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 |
|---|---|
| JIRA MCP Server dsazz/mcp-jira A Model Context Protocol server that integrates JIRA directly into Cursor IDE, allowing users to view assigned issues, get detailed information on specific tickets, and convert JIRA issues into local tasks without leaving their editor. | |
| gramps-ez-mcp dsblank/gramps-ez-mcp Enables natural language queries about family tree data from a Gramps genealogy database. | |
| Express REST API and MCP Server Framework dschaefer97/express-rest-api-and-mcp-server-framework Exposes every generated CRUD service to LLM clients such as Claude, ChatGPT, or Cursor through discoverable MCP tools for create, update, and list actions plus read-only resources, so models can query and manipulate data without raw HTTP ca | |
| anndata-mcp-workshop dschaub95/anndata-mcp-workshop Enables interaction with AnnData objects via the Model Context Protocol, allowing querying and manipulation of annotated data matrices for single-cell genomics. | |
| Base MCP Server dschlabach/base-mcp-alpha An MCP server that provides onchain tools for Claude AI to interact with the Base blockchain and Coinbase API, enabling wallet operations, testnet ETH, balance checks, fund transfers, and smart contract deployment. | |
| mattergate dschnurbusch/mattergate A self-hostable MCP permissions gateway for legal-tech systems that connects legal apps once and exposes only the tools each team member should use, enforcing a thin policy and audit layer over vendor APIs. | |
| Reaper MCP Server dschuler36/reaper-mcp-server Connects Reaper projects to an MCP client like Claude Desktop, allowing users to ask questions and retrieve parsed information about the projects using natural language. | |
| Agent.AI MCP Server dschwartzai/agentai-mcp-server An externally deployable server designed to be hosted on Vercel that can be called from other applications, allowing integration with Agent.AI's Multi-Context Processing capabilities. | |
| surveymonkey-mcp dscovr/surveymonkey-mcp Enables interaction with the SurveyMonkey API v3, providing tools to manage surveys, pages, questions, responses, collectors, webhooks, and contacts via natural language. | |
| booking_chest dsddet/booking_chest MCP server for Cal.com scheduling, providing ~70 tools to manage schedules, event types, bookings, calendars, webhooks, and teams. Enables natural language control of Cal.com from Claude or any MCP-compatible client. | |
| campaign_chest dsddet/campaign_chest Provides 35 MCP tools for automated marketing campaigns, integrating event management, booking, and email marketing into a deterministic pipeline for AI agents. | |
| obsidian-cli-rest dsebastien/obsidian-cli-rest Enables programmatic control of Obsidian vaults via REST API and MCP server for automation and AI assistant integration. | |
| Siigo MCP Server dsfaccini/siigo-mcp Unofficial MCP server for Siigo Colombian electronic invoicing software that enables AI to manage customers, products, invoices, credit notes, and journals through the Siigo API with configurable safety modes. | |
| LiveMCP dsgarage/livemcp Enables Claude Code to control Ableton Live directly through a Max for Live device, letting users read set state, search samples, place clips, build Drum Racks, adjust device parameters, and generate .als project files from sample packs wit | |
| MaxRefMCP dsgarage/maxrefmcp Provides a comprehensive reference tool for Max/MSP and Max4Live with Japanese language support, enabling natural language searches for objects, patching patterns, and packages. It allows users to retrieve technical details, glossary terms, | |
| MaxRefMCP dsgarage/maxrefmcp_dev Provides Japanese-optimized reference, design consultation, and learning support for Max/MSP and Max4Live through natural language queries. | |
| ReviewMCP dsgarage/reviewmcp Enables automatic validation and correction of Re:VIEW manuscript files by checking for unauthorized tags, fixing duplicate/empty IDs, and running fast lint checks to prevent common errors during writing. | |
| UniMCP4CC dsgarage/unimcp4cc Enables Claude Code to directly control Unity Editor, supporting scene manipulation, component operations, asset management, prefab handling, and audio control through natural language commands. | |
| step-modeler-mcp dsh18235538266-crypto/offline-step-viewer Enables conversational creation and editing of STEP CAD models through MCP clients like Codex, Claude, or Cursor, with real-time 3D browser preview and tools for primitives, booleans, mounting holes, flanges, and gripper bases. | |
| onshape-mcp-codex dsh18235538266-crypto/onshape-mcp-codex Enables OpenAI Codex to drive real Onshape parametric CAD via 69 tools for documents, sketches, features, assemblies, parametric updates, FeatureScript, vision, and export. | |
| MCPizza - Enhanced dshanklin-bv/mcp-pizza An educational MCP server that enables users to browse Domino's menus, find coupons, and configure customized pizza orders via natural language. It demonstrates complex tool orchestration and real-time API integration for order validation a | |
| DSH Codex Computer Use dshapp/dsh-codex-computer-use Exposes MCP tools that let agents inspect and control any Mac application through accessibility trees and screenshots, enabling background clicks, typing, scrolling, dragging, and app-state reads. | |
| Construction Intelligence MCP dsharrington84/construction-intelligence-mcp Read-only MCP server exposing the Construction Intelligence Platform's project discovery interface via search_projects and fetch_project tools, returning Pydantic business objects from the ci_market_state DuckDB table without requiring SQL. | |
| Microsoft To Do MCP dshatokhin/microsoft-todo-mcp-server A Model Context Protocol (MCP) server that enables AI assistants like Claude and Cursor to interact with Microsoft To Do via the Microsoft Graph API. | |
| Agent Runtime Proxy dshcorrectover/agent-runtime-proxy Enables fail-closed runtime interception of MCP tool calls, blocking denied, verifier-error, or timed-out invocations while forwarding permitted calls with Ed25519 receipts. | |
| web-search-mcp dshein-alt/crawly-mcp Provides web search and page fetch capabilities using a browser-based approach, enabling LLMs to search DuckDuckGo, Google, or Yandex and retrieve rendered HTML from URLs. | |
| Markup Résumé MCP Server dshelemonchak/markup-resume Enables Claude Desktop and Claude Code to list, read, create, and write CVs and read templates through local MCP tools, with markup validation on every write. | |
| SendPulse Chatbots MCP Server dshemendiuk/mcp-sendpulse Enables interaction with SendPulse Chatbots API to manage chatbot accounts, retrieve bot information, and access dialog conversations. Supports flexible authentication through API credentials or OAuth tokens for comprehensive chatbot manage | |
| MCP MQTT Light Controller dshenaf/mcp-mqtt-light Enables control of smart lights through MQTT messaging protocol, supporting operations like turning lights on/off and adjusting brightness levels from 0-100. | |
| Compounding MCP dshguilherme/compounding-mcp Enables agents to coordinate persistent contributions and numerical experiments in a Git repository, including announcing scopes, recording scored contributions, nominating candidates, and tracing ancestry. Uses Boruna workflows to capabili | |
| Document Intelligence MCP Server dshivasane/building-an-mcp-server-with-ocr Enables Claude to read and analyze PDF documents with automatic OCR processing for scanned files. Features intelligent text extraction, caching for performance, and secure file access with search capabilities. | |
| linear-mcp-server dshurick/linear-mcp-server MCP server for integrating Linear with Claude Code and other MCP clients. Enables issue management, project planning, and status tracking through a set of tools. | |
| dsh-solidworks dshworks/dsh-solidworks Enables MCP clients to inspect, edit in memory, rebuild, render, and export SOLIDWORKS 2016+ parts, assemblies, and drawings on the same PC or in a Windows VM. It provides 13 tools with read-only defaults and controlled export/save behavior | |
| callsense-mcp dsichz/callsense-mcp Enables Claude to score sales calls against a team's own playbook, accepting a score only when it is backed by a verbatim quote from the correct speaker in the call transcript, and rejecting the rest with actionable hints. It also produces | |
| SIMPA dsidlo/simpa-mcp SIMPA is a Model Context Protocol (MCP) service that learns from every interaction to continuously improve prompt quality. It remembers what worked, refines what didn't, and automatically selects the best prompts for any situation. | |
| neo4j-server-remote dsimile/mcp-neo4j-server-sse Enables interaction with Neo4j graph databases through Cypher queries, supporting both read and write operations, schema exploration, and remote database connections via SSE or STDIO transport protocols. | |
| Google Docs MCP Proxy dsingh80/google-docs-mcp Local stdio MCP server that handles Google OAuth2 locally and proxies authenticated requests to Google Docs and Google Drive REST APIs, enabling document and file operations from Cursor or other MCP clients. | |
| Glance dsingh82888/glance Enables Claude Code to drive a real browser — navigating, clicking, typing, screenshotting, and inspecting pages through 30 MCP tools. Supports multi-step test scenarios, assertions, session recording, visual regression, and network/console | |
| Memory MCP dsins/mcpmemo A production-grade memory server for LibreChat that stores conversation turns and distills durable memories like decisions, constraints, and assumptions. It provides hybrid retrieval and consistency auditing to ensure AI plans remain aligne | |
| MCP Nexus dsk-dev-ai/mcp-nexus Provides a single MCP endpoint that dynamically discovers, routes, policy-checks, and executes hundreds of MCP tools from any agent, with optional LLM-based routing. | |
| mcp-tutorial dsl-unibe-ch/mcp-tutorial A minimal MCP server that exposes two tools, enabling language models to discover and call them via MCP. | |
| Healthcare Analytics MCP Server dslans/mcp_healthcare_data Enables comprehensive healthcare data analysis using Tuva Health demo data with tools for value-based care analytics, quality measures, utilization analysis, and financial metrics. Supports patient demographics, PMPM analysis, chronic condi | |
| google-mcp dslh/google-mcp Provides 20 tools for Google Drive, Docs, and Calendar operations with OAuth 2.0 security and comprehensive error handling. | |
| Hermes WPS MCP dsmfrp1024/hermes-wps-mcp Enables an agent to directly drive a running WPS installation over MCP — reading and editing live Excel, Word, and PowerPoint documents in memory through 243 tools, so changes appear on screen immediately without touching files on disk. It | |
| z3-solver-mcp-server dsouflis/z3-solver-mcp-server Enables solving constraint satisfaction problems, mathematical equations, and logic puzzles using the Z3 SMT solver through natural language. | |
| Bright Data Web MCP dsouza-anush/brightdata-mcp-heroku Enables LLMs and AI agents to access real-time web data, search websites, and navigate the web without getting blocked. Includes 5,000 free monthly requests and supports web scraping, browser automation, and bypassing geo-restrictions. | |
| Browser Use Heroku dsouza-anush/browser-use-heroku Enables AI agents to control and automate browser actions through an MCP server deployed on Heroku. Supports programmatic browser automation with natural language tasks across multiple LLM providers. | |
| Exa MCP Server dsouza-anush/exa-mcp-server-heroku Enables AI assistants to perform real-time web searches, company research, content crawling, LinkedIn searches, and deep research tasks using the Exa AI Search API. Can be deployed locally or on Heroku for remote access. | |
| Atlassian MCP Server for Heroku dsouza-anush/mcp-atlassian An MCP server that provides integration with Jira and Confluence for managing issues, boards, sprints, and documentation pages. It is specifically designed for native deployment on Heroku to enable AI models to interact with Atlassian resou | |
| Salesforce MCP Server for Heroku dsouza-anush/mcp-salesforce Enables AI agents to interact with Salesforce CRM data by executing SOQL queries and managing records. It provides tools for object metadata discovery and record operations, specifically optimized for Heroku deployment. |
46,151–46,200 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.