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 |
|---|---|
| Banking MCP Server abdelhamidfg/banking-mcp-server Demo MCP server for a banking use case that returns raw PII payloads to demonstrate external PII guardrails with OpenShift AI/NeMo Guardrails. | |
| CircuitPilot abdelhayali/circuitpilot AI copilot for PCB design: search real JLCPCB/LCSC parts, build schematics, run ERC, auto-place and autoroute 2-layer boards with DRC, export Gerbers/BOM/pick-and-place, and generate 3D-printable enclosures. Changes appear live in the Circu | |
| AI Guest Post & Backlink Outreach MCP abdell1111/ai-guestpost-outreach-mcp Enables AI assistants to discover niche guest-post prospects, check Gmail for duplicate outreach, and prepare simultaneous Gmail drafts—one HTML cold pitch and one complete pre-written article—for editors. | |
| PDF RAG MCP Server abdellahiheiballa/pdf-rag A Model Context Protocol (MCP) server that provides powerful RAG (Retrieval-Augmented Generation) capabilities for PDF documents. This server uses ChromaDB for vector storage, sentence-transformers for embeddings, and semantic chunking for | |
| @abdelrahmanhsn/jira-mcp abdelrahman-hsn/jira-mcp A Model Context Protocol server that connects your AI IDE to Jira. Query your tickets, active sprint, and issue details directly from GitHub Copilot, Cursor, Claude Desktop, or any MCP-compatible client. | |
| SQL Server MCP Server abdelrahmanghoniem/sql-mcp Enables Cursor AI to interact with SQL Server databases, including querying, schema exploration, report generation, and chart creation. | |
| Frontend-Quality abdelrhmanahmed255/frontend-quality A zero-dependency local MCP server that audits and auto-fixes React/Next.js frontend code smells, unused imports, and responsive UI issues | |
| Azure DevOps MCP Server abdelrhmansror/azuredevopsmcp Enables AI assistants to interact with Azure DevOps repositories and pull requests, including listing PRs, fetching diffs, adding comments, and performing automated code reviews. | |
| Lightning Network MCP Server abdelstark/lightning-mcp Enables AI models to interact with the Lightning Network by providing an MCP-compliant API to pay invoices. | |
| handoff-protocol abdelwahab313/handoff-mcp-server Enables AI coding agents to save task context as a validated JSON document and later restore it as a concise briefing with the objective, status, relevant files and focus lines, decisions, and prioritized next steps. | |
| Thaïs MCP Server abderahmaneyousfi/modelcontextprotocol_thais_api Enables Claude to interact with the Thaïs hotel reservation system, including checking availability, listing room types, retrieving prices, and creating bookings with email confirmation. | |
| gemini-notebook-mcp abderrahim-lectures/gemini-notebook-mcp MCP server for Google NotebookLM that lets AI agents chat with notebooks, add sources, generate audio overviews, and extract citations via a real Chrome browser. | |
| Centreon MCP Server abderrahmane010/centreon-mcp Enables natural-language monitoring and management of a Centreon instance, including real-time status checks, configuration operations, incident response, metrics analysis, and guided host diagnosis, with pluggable authentication and role-b | |
| Skill7 abderraouf-yt/skill7 Provides 634+ curated production-ready AI skills for any MCP-compatible client, covering areas like security, frontend, backend, infrastructure, AI/ML, and architecture. Enables AI agents to access best practices, patterns, and solutions ac | |
| math-mcp abdery/math-mcp Provides LLMs with deterministic math tools for sandboxed expression evaluation, descriptive statistics, primality testing, prime factorization, GCD/LCM, quadratic solving, and base conversion. Every operation runs real code rather than rel | |
| MalwareAnalyzerMCP abdessamad-elamrani/malwareanalyzermcp A specialized MCP server for Claude Desktop that allows executing terminal commands for malware analysis with support for common analysis tools like file, strings, hexdump, objdump, and xxd. | |
| mcp-github-agent abdessamad-y/mcp-github-agent Enables AI assistants to query GitHub data directly through natural language, including user profiles, repositories, issues, and search. | |
| FastAPI Architect MCP abdessamadtzn/fastapi-architect-mcp An MCP server that gives Claude Code IDE-level intelligence for FastAPI projects — semantic code navigation, safe renaming, route inspection, dependency trees, and Pydantic model analysis.
Instead of Claude reading files blindly, it calls | |
| mcp-server-coordinate abdiaden-debug/mcp-server Extracts structured commitments (who promised what, by when, under conditions) from text transcripts, emails, Slack logs, etc. using Anthropic API. | |
| StudioRelay abdifrh/studiorelay-cli Enables Claude Code to import local videos, create and review drafts, propose scheduling slots, and approve or cancel social-media publications under brand and account permissions with editorial rules. | |
| tg-mcp abdk4moura/tg-mcp MCP server that gives MCP clients access to a personal Telegram account. It can read chats, search messages, download media, and send messages or files while keeping credentials local. | |
| shared-url-mcp abdoknbgit/shared_url_mcp An MCP server with one job: read a shared AI conversation link and write the whole thing to Markdown. | |
| Jira MCP Server abdoosalomov/jira-mcp Custom MCP server for interacting with Jira, supporting issue management, search, and project operations. | |
| PostgreSQL MCP Server abdou-ghonim/mcp-postgres A Model Context Protocol server that provides AI assistants with secure, read-only access to PostgreSQL databases while offering comprehensive tools for schema exploration, query validation, and performance optimization. | |
| Weather MCP Server abdoukaba/weather-mcp-server A production-ready MCP server that provides real-time weather information, forecasts, and alerts to LLM clients using the Open-Meteo API, with support for 26+ global cities, dual transport (STDIO/HTTP), and Docker deployment. | |
| Glowe Pinterest MCP abdouldotdev/pinterest-mcp Enables AI agents to search public Pinterest pins, retrieve pin metadata and media URLs, and download matching images, GIFs, or videos into a local folder, with read-only tools and explicit confirmation for downloads. | |
| tiktok-downloader-mcp abdouldotdev/tiktok-downloader-mcp Enables downloading TikTok videos and photos without watermarks, extracting metadata and analytics, and performing bulk downloads of user profiles via CLI or as an MCP server for AI assistants. | |
| Supabase MCP Server - Self-Hosted Edition abdqum/supabase-mcp-selfhosted Enables comprehensive management of self-hosted or cloud Supabase instances with 54+ tools for database operations, authentication, storage, real-time subscriptions, migrations, and monitoring through MCP protocol. | |
| HackerOne MCP abdugafforov-bobur/hackerone-mcp Connects Claude to the HackerOne Hacker API, enabling program listing, scope retrieval, report management, and balance checks via natural language. | |
| GitHub MCP abdul-34/custom-github-mcp Enables Claude and other MCP clients to read and write GitHub repositories, pull requests, issues, files, branches, commits, releases, and more using a personal access token without OAuth. | |
| GoHighLevel MCP Server abdul-34/ghl-mcp A comprehensive MCP server that connects AI systems to GoHighLevel CRM, providing 269+ tools for contact management, messaging, calendar, sales, and automation. | |
| CRM MCP Server abdul-34/ghl-mcp-server A self-hosted Model Context Protocol server for GoHighLevel CRM, built for agencies. It enables connecting multiple sub-accounts, selecting tools per client, and issuing unique revocable MCP URLs. | |
| codemap abdul-hamid-achik/codemap MCP server for local-first code intelligence, providing structural code graph, semantic search, and impact analysis to AI agents. | |
| Cortex abdul-hamid-achik/cortex Enforces structured, evidence-guided software engineering tasks with cognitive actions (investigate, plan, verify, remember) and persistent state for LLM-based coding agents. | |
| Minerva abdul-hamid-achik/minerva Manages skills and profiles on disk and probes companion tools (bob, cortex, mcphub, etc.) over stdio MCP, enabling library operations and stack readiness checks. | |
| Tarot MCP Server abdul-hamid-achik/tarot-mcp Provides tarot card reading capabilities with a complete 78-card deck, multiple spread layouts (Celtic Cross, Past-Present-Future, etc.), and detailed card interpretations for divination and daily guidance. | |
| Odoo ChatGPT Direct Connector abdul0000/odoo-mcp Enables ChatGPT to interact with Odoo by providing tools for repository management, git operations, Odoo.sh management, Odoo RPC, browser screenshots, and approval workflows. | |
| CodePecker abdul4code/codepecker MCP server that reviews and fixes code across four dimensions (security, standards, production readiness, sustainability), runs tests to verify fixes, and provides findings with diffs. | |
| ERP MCP Bridge abdulahad-devscore/erp-mcp-bridge Places an MCP server in front of Odoo so AI agents can read live ERP data — stock by warehouse, reorder suggestions, invoices, sales, purchase and manufacturing orders — and draft proposed writes such as purchase orders, stock transfers, ma | |
| kicad-mcp abdulazeez0001/kicad-mcp An MCP server that gives AI agents end-to-end control of KiCad 9+ for rule checks, manufacturing exports, production-readiness certification, and live PCB editor control. | |
| crash-mcp abdulaziz001/mcp-local A structured reasoning and problem-solving MCP server that helps track step-by-step analysis with confidence levels, branching, and revisions, ideal for complex multi-step tasks like code optimization and debugging. | |
| moysklad-analytics-mcp abdulaziz1224/moysklad-analytics-mcp Enables AI assistants to query live MoySklad data — inventory, sales, cash flow, documents, and analytics — through read-only MCP tools that match the dashboard's metrics. | |
| ADO Guard MCP abdulbasit7010/ado-guard-mcp Enables AI assistants such as Claude, VS Code Copilot and Cursor to browse and modify Azure DevOps projects, work items, pull requests and pipelines through the Azure DevOps REST API, with a policy engine enforcing read-only defaults, dry-r | |
| ransomware-live-mcp abdulbrown/ransomware-live-mcp Enables MCP clients to query the ransomware.live PRO threat-intelligence API through 25 read-only tools covering ransomware group TTPs, victims, IOCs, YARA rules, ransom notes, leaked negotiation chats, press coverage, SEC 8-K disclosures, | |
| fcp-mcp abdulfatiraziz/fcp-mcp Enables Claude or any MCP client to build, validate, import, and read Final Cut Pro XML timelines, and to control the macOS app through menus, shortcuts, dialogs, exports, and screenshots, all locally. | |
| teamshare-server abdulgeek/teamshare Enables coding agents on a team to publish short context notes that are automatically surfaced at the start of every teammate's next session, with read receipts and SQLite-backed persistent storage over MCP. | |
| Social MCP abdulhadi-98/social-mcp Enables AI assistants and agents to read analytics and manage advertising across Google Ads, Google Analytics 4, and Meta Ads through natural language, with preview-confirm guardrails and configurable account and budget limits. | |
| Sentinel MCP abdulhadi111511-ship-it/sentinel-mcp Enables AI agents and software engineers to investigate and resolve realistic distributed-system incidents using safe MCP-based diagnostic tools for code, logs, metrics, traces, database, and deployments. | |
| SuufScan MCP Server abdulhakiiim/suufscan-mcp Enables a voice assistant to guide land buyers in Senegal and its diaspora through pre-purchase protection: concrete steps and documents to request for a given land status, common fraud warning signs, plain explanations of Senegalese land d | |
| ticktick-mcp abdulhamid-n/ticktick-mcp MCP server for TickTick using the official OAuth 2.0 API. Create, list, update, complete, and delete tasks just by talking to Claude. |
22,901–22,950 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.