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 |
|---|---|
| ERP MCP Server burakozden1/erp-mcp-agent Enables Claude to answer business questions about stock, orders, customer balances, overdue orders and KPIs from live ERP data using fixed, parameterized read-only queries, with bounded results and every call logged to an audit trail. | |
| vault-ask burakozg/vault-ask Lets Claude Code and Claude Desktop retrieve and explore an Obsidian vault through tools for semantic search, reading notes, following graph neighbors, and listing topics. | |
| PantryPilot MCP burbanodev-lab/pantrypilot-mcp Enables agents to manage household pantry inventory, dietary preferences, meal planning, product search, and shopping cart workflows over Streamable HTTP, with optional Bedrock-backed meal generation. | |
| Microsoft Graph MCP Server burconsult/msgraph-mcp A comprehensive server that enables AI applications to interact with Microsoft 365 and Azure AD services through standardized Model Context Protocol interfaces. | |
| Azure DevOps MCP Server burcusipahioglu/azure-devops-mcp-onprem Brings on-premises Azure DevOps Server (including TFVC) to AI assistants with 49 tools for work items, repositories, pipelines, test plans, and wiki, along with profile-based secrets and write safety layers. | |
| Stealth Browser MCP burgebj/stealth_browser_mcp Undetectable browser automation for AI agents that bypasses Cloudflare, antibot systems, and social media blocks using real browser instances with 97 tools across 11 sections. | |
| Seed MCP Server burgeonbot/seed-mcp-server Enables creating and inspecting Seed tables and relationships through the Seed backend HTTP API. | |
| Storywright MCP burgersjackson/storywright-mcp A multi-agent book-writing MCP server that manages a guarded chapter pipeline (writer → editor → third-pass agents → approve) with project planning, continuity tracking, and export/diff helpers. | |
| Memory MCP burgessadrien/memory-mcp Provides persistent AI agent memory using a local vector database for long-term semantic storage and short-term session scratchpads. It enables low-latency memory operations including search, storage, and bulk management without external cl | |
| text-image-mcp burgessadrien/text-image-mcp Enables AI agents to generate stylized images from text and code, with syntax highlighting and markdown formatting support. | |
| cal-mcp burghr/cal-mcp Enables read-only access to the local Apple Calendar on macOS through an MCP client, allowing retrieval of today's events, events for a specific date, or events in a date range. It supports optional calendar filtering and keeps calendar dat | |
| reminders-mcp burghr/reminders-mcp Enables reading, creating, updating, completing, and deleting local Apple Reminders on macOS through EventKit, with list filtering, due dates, notes, priorities, and an optional read-only mode. | |
| ga4-mcp-server burhan29ee/ga4-mcp-server A Model Context Protocol server for Google Analytics 4 with both read and write access, enabling natural language reporting, configuration management, audience creation, and server-side event sending via Google credentials. | |
| google-ads-mcp-server burhan29ee/google-ads-mcp-server An MCP server that provides read and write access to Google Ads, allowing natural language management of campaigns, budgets, ad groups, bids, and keywords, with dry-run validation for safety. | |
| google-analytics-gtm-mcp burhan29ee/google-analytics-gtm-mcp MCP server for Google Analytics 4 and Google Tag Manager with read and write access, providing 40 tools to manage GA4 reports, audiences, and GTM tags, triggers, and variables via natural language. | |
| BioMCP burhanabdullah/biomcp Enables installing, configuring, and running modular MCP servers for biology, bioinformatics, and bioimaging tasks, including local image analysis, ImageJ/Fiji bridging, and LLM-based agent workflows. | |
| PSX MCP Server burhank928/psx-mcp-server Provides tools to scrape and access Pakistan Stock Exchange (PSX) market data, including market data, intraday, historical, sector, gainers/losers, OHLCV, and volume analysis. Supports both local stdio and remote HTTP deployments with API k | |
| Charlotte burke35546/charlotte Gives AI agents token-efficient, structured access to web pages through a persistent headless browser session, returning a compact page orientation on arrival, targeted element queries, and full detail only when explicitly requested. Also e | |
| twilio-call-data-mcp burkecampbell/twilio-call-data-mcp Read-only MCP server for Twilio call data, providing tools to search calls, fetch recordings and transcripts, list agents, and generate summaries while explicitly handling timezone and duration measurement discrepancies. | |
| VS Code MCP Button Generator burkeholland/mcp-vsc-button-gen Generates VS Code installation buttons and markdown badges for MCP servers, supporting both Stable and Insiders versions with configurable inputs and commands. | |
| XMCP Application burkeholland/youtube-mcp A development server that automatically discovers and exposes tools from the src/tools directory, allowing you to create and run Machine Comprehension Protocol (MCP) services with either HTTP or STDIO transport methods. | |
| Cloudzero Model Context Protocol Server burkestar/cloudzero-mcp A server that allows users to query and analyze cloud cost data from Cloudzero using natural language through Large Language Models. | |
| n8n MCP Server (Custom) burnham/n8n-mcp-server-custom Custom MCP server for n8n automation, providing 27 tools to manage workflows, executions, credentials, variables, and more via the n8n REST API. Designed to fix compatibility issues with Antigravity AI assistant. | |
| jev-mcp burnigtm/jev-mcp Enables coding agents to make cheap, fast probabilistic decisions on every turn, with tools for coding-loop checks, review, verification, screening untrusted input, and ranking candidates. | |
| Geoapify MCP Server burningion/geoapify-mcp Converts addresses to GPS coordinates and creates map visualizations using the Geoapify API, allowing Claude users to generate GeoJSON data and map images from location lists. | |
| mcp-token-saver burnrate-ai/mcp-token-saver Real-time Claude.ai subscription awareness for AI coding assistants. Surfaces live utilization, forecasts limits, gates expensive operations, and measures real per-task cost. | |
| Sherlock MCP Server burnsedia/sherlock-mcp Enables username enumeration across 400+ social media platforms using the Sherlock OSINT tool. Perfect for open-source intelligence gathering, cybersecurity research, and investigating social media presence through AI assistants. | |
| SovietRepublic-MCP burnshall-ui/sovietrepublic-mcp An MCP server that exposes live game data from Workers & Resources: Soviet Republic to Claude by parsing game autosave files. It enables users to monitor population demographics, economic metrics, and trade history through natural language | |
| lunanode-mcp burntberry/lunanode-mcp Enables management of LunaNode VPS resources including VMs, images, volumes, floating IPs, SSH keys through natural language with tiered safety controls. | |
| a11y-learning-guide burnworks/mcp-a11y-learning-guide Guides users to official WCAG and W3C resources for learning web accessibility, without providing its own explanations. | |
| mcp-movabletype-writer burnworks/mcp-movabletype-writer MCP server for Movable Type. It lets MCP-compatible AI tools such as Claude Desktop work with Movable Type so that AI-generated drafts can be created and edited directly inside MT. | |
| microCMS MCP Server burnworks/microcms-api-mcp-server Enables to access and manage content on microCMS through MCP, supporting listing, retrieval, search, and filtering of API endpoints. | |
| xrpl burnxrp/xrpl-agent-tools Enables AI agents to build, validate, and submit ledger-native XRPL transactions against public nodes — escrows, XRP and token payments, DEX/AMM swaps and liquidity, issuer clawback, and x402 pay-per-request — with validated-ledger proof of | |
| HomeOps MCP burpingspider/homeops-mcp Enables voice-first household maintenance tracking, turning spoken updates into durable records, service history, and due-date reminders for a concise maintenance brief. | |
| fastmcp-endpoint-toolsets burri-ritvik/fastmcp-endpoint-toolsets A single FastMCP server that exposes multiple URL-scoped tool groups, allowing agents to access only relevant tools via separate endpoints, reducing context bloat and token costs. | |
| semblekit burrows99/semblekit MCP server for the Semble practice-management API, enabling AI agents to search for patients, contacts, and users, as well as retrieve patient relationships via read-only tools. | |
| self-hosted-pages-mcp burserk84/self-hosted-pages-mcp Enables AI assistants to deploy and manage static websites on EdgeOne Pages via the Model Context Protocol. | |
| HexStrike AI MCP Agents burstbullet666-bit/fix222 Enables Claude AI to access and run over 150 integrated cybersecurity tools through a public ngrok tunnel, supporting agentic security workflows via MCP. | |
| research-mcp burton-david/researchassistantmcp A citation-finding research assistant for scientists, exposed as an MCP server that extracts claims from draft paragraphs, searches multiple academic sources, scores paper quality, and explains recommendations. | |
| Busabase busabase/busabase Open-source, self-hosted database and workspace for AI agents. Its MCP server lets agents manage structured records, documents, files, reusable skills, and apps, with auditable Change Requests for writes. | |
| SharePoint MCP Server bush-bush-law-group/bblg-sharepoint-mcp Enables AI assistants to access and manage SharePoint sites, lists, and files along with Microsoft Graph and Azure Resource Manager resources over stdio, with authenticated access, write previews/confirmations, and file downloads. | |
| okfgen-mcp bushans/okfgen An MCP server that enables AI agents to generate, search, and reason over knowledge graphs from code, databases, docs, and open-data portals without requiring an LLM or API key. | |
| gsc-mcp-connector bushraorganic-dot/gsc-mcp-connector Self-hosted Google Search Console MCP server deployable to Cloudflare Workers, allowing natural language queries of GSC data via ChatGPT, Claude, or any MCP-capable client. | |
| MCP Server Metasearch busigui2023/mcp-server-metasearch A unified MCP server aggregating 15 web search and extraction tools across 5 providers (Jina, Tavily, Exa, Firecrawl, Bocha) with automatic API key validation and plugin architecture. | |
| @businessmaps/mcp business-maps/bifrost An MCP bridge server that allows AI tools to call functions and execute code directly within a web browser tab. It enables developers to register custom browser-side tools with full access to the DOM, web APIs, and local application state. | |
| Keepa MCP Server business2business17-ui/keepa Provides conversational access to Keepa Amazon product and sales data, enabling product research, sales velocity and inventory analysis, deal discovery, category intelligence, and competitive analytics. | |
| N8N MCP Server businessarchi/n8n-mcp-server Enables management of multiple N8N workflow automation instances through MCP. Supports listing, creating, updating, deleting, executing workflows and monitoring their executions across different N8N environments. | |
| MCP Sentinel businesscanva12-tech/mcp-sentinel Enables AI coding assistants to detect exposed secrets and unsafe dynamic execution patterns in real time using regex, entropy analysis, and Python AST inspection before changes are finalized. It supports MCP stdio integration for Claude an | |
| origo-bc-mcp-server businesscentralal/origo-bc-mcp Connects AI clients like VS Code Copilot and Claude Desktop to Microsoft Dynamics 365 Business Central via the Cloud Events API. | |
| Dataverse Local MCP businessnone/dataverselocalmcp Enables interaction with Microsoft Dataverse and Dynamics 365 data through natural language, including CRUD operations, metadata exploration, and saved views. |
36,101–36,150 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.