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 |
|---|---|
| control-expert-mcp apexsotjo-blip/control-expert-mcp MCP server that enables AI agents to read, edit, and create PLC projects in EcoStruxure Control Expert via COM automation. | |
| RemoteConnect MCP Server apexsotjo-blip/remoteconnect-mcp Enables AI agents to discover, inspect, edit, rebuild, and save Schneider Electric RemoteConnect and SCADAPack x70 IEC logic projects, including program sections, hardware, variables, and Modbus configuration. | |
| rustchain-mcp apextheboss/rustchain-mcp Enables querying and interacting with the RustChain blockchain from Claude Code or any MCP-compatible client, including balance checks, miners, epoch info, health, and transfers. | |
| protonmail-mcp apexxapps/proton-mail-bridge-mcp MCP server that gives AI coding agents access to ProtonMail via Proton Bridge, enabling secure search, read, draft, and send of emails while keeping decrypted mail local. | |
| MCP XMind Server apeyroux/mcp-xmind A Model Context Protocol server that allows intelligent analysis and querying of XMind mind maps, providing capabilities for searching, extracting, and analyzing content across XMind files. | |
| search-box aphelion-development/search-box Provides keyless, privacy-focused web search through DuckDuckGo and SearxNG via MCP, with token-efficient tool discovery and caching. | |
| tero-mcp-lite aphelion-development/tero-mcp A lightweight, dependency-free MCP server that answers cited queries over a Tero corpus index.json via stdio JSON-RPC 2.0, with honest refusal semantics and no silent empty results. | |
| Pentest MCP aphillips0102/pentest-mcp Enables professional penetration testers to run reconnaissance, network and web scanning, content fuzzing, vulnerability templates, brute-force checks, SQLi extraction, traffic capture, and engagement report generation through MCP clients. | |
| fusion-spatial-mcp aphollis/fusion-spatial-mcp An MCP server that gives AI agents genuine 3D spatial understanding of Autodesk Fusion 360, enabling exact measurements, collision analysis, and free-space placement search, plus Fusion-native parametric authoring for clean, human-editable | |
| Cloudways MCP Server aphraz/cw-mcp A simple MCP server that provides read-only access to Cloudways hosting resources, including servers, applications, monitoring data, and team management features. | |
| Spotlight MCP api-commons/spotlight-mcp Enables AI agents to lint API artifacts (OpenAPI, AsyncAPI, Arazzo) and manage rulesets conversationally via the Model Context Protocol. | |
| npmswitch apicartops/npmswitch Enables AI agents to work with the npm registry across multiple named accounts, routing each call to the right token based on an explicit account, a matching package scope, or the default. Offers read tools for search, package details, down | |
| Octoswitch apicartops/octo-switch Enables AI agents to work with multiple GitHub accounts at once, automatically routing each call to the correct token based on an explicit account argument, the repository owner's login, or a configured default. Exposes tools for listing re | |
| Quillpost apicartops/quillpost Enables AI agents to build, check and preview LinkedIn posts using seven structured styles, then publish text, images, documents or link cards to the user's own profile through LinkedIn's official API. Also covers drafts, a local schedule a | |
| Brewteco MCP Server apiccelli/brew_mcp Integrates Brewteco APIs with AI assistants, enabling natural language queries for sales data, product performance, team analytics, customer segmentation, and detailed customer profiles across multiple store locations. | |
| kali-mcps apichat296/awsome_kali_mcpservers Enables users to run Kali Linux security tools such as Nmap, nm, objdump, strings, and tshark through MCP clients for network scanning, binary analysis, and traffic capture, with Docker sandbox support for isolated command execution. | |
| Snippy apichat4793/snippy Enables AI assistants to save and retrieve code snippets, perform semantic code search, generate language-specific style guides, create comprehensive wiki documentation, and orchestrate multi-agent documentation workflows through MCP tools. | |
| data-gov-il-mcp apichat61939/data-gov-il-mcp Enables MCP-compatible clients to discover, inspect, and query Israeli Government Open Data from data.gov.il through the official CKAN API, including datasets, resources, tags, organizations, and tabular records. Supports catalog search, me | |
| IDA Pro MCP Server apichat63350/mcp-server-idapro Enables AI assistants to interact with IDA Pro for reverse engineering and binary analysis tasks. Supports executing Python scripts, retrieving binary strings, imports, exports, and functions, and searching immediate values, text, and byte | |
| flameox apichathara/flameox Enables coding agents to coordinate local profilers, benchmark tools, trace processors, and direct targets to turn explicit artifacts or commands into bounded runtime evidence for analyzing application/native code, GPU kernels, and inferenc | |
| Kingdee MCP Server apichatshah33/kingdeemcp Enables AI assistants like Claude and Cursor to query and operate Kingdee Cloud Star ERP in natural language, covering purchasing, sales, inventory, production, cost, and financial workflows through 87 tools. | |
| apicrate-mcp apicrateio/apicrate-mcp Provides AI agents with 22 data tools across 9 domains, including IP geolocation, email risk scoring, postal codes, countries, timezones, user-agent parsing, cryptographic hashing, Bible search, and QR code generation. | |
| docs-mcp apideck-libraries/docs-mcp Lets AI agents search and read a folder of Markdown documentation at query time, exposing heading-level search, whole-page or section retrieval, and page listing as tools and resources over stdio or Streamable HTTP. Can run as a CLI, a host | |
| apidrifter apidrifter/apidrifter Enables agents to plan and run requests from OpenAPI documents, verify live API responses against specs, diff spec versions for breaking changes, and snapshot or compare MCP servers including tool descriptions. | |
| devns apiep/devns Enables managing local development domains under .test TLD, including adding/removing domains, health checks, and DNS-over-HTTPS status. | |
| Apifox MCP Server apifox/apifox-mcp-server A server that connects AI coding assistants like Cursor and Cline to Apifox API definitions, allowing developers to implement API interfaces through natural language commands. | |
| Playwright MCP Server apify/actor-playwright-mcp This server provides browser automation capabilities using Playwright, allowing LLMs to interact with web pages through structured accessibility snapshots. It enables tasks like web navigation, form filling, and data extraction without the | |
| mcp-server-rag-web-browser apify/mcp-server-rag-web-browser Implementation of an MCP server for the RAG Web Browser Actor. This Actor serves as a web browser for large language models (LLMs) and RAG pipelines, similar to a web search in ChatGPT. | |
| EU VAT Validator (VIES) apifymcpfactory-droid/eu-vat-validator-mcp Validates EU and Northern Ireland VAT numbers against the official VIES service, returning validity, company name and address, and distinguishing invalid from unavailable. Supports bulk checking up to 100 VAT IDs. | |
| Sanctions Screening MCP Server apifymcpfactory-droid/sanctions-screening-mcp Screens names and companies against OFAC, EU, UK, and UN sanctions lists with fuzzy-match scores, supporting bulk lookups for AML/KYC checks. Data is sourced directly from official government lists and cached for fast repeat checks. | |
| tech-stack-detector-mcp apifymcpfactory-droid/tech-stack-detector-mcp Detects what technologies (CMS, frameworks, analytics, etc.) a website uses by fingerprinting its HTTP response and markup, returning confidence-scored results for single or bulk URL queries. | |
| Apillon MCP Server apillon/mcp-server Enables AI models to manage decentralized storage, hosting, and NFTs via Apillon's API. | |
| API Locker apilocker/apilocker Encrypted credential vault with a 21-tool MCP server. Store and manage LLM API keys, service API keys, and OAuth credentials — then let your AI agent list, reveal, rotate, rename, pause, and proxy calls through them. | |
| APIMatic Validator MCP Server apimatic/apimatic-validator-mcp Enables validation of OpenAPI 2.0 and 3.0 specifications in JSON or YAML format using APIMatic's comprehensive API validation service through the Model Context Protocol. | |
| @apinator/mcp apinator-io/sdk-mcp Enables AI agents to publish events, inspect channels, sign channel auth, and watch live WebSocket traffic so they can build and debug realtime features end to end. | |
| apinoa-mcp apinoahq/apinoa-mcp Enables AI assistants to query live marketplace product data across major platforms, retrieve social profiles, posts, and comments, and translate text in images. It provides read-only MCP tools for commerce and social data workflows. | |
| ktzr-memory apiotrowski-afk/claude-legal-persistent-memory-pl Persistent memory server for AI assistants that stores notes with categories and tags, and enables full-text recall across sessions. | |
| krs-verify apiotrowski-afk/krs-verify MCP server for verifying Polish business entities from the National Court Register (KRS) and VAT White List. Allows querying by KRS, NIP, or REGON to retrieve official company data including name, address, board, and capital. | |
| legal-cite apiotrowski-afk/legal-cite-pl Verifies legal citations by fetching the exact, in-force wording of cited articles from official PL and EU legal sources, preventing hallucination by returning verbatim text. | |
| apipj MCP server apipj/apipj-mcp Enables lookup and validation of Brazilian companies by CNPJ, returning registration status, address, CNAE activities, Simples Nacional/MEI status, and partners from monthly Receita Federal open data, plus validation of numeric or alphanume | |
| Apirro-AI/apirro-mcp apirro-ai/apirro-mcp Infrastructure layer for agentic commerce, website AI-readiness scanning, and protocol connectivity. | |
| AITable MCP Server apitable/aitable-mcp-server AITable.ai Model Context Protocol Server enables AI agents to connect and work with AITable datasheets. | |
| meteor-mcp apitlekays/meteor-mcp Provides complete Meteor.js v3.4.0 API documentation, code examples, and architectural guides to AI coding assistants. | |
| Apito MCP Server apito-io/apito-mcp Enables LLMs to interact with Apito's system GraphQL API to build and manage headless CMS schemas, including models, fields, and relations. It allows for comprehensive model management and schema introspection through both local and Cloudfl | |
| Apitomy Data Models MCP apitomy/apitomy-data-models-mcp An MCP server that wraps the @apitomy/data-models library for querying, validating, and editing OpenAPI and AsyncAPI documents. | |
| ApiVault Remote MCP Server apivault-tech/apivault-mcp Secure, encrypted API key management for AI coding agents, enabling search, inspection, and use of credentials with scoped permissions and optional zero-knowledge decryption. | |
| dl32 apiwat59/atk-dl32-mcp Enables AI assistants to capture, measure, and decode USB logic-analyzer signals, including 16-channel streaming and sigrok protocol decoding for UART, I2C, SPI, CAN, and other protocols. | |
| PXE200 SA MCP apiwat59/pxe200-sa-mcp Enables AI assistants to drive a Harogic PXE200 spectrum analyzer through an SCPI bridge inside SAStudio4, running measurements, sweeps, traces, markers, channel power, digital demodulation, screenshots and saved states. It also builds and | |
| rigol-dho-mcp apiwat59/rigol-dho-mcp Enables an AI assistant to connect to and control Rigol DHO900-series oscilloscopes over VISA, configure acquisition, trigger, channels and timebase, use the built-in waveform generator, capture screenshots, measurements and waveform data, | |
| Jev Harness (Apixly) apixly-ai/jev-harness Experimental local stdio MCP adapter for caller-owned Python tasks and independently verified actions. Glama release 0.1.0 is a synthetic inspection build. Install from GitHub and supply your own task. |
29,851–29,900 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.