients to access Zepp/Amazfit health and fitness data such as steps, sleep, heart rate, workouts, and user profile information via tools. | |
| LazyRoom MCP Server adit-0132/lazyroom Enables AI agents to drive a full photo-editing engine through validated, non-destructive operations — exposure and colour grading, effects, geometry, text/watermarks, style matching from a reference image, natural-language looks, and batch | |
| Tend MCP Server adit-parab-06/tend-alexa-mcp Enables voice-first family care coordination through Alexa+, exposing tools for medication logging, routine check-ins, shared sibling tasks, and deterministic spoken briefings. It supports OAuth-secured Alexa+ interactions and an interactiv | |
| jagabukit-mcp aditdinov-eng/jagabukit-mcp Enables MCP clients to read reception data from a bookings sheet through five query tools for recent messages, conversation history, bookings, villa search, and reception statistics. | |
| gemini-spark-mcp aditechio7x/gemini-spark-mcp Deployable MCP server for GitHub and Vercel integration. Enables creating repos, pushing multiple files in a single commit, deploying projects to Vercel, managing environment variables, and combined deploy workflows via natural language. | |
| Personal-reflection-mcp adithi1367/personal-reflection-mcp A FastMCP server for journaling, habit tracking, and task management with SQLite storage. | |
| COS-MCP adithya-1010010/cos-mcp COS-MCP is an MCP server that provides AI-powered organizational continuity planning. It maintains a knowledge graph of employees, systems, projects, and relationships, and exposes tools, resources, and prompts for knowledge graph visualiza | |
| NASA MCP Server adithya1012/nasa-mcp-server Provides access to NASA's public APIs including Astronomy Picture of the Day, Mars Rover Images, and Near Earth Objects data, enabling users to query and retrieve space-related information through natural language. | |
| Doorstep MCP Server adithya4001/doorstep Enables compatible assistants to record and track parcel or visitor arrivals, acknowledge them, retrieve handoff instructions, complete or cancel handoffs, check home status, and toggle quiet mode through MCP tools. | |
| Image Generation MCP Server adithyalabs-ind/image-gen-mcp An integration server that connects to gpt-image-1 and Gemini imagen4 models, allowing users to generate high-quality images from text descriptions via simple API endpoints. | |
| HandoffOS adithyanandanarun/handoffos An enterprise workflow intelligence MCP server that reconstructs events into live workflow state, detects bottlenecks with deterministic rules, and provides evidence-based explanations and actions. | |
| TokLedger adithyanraj03/tokledger Exposes a local inference ledger over MCP stdio, letting agents query request counts, token usage, TTFT, energy consumption, local costs, cloud-equivalent costs, savings percentages, and per-model breakdowns from an OpenAI-compatible proxy' | |
| MCP File Manager adithyenkandasamy/mcp-file-managment Enables listing, reading, and searching local files and directories through MCP tools. | |
| CodeWeaver adithyx-0/codeweaver An MCP server that reads a clinical note and returns ranked ICD-10-CM diagnosis code candidates with clinical reasoning, validated against official CMS coding constraints. | |
| crypto_price_tracker adity-star/mcp-crypto-server An MCP server that enables AI agents to fetch real-time cryptocurrency prices and market data using the CoinGecko API. | |
| RepoPilot MCP adity0208/repopilot-mcp Enables LLM-powered developer environments to discover and evaluate potentially beginner-friendly GitHub issues using explainable heuristics, clear rationale, and direct evidence links over stdio. | |
| claude-memory-graph aditya-20121/claude-memory-graph Enables Claude to recall and query past conversations through a local knowledge graph and vector index, with tools for searching memory, retrieving related entities, and adding new memories. | |
| vs-code-mcp-server aditya-613/vscode-mcp-server Provides AI assistants with VS Code integration for file operations, command execution, project analysis, and development workflow automation. | |
| MCP-Finance-Reconciliation aditya-j101/mcp-finance-reconciliation Automates month-end close reconciliation tasks including bank statement matching, GL account reconciliation, intercompany balance checking, and close task tracking. | |
| mcp-clinical-doc-agent aditya-khadye/mcp-clinical-doc-agent Enables analysis of clinical trial protocols using MCP tools for document listing, entity extraction, adverse event clustering, and summarization. | |
| Exa MCP Server aditya002p/mcp-server Enables AI assistants to perform web searches, research papers, Twitter searches, company research, URL crawling, and LinkedIn searches using the Exa AI Search API for real-time web information. | |
| Taskboard MCP Server aditya020402/mcp Integrates GitHub Copilot Chat with your Taskboard instance to manage workspaces, boards, lists, and cards using natural language. It supports full task lifecycle operations, searching capabilities, and knowledge base queries via RAG. | |
| AWS Compliance MCP Server aditya0529/aws-compliance-mcp-server Enables LLMs to perform automated compliance scanning of AWS infrastructure against PCI-DSS, CIS, and Well-Architected frameworks. It provides tools for scanning, remediation, and audit report generation. | |
| mcp-from-scratch aditya0si/mcp-from-scratch Enables clients to interact with a bundled documentation corpus through MCP tools and resources over HTTP or stdio, and provides a trajectory evaluation harness for grading agent performance. | |
| DevAssist MCP Server aditya1335/devassist-mcp-server Enables AI assistants to interact with GitHub data and Codeforces competitive programming analytics, including profiles, repositories, commits, PRs, issues, contest history, weak-topic analysis, and problem recommendations. | |
| LocalForge aditya1503/mcprelay Enables hybrid agentic coding by delegating token-heavy implementation, editing, and test-debug loops to local open-source models while frontier cloud models handle architecture and review, reducing premium API token usage and keeping code | |
| Movie Booking MCP Server aditya17koushik/mcp-movie-booking-server Enables searching for movies, checking Google Calendar for conflicts, and booking tickets with seat type and INR pricing, all through natural conversation. Supports demo mode without API keys. | |
| AI Competitive Research Assistant (NitroStack MCP) aditya201206/gapfinder Automates competitive research for startup ideas by executing a 7-step pipeline including idea understanding, competitor discovery, profile extraction, feature comparison, market gap analysis, innovation scoring, and report generation. | |
| MCP Calculator Server aditya24023022/mcp-calculator-server-using-model-context-protocol-mcp-sdk A lightweight TypeScript-based MCP server that demonstrates how to build custom MCP tools by implementing a simple addition calculator. Serves as a starting point for building MCP-compatible tools. | |
| OpenTool aditya251610/opentool OpenTool is an MCP server that provides AI agents with secure, authenticated access to a wide range of tools (GitHub, Notion, Slack, etc.) through a single MCP connection. It is fully open-source and self-hostable. | |
| repo-atlas-mcp aditya31398/repo-atlas-mcp Provides a graph-based code analysis to coding agents, enabling tools to trace call dependencies, assess change impact, and identify hotspots using tree-sitter and Neo4j. | |
| Strapi MCP Server aditya69505/mcp-server A Strapi v5 backend that exposes MCP endpoints for Google Search Console and Meta Ads, enabling AI agents to automate SEO and marketing workflows. | |
| lentera-aseprite-mcp adityaairlangga12/lentera-aseprite-mcp Custom MCP server that automates pixel art manipulation, layers, animation frames, palette quantization, and spritesheet export in Aseprite for the Lentera Pudar project. | |
| lentera-godot-mcp adityaairlangga12/lentera-godot-mcp Custom MCP server for automating Godot Engine 4.x, enabling direct scene manipulation, node inspection, GDScript injection, and runtime testing via a WebSocket bridge. | |
| gitatlas adityaarakeri/gitatlas Enables coding agents to explore a repository map via MCP, with tools for briefs, scoping, symbol lookup, module details, and freshness checks. | |
| mcp-github-issues adityaaravind/mcp-github-issues Exposes GitHub issue operations as tools for LLM agents, enabling listing, creating, commenting on, closing, and searching issues via natural language. |
23,801–23,850 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.