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 |
|---|---|
| jalipata-mcp-memory alfianyusufabdullah/jalipata Provides persistent, multi-tenant knowledge graph memory for MCP-capable AI tools, allowing them to recall and store entities, observations, and relations across sessions with keyword search. | |
| sap-mcp-simulation alfmorais/sap-mcp-simulation Simulates and intermediates integrations with SAP via OData, exposing automated tools for AI agents and assistants. | |
| Contex alfonsogober/contex Converts any OpenAPI 3.x specification into a fully functional MCP server with OAuth 2.1 support and a purely functional architecture. | |
| Things MCP alfonsopuicercus/things-mcp Enables MCP clients to read and manage a local Things 3 database on macOS through Things' supported scripting interface, listing, searching, creating, updating, moving, scheduling, and completing tasks, projects, and areas without any hoste | |
| sfm-mcp alfred-bulgakob-steelfm/sfm-mcp Enables Claude or other MCP clients to inspect and edit a running Source Filmmaker scene, add models, lights, and cameras, animate characters, capture screenshots, and render stills or movies. | |
| razorpay-mcp-guard alfred-hqbot/razorpay-mcp-guard Enforces spend policies on Razorpay MCP tool calls by applying per-agent spend caps, category allowlists, and approval thresholds, with a tamper-evident audit ledger. | |
| NotebookLM MCP alfredang/notebooklm-mcp Integrates Google NotebookLM into Claude to allow users to manage notebooks, add sources, and generate diverse content like podcasts, slides, and reports. It enables natural language interaction with notebook sources across Claude Desktop a | |
| Microsoft 365 MCP Server alfredo-ia/ms-365-mcp-server An MCP server that enables interaction with Microsoft 365 services like Outlook, OneDrive, Teams, and SharePoint via the Microsoft Graph API. It supports comprehensive operations including email management, file access, and organizational c | |
| mlx-mcp alfredo-sandoval/mlx-mcp Gives coding agents searchable access to MLX, MLX Data, and MLX LM documentation so they can check the docs before writing MLX code. Runs locally on Apple silicon with no account or API key, and works offline after the first search. | |
| markitdown-mcp alfredoanton82/markitdown-mcp Converts documents (PDF, DOCX, XLSX, PPTX, HTML, TXT, MD) to Markdown and stores them locally with search and retrieval capabilities. | |
| api-redbox-mcp alfredojrc/api-redbox-mcp Provides a disposable, hardened Kali Linux sandbox with an MCP interface for LLM-driven security analysis of REST APIs, confining blast radius via container isolation. | |
| agent-gpu-pool alfredquan/agent-gpu-pool Provides a persistent compute queue for AI agents, enabling them to submit hardware-aware GPU jobs, monitor execution, and retrieve results and artifacts across sessions via MCP tools. | |
| CoinMarketCap Portfolio MCP Server alg0-labs/crypto-portfolio-mcp Transforms Claude AI into a personal crypto portfolio analyst, enabling wallet analysis, AI-powered recommendations, and portfolio tracking across 8+ blockchains through natural conversation. | |
| Java Testing Agent algeek01/se333_final_project Automates Java Maven testing workflows with decision table-based test generation, security vulnerability scanning, JaCoCo coverage analysis, and Git automation. | |
| ObsiScripta Bridge algiadev8/obsidian-obsiscripta-mcp Enables MCP-based operations on an Obsidian vault, including reading, editing, and custom script tools. | |
| quartus91-mcp alglb123/quartus91-mcp Wraps Quartus II 9.1 command-line tools into MCP tools, enabling AI agents to create projects, assign pins, generate simulation waveforms, run simulations, compile, read reports, and program devices. | |
| AlgoChains MCP Server algochains/algochains-mcp-server Enables AI assistants to interact with a complete trading infrastructure, including live futures bots, real market data, backtesting, and copy-trading signals. Supports 503 tools across 20 domains, from market data to order execution, with | |
| Algorand MCP Server algodev-studio/algorand-mcp Provides 50+ tools for comprehensive Algorand blockchain development including account management, asset operations, smart contracts, atomic transactions, swap functionality via Pera Swap, and semantic search through Algorand documentation. | |
| algoglide algoglide/mcp MCP server for AI coding editors — deploy and manage prediction-market trading agents directly from your editor. | |
| MCP Trading for Vietnam Securities Market algolabx/mcp-trading Including SSI, TCBS, DNSE | |
| mapsi-mcp algolayertechnologies/mapsi-mcp Geospatial API tools for AI agents — geocoding, reverse geocoding, routing, isochrone, distance matrix, static maps, H3 hexagons, elevation, GPS map-matching, point-in-polygon, address normalisation, timezone lookup, and batch geocoding. Bu | |
| Algolia algolia/mcp MCP servers for interacting with Algolia | |
| Algolia Node.js MCP algolia/mcp-node Enables natural language interactions with Algolia search and analytics APIs through Claude Desktop. Supports searching indices, managing data, analyzing metrics, monitoring performance, and visualizing insights across your Algolia applicat | |
| AlgoLift MCP Server algolift-ai/mcp Enables AI assistants to look up futures prop firm rules with each rule's verification status and cited source, run 217 tested technical indicators and candlestick patterns, and compute Setup Odds for intraday setups on the user's own bars, | |
| mcp-crossref algonacci/mcp-crossref Enables searching roughly 170 million scholarly works and resolving DOIs into normalized metadata, complete with citation formatting in any style, reference and citing-work snowballing, and author, journal, funder and topic profiles. It als | |
| mcp-email algonacci/mcp-email A minimal MCP server for reading, searching, managing, and sending email over IMAP and SMTP. | |
| mcp-exa algonacci/mcp-exa Enables MCP clients to connect to Exa for web search, retrieving URL contents, deep cited-answer search, and research-agent runs. It provides Exa search, content, and research tools with filtering, structured output, and cost reporting. | |
| mcp-google-calendar algonacci/mcp-google-calendar A minimal MCP server for Google Calendar using OAuth 2.0, enabling calendar management, event CRUD, sharing, and push notifications via natural language. | |
| Algonius Browser algonius/algonius-browser An open-source MCP server that provides browser automation capabilities to external AI systems, enabling navigation, DOM interaction, and web content extraction. | |
| analog-rytm-agent-bridge algonormative/analog-rytm-agent-bridge Enables a coding agent to operate an Elektron Analog Rytm MKII through semantic MCP tools, with validation-first safety, snapshots, and rollback for persistent changes. | |
| Linux MCP Server algony-tony/mymcp Exposes full Linux system control to AI clients via MCP tools for bash execution, file operations, and search, with configurable permissions and audit logging. | |
| agent-commons algorerthym/agent-help-desk Enables agents to search answered tickets, ask new questions, and answer waiting questions on the shared help desk, while providing read-only observation of visits. | |
| minimax-omni algovate/minimax-omni MCP server for MiniMax's multimodal generation models, enabling text-to-speech, voice cloning, image, video, and music creation through natural language. | |
| XHS MCP algovate/xhs-mcp Enables interaction with Xiaohongshu (Little Red Book) platform through automated browser operations. Supports authentication, content publishing, search, discovery, and commenting using Puppeteer-based automation. | |
| Meta Ads MCP algoyandreina1236-web/meta-ads-mcp-pwm Enables AI assistants to manage Meta Ads (Facebook, Instagram) end-to-end through natural conversation, including launching campaigns, uploading creatives, updating budgets, and analyzing performance. | |
| Remote MCP Server Template (Authless) algtools/mcp A template for deploying custom MCP servers on Cloudflare Workers without authentication. Enables users to create and deploy their own tools accessible from Claude Desktop and AI Playground via SSE endpoints. | |
| Remote MCP Server Template (Cloudflare) algtools/mcp-template A template for deploying authentication-free MCP servers on Cloudflare Workers, enabling custom tool creation and integration with Claude Desktop and AI Playground via remote connections. | |
| truthgate alh477/trvthnvke Enables agents to verify README claims and apply structured edits that automatically revert if they fail the repository's gates. | |
| taste-layer alhassanmohammederc3643-cmyk/taste-layer Exposes two Qloo-grounded tools, resolve_taste_anchor and recommend_for_group, so any agent can turn what individual people like into per-person signals instead of stereotypes. Group picks are ranked by how many people each option covers, t | |
| Remote MCP Server alhwyn/call_mcp A deployable MCP server on Cloudflare Workers that can be accessed from Claude Desktop or Cloudflare AI Playground, allowing users to create and use custom AI tools without authentication. | |
| canlii-mcp alhwyn/canlii-mcp Provides access to the CanLII API for searching and retrieving Canadian legal information, including court decisions, legislation, and citations. | |
| RAG MCP Server ali-48/rag-mcp-server Combines a knowledge graph with RAG (Retrieval-Augmented Generation) capabilities for semantic code indexing and search. Enables creating entity relationships, managing observations, and performing semantic searches across indexed codebases | |
| Absher Voice Assistant MCP Server ali-bouali/absher-mcp-server Enables interaction with Saudi government services through the Absher platform, supporting identity verification, user profile management, and service discovery. It allows users to perform tasks like renewing passports, querying traffic fin | |
| klaxon ali-cabukel/klaxon Enables incident management through natural language, with tools for searching, retrieving, creating, updating, and commenting on issues, simulating upstream events, creating GitHub issues, and listing side effects. | |
| mcp-data-gateway ali-chaghou/mcp-data-gateway Enables AI agents to query a PostgreSQL database through a small set of controlled, read-only tools for schema inspection, row lookup, and aggregate statistics. | |
| tlgrm ali-commits/tlgrm Drives a personal Telegram account from the terminal or via MCP, enabling AI assistants to list chats, send/edit messages, fetch history, manage groups, and more with tiered read/write/destructive permissions. | |
| Axon.MCP.Server ali-kamali/axon.mcp.server An MCP server that transforms codebases into intelligent, queryable knowledge bases, enabling AI assistants to perform semantic search, explore architecture, and analyze code relationships. | |
| Deep Research MCP ali-kh7/deep-research-mcp A Model Context Protocol compliant server that facilitates comprehensive web research by utilizing Tavily's Search and Crawl APIs to gather and structure data for high-quality markdown document creation. | |
| fluxforge ali-kishk/fluxforge_mcp Predicts CRISPR gene dependencies and drug targets by integrating literature, regulatory/PPI networks, and genome-scale metabolic models. | |
| Bridge-MCP ali-moghadam/bridge-mcp Unified MCP server that integrates Jira, GitLab, and Confluence for AI assistants to access project management, code repositories, and documentation from a single interface. |
26,451–26,500 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.