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 |
|---|---|
| mcp-impo daedalus/mcp-impo MCP server for accessing Uruguay's IMPO open data API with SQLite caching. Provides tools to retrieve legal norms, search regulations, and access schema documentation from Uruguay's official legal database. | |
| mcp-registry daedalus/mcp-registry An MCP server designed for interacting with the Model Context Protocol Registry API to discover and retrieve information about available MCP servers. It provides tools to search, list, and view detailed configurations and version history fo | |
| mcp-server-nmap daedalus/mcp-server-nmap Enables network scanning and reconnaissance through MCP tools, leveraging nmap for port scanning, service detection, and host discovery via synchronous, asynchronous, and streaming interfaces. | |
| mcp-snap7 daedalus/mcp-snap7 Enables MCP clients to connect to and interact with Siemens PLCs via python-snap7, supporting read/write operations on data blocks, memory, timers, counters, and CPU management. | |
| portfolio-agent daegyu519/portfolio-agent Provides grounded investment decisions with evidence links and invalidation conditions, enabling users to review their portfolio through a structured decision process. | |
| onbid-mcp daehyub71/onbid-mcp Enables LLM clients to ask plain-language questions about Korean public auction property data from the 온비드 OpenAPI, including normalized pricing, location, and failed-sale history. | |
| PowerPoint Translator daekeun-ml/ppt-translator Translates PowerPoint presentations while preserving formatting using Amazon Bedrock models, available as both a standalone tool and a FastMCP service for AI assistants like Amazon Q Developer. | |
| iqprompt-mcp daemd/iq-mcp Standalone MCP server that proxies tool calls to the IQPROMPT API, enabling prompt enhancement and session creation through natural language. | |
| google-activity-assistant daemon-killer/google-activity-assistant MCP server for querying your local Google Takeout activity (Search/YouTube history) via SQLite/FTS5. Provides tools for keyword search, activity stats, and database info, enabling AI assistants to cite your personal history. | |
| prospective-memory daemon-killer/prospective-memory An MCP server that lets users capture quick phone thoughts via Android and later query them from AI assistants like Grok or Claude, functioning as a simple task memory store without notifications or geolocation. | |
| daemons-mcp daemonpage/daemons-mcp Connects the Claude app to Claude Code by enabling it to search recent sessions, transcripts, memory files, and CLAUDE.md, and to save markdown tasks called bounties for later agent execution. | |
| mcp-audit daerda/mcp-audit A frontend security dependency auditing tool that identifies vulnerabilities in local and remote repositories using the Model Context Protocol. It provides detailed audit information like CVSS scores and dependency chains, generating standa | |
| Korean Law MCP daeryundf2-prog/korean-law-mcp Enables AI assistants and terminals to retrieve and cross-reference Korean legal sources through 10 tools built on 42 Ministry of Government Legislation APIs, covering statutes, precedents, administrative rules, ordinances, treaties, and in | |
| tokenectomy-git daffa2555/tokenectomy-git for tokenectomy git workflow | |
| jekyll-component-mcp daffadevhosting/jekyll-component-mcp Enables AI agents to understand, inspect, create, validate, build, and document Jekyll component frameworks through Jekyll-aware tools, resources, prompts, sandboxed filesystem access, and configurable write modes. | |
| safe-mathjs-mcp daffamumtaz2361/safe-mathjs-mcp Safe MCP server for math operations: evaluate, simplify, and differentiate expressions with configurable precision, using a sandboxed worker thread and strict AST allowlist to block dangerous input. | |
| Telegram Drive MCP Server daffaroffi/telegram-drive-mcp Enables AI assistants to manage Telegram files, messages, and dialogs directly via MTProto, supporting upload, download, search, forwarding, and storage overview operations. | |
| mcp-openems dafloresco/mcp-openems Enables an AI agent to drive the openEMS FDTD electromagnetic simulator in two teaching modes: executor, where the agent designs, simulates and tunes antennas, and tutor, where the student designs while the agent may only run, inspect and e | |
| Kronvex daftgoldens/kronvex Persistent memory API for AI agents — store, recall, and inject semantically-searchable context across sessions. EU-hosted, GDPR-compliant. Supports Claude, Cursor, Cline, and any MCP-compatible client. | |
| cn-websearch-mcp daftpunkwav/cn-websearch-mcp Enables unified web search across multiple Chinese LLM providers (Kimi, Xiaomi MiMo, Zhipu GLM, and StepFun) via a single MCP tool, with configurable provider priority, automatic fallback, multi-source aggregation, timeouts, and retries. | |
| rag-mbti MCP server dafuqhappen/rag-mbti Enables any MCP client to search, filter, and retrieve socionics type reference data through hybrid search, exact dichotomy filters, type-card lookup, full-type resources, and comparison prompts. | |
| helm-mcp dagamon/helm-mcp MCP server exposing the HELM dashboard REST API as tools for managing services, scripts, and system operations. | |
| iOS Development MCP Server dagba/ios-mcp An MCP server that provides comprehensive tools for managing iOS simulators, including device control, app lifecycle management, and UI automation. It enables developers to boot devices, install apps, capture screenshots, and simulate user | |
| repo-contract dager23/repocontract An MCP server that enforces repository governance rules for AI coding agents, providing tools to validate plans, diffs, and scan for architectural and safety violations. | |
| Clinical Conversation Coach for Alexa+ daggerstuff/alexa-submit Enables scenario-based clinical communication practice through MCP tools for discovering scenarios, starting sessions, sending practitioner turns, and receiving evidence-linked evaluation feedback. | |
| GitMCP daggubatikundan/model-context-protocol-git-mcp Transforms any GitHub repository into a documentation hub for AI assistants, enabling up-to-date access to documentation and code to eliminate hallucinations. | |
| selenium-mcp-server dagiim/selenium-mcp-server An autonomous, self-managing MCP server providing comprehensive UI analysis, cross-browser testing, and intelligent browser automation with zero-configuration setup. | |
| quillink-mcp dagistankaradeniz/gcp-note-taking-mcp A read-only MCP server for accessing Quillink notes, folders, and tags, enabling AI tools like Claude to search, retrieve, and list notes and related metadata. Requires a Pro Quillink plan and supports OAuth or personal access token authent | |
| mcp-dev-servers dagonet/mcp-dev-servers Provides 7 MCP servers with 95 tools for git, GitHub, .NET, Ollama, Rust, template sync, and Python, enabling natural-language commands to perform real development operations. | |
| Excalidraw Architect MCP dagostini4108/excalidraw-architect-mcp Enables AI coding assistants to turn architecture and engineering concepts into auto-laid-out, hand-drawn Excalidraw diagrams across 25 types, with natural-language revision and SVG/PNG export. Optionally persists systems as a queryable, ve | |
| arxiv-latex-mcp dagostini457/arxiv-latex-mcp Enables MCP clients to fetch and process arXiv LaTeX sources, giving LLMs accurate access to equations, notations, abstracts, and individual paper sections for precise mathematical interpretation. | |
| MCP Server with OpenAI Integration dagudelot/mcp-server-openai-sdk Enables automatic weather information retrieval through a custom MCP server integrated with OpenAI using Cloudflare tunnels. Demonstrates seamless function calling between OpenAI and custom MCP tools without manual intervention. | |
| mcp-youtube-transcript dahbimoad/mcp-youtube-transcript Enables retrieving plain-text transcripts from YouTube videos in any available language, including auto-generated captions, by providing a URL or video ID. | |
| Muninn dahch/muninn Enables AI coding agents to persistently save and search project knowledge — categorized observations such as decisions, conventions, discoveries, and bugfixes — ranked with full-text search and linked to an indexed TypeScript symbol graph | |
| arXiv Research Assistant MCP Server daheepk/arxiv-paper-mcp An MCP server that allows Claude AI to search, explore, and compare arXiv papers efficiently through a custom-built local server. | |
| Clipboard MCP dahlia/clipboard-mcp Provides tools for reading and writing system clipboard data across Linux, macOS, Windows, and WSL platforms. | |
| daho mcp dahoai/cli Enables MCP clients to list connected apps and connections and to read from or write to those apps' native APIs (Gmail, Google Ads, HubSpot, Stripe, Resend and more) through the DAHO API gateway using a single API key. Reads and writes are | |
| Phone Carrier Detector MCP Server dahuangbaojian/sms-mcp-server Detects Chinese mobile phone number carriers (China Mobile, China Unicom, China Telecom, etc.) and their geographical location (province and city) using a database of 492,088 records. Supports both single and batch number detection (up to 1 | |
| sloth-mcp dahx5/sloth-mcp MCP server that lets Claude use your Mac — native apps and the browser — by remembering what it has seen instead of screenshotting every step. | |
| Document Operator MCP dai-zw/document-operator-mcp Enables AI assistants to read, modify, and create Word (.docx) and Excel (.xlsx) files through natural language commands, including batch queries and temporary table management. | |
| libreoffice-mcp-writer daidahan/libreoffice_mcp_writer Enables Claude to create, edit, and format .odt documents through the UNO API with headless operation and sandboxed access to a single documents folder. It supports text, lists, tables, paragraph styles, and character formatting via MCP too | |
| AstroInsight Research Assistant daiduo2/generate-hypothesis-mcp Enables AI-powered academic research workflow from keyword search to hypothesis generation. Integrates multiple AI models to automatically search ArXiv papers, extract key information, and generate innovative research hypotheses for researc | |
| strength-training-mcp daiduo2/strength-training-mcp A stateless MCP server that exposes tools for evidence-based strength training, including classical powerlifting programs and fatigue management. | |
| CATIA V5 MCP Server daiemon12/catia-v5-mcp-server Connect Claude AI to Dassault Systemes CATIA V5 via the Model Context Protocol (MCP). Drive CATIA V5 CAD modeling from Claude Desktop or Claude Code using natural language. | |
| Sprinklr MCP Server daiict218/sprinklr-mcp Enables AI assistants read-only access to Sprinklr data via MCP, allowing querying reports, searching cases, and calling Sprinklr API endpoints. | |
| Rybbit MCP Server daikazu/rybbit-mcp-server An MCP server for interacting with the Rybbit Analytics API, enabling querying analytics data, managing sites, tracking events, and more. | |
| MCP GitHub Project Manager daiki35/mcp-github-project-manager Turns GitHub Projects v2 into an agentic task substrate where AI coding agents register, atomically claim and complete tasks, exchange heartbeats, review one another's work products, and operate within token budgets. Humans get AI-powered P | |
| mellos-mapping daiki806/mellos-mapping Exposes eight mmap_* tools that let an agent declare a system's ghost dependency design first, then light each node up as it is built and verified, with downward-only edges and evidence-backed green status. Clients get a live ledger of what | |
| byob daikihunter/byob A local MCP server that enables AI coding assistants to drive the real, already-logged-in Chrome browser — navigating pages, clicking, typing, reading content, taking screenshots, and inspecting tabs, cookies, and network traffic through na | |
| OpenClaw MCP Server daikiishii96/openclaw-mcp Enables Claude clients to securely connect to self-hosted OpenClaw assistants via OAuth 2.1, send synchronous or asynchronous chat messages, check gateway health, and manage long-running tasks. It also supports routing requests across multi |
41,651–41,700 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.