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 |
|---|---|
| kie-ai-mcp-server daanjonk/kie-ai-mcp-v1 Universal MCP server for all Kie AI image generation and editing models, enabling text-to-image, image-to-image, and image editing via natural language. | |
| Fastmail MCP Server daankumar/fastmail-mcp Enables AI assistants to read, search, send, draft, and organize email, manage contacts, and create or update calendar events through Fastmail's JMAP, CalDAV, and WebDAV APIs. Supports attachments, conversation threading, label versus move | |
| Simplicate MCP Server daanno/simplicate-mcp Enables AI assistants to securely access and interact with Simplicate business data including CRM, projects, timesheets, and invoices through natural language. Supports searching across resources and retrieving detailed information about or | |
| grafana-mcp daanrongen/grafana-mcp MCP server for Grafana enabling management of dashboards, datasources, alert rules, folders, and annotations via stdio. | |
| signal-mcp daanrongen/signal-mcp MCP server for Signal via signal-cli that enables sending and receiving messages, managing contacts and groups, and reacting over stdio. | |
| Aras Innovator Claude Agent daantheoden/aras-claude-agent Enables Claude Desktop to interact with Aras Innovator PLM systems via OAuth 2.0, allowing users to query PLM data, create items, and call server methods through natural language. | |
| AKIMCP daanwu35/aki-mcp-sv Exposes a governed suite of 38 OAuth-gated tools that let web-based AI chat clients read, write, edit, and search local files, run whitelisted shell commands, inspect databases and localhost APIs, drive browsers and DevTools, and manage bac | |
| Doorstep Resolve daanyal-23/doorstep-resolve Exposes MCP tools that fetch order details, check policy eligibility and multi-warehouse inventory against carrier cutoffs and transit times, and return deterministically ranked replacement options with step-by-step evidence. Requires expli | |
| Serverless MCP Framework daaru00/aws-serverless-mcp A framework to deploy MCP servers on AWS using serverless services like Lambda, API Gateway, and EventBridge, with dynamic tools, prompts, and resources managed via SSM parameters and Lambda functions. | |
| MCP WeChat ADB Server dabaigoose/mcp-wechat-adb-server Enables AI assistants to send WeChat messages and take screenshots through ADB automation with LDPlayer emulator. Supports automated WeChat replies to multiple contacts with personalized messages for business and personal use. | |
| DBT Manifest MCP Server dabblefish-solutions/dabblefish__mcp__dbt-core-tools Enables the analysis of DBT manifests with automatic schema version detection and lineage tracking, allowing users to query model dependencies, access compiled code, and get detailed model information. | |
| mcp-hubspot dabelstech-creator/hubspot-mcp Enables AI assistants to directly access and manage HubSpot CRM data, including contacts, companies, and conversations, with semantic search and caching for improved performance. | |
| OKR Manager MCP Server dabelstech-creator/mcp-stytch-b2b-okr-manager Enables AI agents to interact with a B2B OKR management application to view and manage objectives and key results, with Stytch-backed multi-tenant authentication and role-based access control. | |
| Better Auth MCP Server dabhivijay2478/better-auth-mcp-server Provides access to Better Auth framework documentation, authentication provider configurations, database adapter setup, and generates production-ready authentication configs for modern web frameworks. | |
| drawio-parser-mcp dabian321/pydrawioparsermcp Validates and parses Draw.io XML syntax, enabling analysis and verification of diagram structures, especially for AI-generated content. | |
| YouTube Insights MCP Server dabidstudio/youtubeinsights-mcp-server Enables extraction of transcripts, keyword-based video search with metadata retrieval, and channel information discovery from YouTube videos through natural language interaction. | |
| mcp-brain dabielf/mcp-brain A personal second brain on Cloudflare Workers that stores knowledge as a semantic graph with auto-linking, deduplication, and MCP tools for AI agents to save, search, and connect information. | |
| PlanFlow dabik/mcp-plan-generation MCP server for creating, validating, and reviewing implementation plans in GitHub Copilot Chat, with visual review interface and MongoDB persistence. | |
| Polygon MCP Server dablclub/polygon-mcp A Model Context Protocol (MCP) server that provides onchain tools for Claude AI, allowing it to interact with the Polygon PoS blockchain to call contract functions, manage ERC20 tokens, and check gas prices. | |
| kdeconnect-mcp dablitzstein/kdeconnect-mcp Enables LLM agents to access Android SMS, calls, and notifications via KDE Connect, with PII redaction at ingest to protect OTPs, card numbers, IBANs, and phone numbers. | |
| modu-emergencybell dablro12/modu-emergencybell-mcp Provides emergency hotline numbers, restrooms and outdoor safety bells, after-hours clinics, pharmacies, ER beds, and foreign visitor phrase cards. Information only—does not place calls or diagnose. | |
| nidonnaesan dablro12/nidonnaesan-mcp Enables reviewers to find sponsorship campaigns, assess their value, and generate application messages via a conversational interface. It integrates with Korean review platforms and provides tips for increasing selection rates. | |
| Tesseract OCR MCP Server daboatan/tesseract-ocr-mcp Enables AI assistants and applications to perform optical character recognition (OCR) from images via stdin/stdout streams or REST API endpoints. | |
| tmux-bridge-mcp dabrowski72203/tmux-bridge-mcp Lets AI agents running in separate tmux panes read each other's output, send messages and keystrokes, and coordinate multi-agent workflows through standard MCP tool calls. It works with any MCP-compatible agent and talks directly to tmux, r | |
| cv-mcp dabs1/cv-mcp Exposes a curriculum vitae hosted on a backend REST API to AI assistants over stdio, letting them retrieve the full CV, list and fetch individual sections, and search for terms like technologies or companies. It also provides the full CV as | |
| Accord Server MCP daccordproject/accordserver-mcp Connects AI agents to Accord chat server instances via the Model Context Protocol to manage spaces, channels, and messages. It supports a comprehensive range of operations including searching conversation history, sending messages, and perf | |
| Sales Dashboard dacdigital/mcp-app-demo Enables interactive sales data exploration within Claude through a dynamic dashboard with filterable charts and tables. | |
| MCP Prompt Cleaner dacebt/mcp-py-prompt-cleaner Enhances and cleans raw prompts using AI to make them more clear, actionable, and effective. Provides quality assessment, suggestions, and supports both general and code-specific optimization modes. | |
| Prompt Cleaner MCP Server dacebt/prompt-cleaner-mcp Enables cleaning and sanitizing prompts through an LLM-powered tool that removes sensitive information, provides structured feedback with notes and risks, and normalizes prompt formatting. Supports configurable local or remote OpenAI-compat | |
| lex-provenance-mcp dacheah/lex-provenance-mcp A read-only MCP connector for searching, fetching, and citing provenance-tracked legal corpora with verifiable content hashes. | |
| StatHead dachhack/stathead An open NFL fantasy-football analytics platform that provides live data, machine-learned projections, dynasty values, and prospect grades via an MCP server for AI clients. | |
| ABAP-ADT-API MCP-Server dachienit/mcp_abap An MCP server that facilitates seamless interaction with SAP ABAP systems to manage development objects, transport requests, and source code. It provides a comprehensive suite of tools for performing syntax checks, object searches, and code | |
| ABAP-ADT-API MCP-Server dachienit/mcp-local A Model Context Protocol server that facilitates seamless communication between ABAP systems and MCP clients for managing ABAP objects, transport requests, and code analysis. It acts as a wrapper for the ABAP ADT API to enhance the efficien | |
| ABAP-ADT-API MCP-Server dachienit/mcp-server An MCP server that enables seamless communication between ABAP systems and MCP clients using the ABAP Development Tools (ADT) API. It provides tools for managing ABAP objects, handling transport requests, and performing code analysis direct | |
| Claude Code Starter Kit MCP dachivadachkoria/claude-code-starter-kit Enables AI-powered automated testing, security scanning, code review, and maintenance tasks directly within Claude Code or desktop. | |
| Godot Docs MCP dachnikrus/godot-docs-mcp Enables searching and retrieving Godot documentation pages using fuzzy search, with support for multiple documentation versions. | |
| Cuéntica MCP dacmail/cuentica-mcp MCP server to interact with the Cuéntica accounting API, allowing users to manage invoices, expenses, income, clients, providers, and bank accounts via natural language. | |
| indexa-capital-mcp-server dacmail/indexa-capital-mcp-server A read-only MCP server that enables Claude to monitor Indexa Capital investments, providing tools to query portfolio summary, account details, performance, transactions, and fees. | |
| Contextual Memory MCP dacodechick/contextual-memory-mcp A local-first persistent contextual-memory engine with an MCP adapter for AI models such as Qwen. | |
| GhidraMCP dacodechick/ghidramcp MCP server that allows LLMs to autonomously reverse engineer applications using Ghidra, exposing tools like decompilation, renaming, and listing methods. | |
| CyberMCP dacraezy1/cybermcp Enables AI agents to conduct authorized pentests and bug-bounty workflows with scope enforcement, audit logging, reconnaissance, safe vulnerability checks, payload/wordlist generation, and professional report generation. | |
| MCP HuliHealth dacsdev/mcp-hulihealth An MCP server for HuliHealth that enables automation tools like n8n to invoke HuliHealth APIs through a standard MCP interface. | |
| ossie-clickhouse MCP Server dactopus/dactopus-ossie-clickhouse Exposes an Apache Ossie semantic model over MCP so AI agents can discover metrics, dimensions and relationships, then translate business-term questions into a single ClickHouse query. Also serves the generated SQL and model descriptions, le | |
| protonmail-mcp dadamonis/protonmail-mcp Enables AI assistants to read, search, send, reply, and organize ProtonMail emails through a local ProtonMail Bridge, with automatic Bridge discovery and pinned TLS verification. | |
| MCP SOP Server dadapera/mcp-sop-server Enables AI agents to search and retrieve Standard Operating Procedures using semantic search with Italian language support, powered by ChromaDB and RAG for intelligent document retrieval from categorized SOP collections. | |
| AiTop Club dadcz/aitop-club The first open catalog and community for AI agents. Register, search, share skills, find partners. REST API + MCP. Free and open forever. First Czech MCP server included. | |
| WHOIS MCP Server dadepo/inet-registry-mcp Enables network information lookup through WHOIS and RIPE Database queries. Supports domain/IP/ASN lookups, AS-SET expansion, route validation, and contact information retrieval across multiple Regional Internet Registries. | |
| Pinterest Ads MCP dadof3bytes/pinterest-ads-mcp Connects an AI assistant to a single Pinterest ad account so it can read campaign, ad, and analytics performance data, run account audits, and apply guarded changes such as previewing and then confirming campaign, ad, keyword, and Pin updat | |
| sn-mcp dadshorts/sn-mcp Enables LLMs to securely query and optionally write to ServiceNow instances with strict allowlist/denylist safety controls. | |
| warmstart dadwritestech/warmstart An MCP server that exposes a verified manifest of a repository's development commands, allowing AI coding agents to instantly learn the correct dev loop without trial-and-error. |
41,601–41,650 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.