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 |
|---|---|
| code-recall abians/code-recall Gives AI coding agents persistent memory by storing observations, decisions, and learnings in a local SQLite database with vector search, full-text search, and a rules engine. | |
| inspector-mcp abians/inspector-mcp A Node.js debugger for AI agents that enables setting breakpoints, stepping through code, and inspecting variables via the Chrome DevTools Protocol. | |
| semarcy-mcp abicyclerider/semarcy-mcp MCP server providing RAG-powered access to Semarchy documentation (xDM, xDI, xDG) for AI assistants. | |
| whisper-telegram-mcp abid-mahdi/whisper-telegram-mcp An MCP server that enables transcribing local audio files and Telegram voice messages using OpenAI's Whisper via local inference or cloud API. It supports multiple audio formats, automatic language detection, and optional word-level timesta | |
| Shopmium MCP Server abidil98/shopmium-mcp-server A custom MCP server that provides high-level tools for controlling Shopmium and Quoty apps on Android emulators, allowing for automated app navigation, interaction, and testing without needing to handle low-level implementation details. | |
| eSewa-Khalti MCP abidit/esewa-khalti-mcp Integrates eSewa and Khalti payment gateways into Claude, enabling payment processing via natural language. | |
| mcp-virustotal abigaila6591/mcp-virustotal Gives AI agents access to the VirusTotal v3 API, returning detection reports and analyst-style pivots such as contacted hosts, dropped files, resolutions, and threat actors for files, URLs, IPs, and domains. Also supports corpus search with | |
| Recall abigailhassan/recall Enables Claude and other AI agents to store directives, decisions, code patterns, and knowledge persistently, then retrieve relevant context automatically across sessions so memories survive context limits, restarts, and compaction. Memorie | |
| Typst MCP Server abigaillewandowski/typst-mcp Enables AI models to interact with Typst by converting LaTeX to Typst, validating Typst syntax, retrieving Typst documentation, and rendering Typst code as images. | |
| mcp-spreadsheet abigaillopes-eng/por_mcp Enables MCP clients to read, create, update, and summarize .xlsx spreadsheets in an isolated directory, with resources for catalog and metadata, tools for range reading, row appending, cell updates, and numeric summaries, plus a reusable sa | |
| caldav-mcp abigailsolovyov/caldav-mcp Enables AI assistants to connect to CalDAV servers and perform calendar and task operations, including listing calendars/events, creating, updating, and deleting events, and managing VTODO tasks with scheduling, recurrence, status, and pagi | |
| Keystone abijith-kumar-sinha/keystone Enables MCP clients to query an organisation's merged-PR history as a FalkorDB graph, computing bus factor, module risk and successor candidates with the evidence path behind each answer. It also forks the graph to simulate a person's depar | |
| Jokes MCP Server abilashraghuram/mcpdemo Enables users to retrieve jokes from various categories including Chuck Norris jokes and dad jokes. Provides a humor-focused tool that can be integrated into Microsoft Copilot Studio agents for delivering appropriate and engaging jokes upon | |
| iso26262-agent abinash009/iso26262-agent AI-powered MCP server for automotive functional safety engineering. Enables generation of HARA, FMEA, safety requirements, and compliance checks grounded in ISO 26262 standards. | |
| sync-spec-agent abinash009/sync-spec-agent AI-powered MCP assistant for telecom synchronization standards (ITU-T & 3GPP). Ask questions about PTP, SyncE, GNSS, timing budgets in plain English and get answers with exact standard references. | |
| mlops-engine abinash123hg/agentic-mlops-mcp-engine Enables local offline machine learning workflows, including CSV profiling and cleaning, classifier and neural network training, hyperparameter optimization, evaluation metrics, confusion matrix plots, Streamlit dashboards, and HTML reports | |
| MCP WebPilot abinash123hg/mcp- Connects a local multimodal Ollama model to browser automation over MCP, letting an agent observe a page's DOM and screenshot, then plan and execute one safe Playwright action at a time until the task finishes. Includes a safety gate and au | |
| SkillsWebMcp abinashbalaraman/skills-webmcp Enables AI agents to discover and execute over 1,000 developer skills and tools via MCP and WebMCP, with progressive disclosure for efficient token usage. | |
| repro-mcp abindoff/repro-mcp An MCP server that logs AI-assisted scientific computing sessions, capturing prompts, responses, decisions, and environment snapshots to human-readable markdown files for reproducibility. | |
| ena-biosamples-mcp abinesh-t/ena-biosamples-mcp Enables researchers to query public ENA and BioSamples genomics data in plain English through any MCP client, including counting records, searching samples, retrieving sample details, and checking metadata quality against project requiremen | |
| MCP Server Kubernetes abinesh0206/kube-mcp Enables comprehensive Kubernetes cluster management through kubectl operations, Helm chart deployments, pod troubleshooting, and node management. Supports both read-only and full cluster administration capabilities with built-in safety feat | |
| one-chrome abinmadathil07/one-chrome Lets several AI clients drive one shared, signed-in Chrome at the same time, giving each session its own background tabs and tab group with per-tab leases so mutations queue while reads overlap. Exposes a full Chrome DevTools-style toolset | |
| vivid-odoo abipsha/vivid-odoo-mcp Enables direct, unattended read/write access to the Vivid Windows Odoo CRM over its external API, so lead syncs run without a browser tab or Chrome extension. It provides guarded CRUD and workflow helpers for lead lookup, deduplication, mer | |
| fincon abishai95141/fincon Enables AI assistants to perform financial reconciliation with a deterministic proof engine: intake files, match transactions, verify proofs, resolve exceptions, and sign off on balanced journals under the user's authority. | |
| SF Tech Week MCP abishakkodi/tech-week-mcp Enables read-only discovery and planning of San Francisco Tech Week events, including searching by hosts, topics, dates, and building itineraries or calendar drafts. | |
| Book Library MCP Server abishek-0607/library-management-mcp Enables Claude or any LLM to manage a book library via MCP tools, allowing listing, searching, creating, updating, and deleting books through natural language. | |
| Forge MCP abishekrsrikaanth/laravel-forge-mcp Lets AI coding agents securely operate self-hosted Laravel Forge servers and sites, including deployments, logs, queue workers, environment files, commands, and maintenance tasks under per-token permissions. | |
| RavensPort abishekvupputur/ravensport RavensPort is an MCP proxy that lives in your tray and listens on 127.0.0.1. Point Claude, Cursor, VS Code or any other MCP client at it, and each agent gets one endpoint carrying exactly the tools you granted, from as many MCP servers and | |
| Gemini MCP Server abiter81/gemini-mcp-server Enables users to ask questions answered through the Google Gemini REST API's generateContent endpoint, exposed as a single tool that accepts a prompt plus optional model, temperature, and token-limit settings. It runs locally over stdio and | |
| Zvec MCP Bridge abivan-tech/zvec-mcp Indexes project source files into a local Zvec vector database and provides semantic search through MCP tools, enabling natural-language queries over code. | |
| tasas-ve-mcp abixaiprin/tasas-ve-mcp Enables AI assistants to retrieve Venezuela’s official BCV USD and EUR rates plus a USDT P2P market reference, convert amounts between bolívares and those currencies, and calculate the exchange-rate gap. | |
| ltagent-mcp abiyulingga/ltspice-mcp Generates, simulates, and inspects LTspice circuits via MCP tools and resources, providing structured JSON interfaces for AI agents. | |
| reg-docs-mcp abiz95/reg-docs-mcp An MCP server that answers questions over insurance and regulatory documents using retrieval-augmented generation, returning grounded, cited passages via local embeddings and OpenSearch. | |
| MCP OAuth Gateway abj453demo/mcp-oauth-gateway A transparent proxy server that simplifies authentication by chaining its own OAuth layer with an upstream MCP server's credentials. It manages dual token sets behind a single interface, enabling secure and streamlined access to protected M | |
| io.github.abl030/pfsense-mcp abl030/pfsense-mcp An MCP server that gives AI agents full control over pfSense firewalls via the REST API v2, with 677 tools covering firewall rules, NAT, VPN, services, routing, certificates, users, diagnostics, and more. | |
| slskd-mcp abl030/slskd-mcp An MCP server that gives AI agents full control over slskd, a modern Soulseek client, enabling search, download, browse peers, monitor transfers, and manage the slskd instance. | |
| Web Auth MCP Server ablagodarenko/web-auth-mcp Enables executing HTTP requests with automatic browser-based authentication, supporting OAuth, form login, and cookie/session management. | |
| jev-mcp ablau911-ux/jev-mcp Enables coding agents to ask typed yes/no, choice, score, and bounding-box questions about code, diffs, logs, and screenshots, returning structured decisions with calibrated confidence, caching, and cost controls. | |
| ablaut-mcp ablaut-dev/ablaut-mcp Enables AI agents to conjugate verbs in 14 European languages via a hosted Rust API, requiring only a free API key. | |
| Local Computer Agent MCP ablazeghr/chat-local-agent-mcp Enables ChatGPT to privately read and edit files, run PowerShell/Git Bash commands, and maintain persistent interactive terminals on a Windows host through authenticated remote MCP. | |
| agent-mosaic-skill able-rip/bmbrick-photo-to-lego-mosaic-skill Official BMBrick engine for converting local images into high-fidelity LEGO-style brick mosaics for AI agents. | |
| plugins abletime/claude-plugin Enables AI agents to track time, manage the project board with epics, milestones, schedules and dependencies, and generate shareable reports through a single authenticated connection. | |
| shop-mcp ablinovsibset-spec/internet-shop-mcp A read-only MCP server that lets AI agents run safe, specialized analytics over an internet shop's SQLite database, covering customers, products, orders, and revenue. It exposes no generic SQL or write tools, so agents can answer questions | |
| mcp-remote abluva/mcp-remote Bridge that lets stdio-only MCP clients connect to remote MCP servers with OAuth and other auth support, enabling local clients to use remote, authorized MCP servers. | |
| mcp-request-idempotency-reference abluva/mcp-request-idempotency-reference Demonstrates the proposed idempotencyKey mechanism on tools/call with server-side deduplication and conflict fingerprint rejection. Includes a runnable client demo showing retry dedup and conflict behavior. | |
| gflow-cli abm-dungtq/gflow-studio Enables AI agents to generate and edit Google Flow images and videos, run batch storyboards, manage projects and characters, check credits, and download 1080p clips through a signed-in Flow account. | |
| tqd-voice abm-dungtq/tqd-voice MCP server for Vietnamese text-to-speech with voice cloning, 10 built-in voices, text normalization, and long-form queuing, running 100% locally. | |
| agent-hub abn/agent-hub Enables a fleet of AI agents to connect over MCP to a local-first hub, where they can read time-ordered project feeds, keep session-scoped memory that survives compaction and resume, exchange artifacts, and send finished work or approval re | |
| TekAutomate MCP Server abnasim/tekautomate-mcp An AI orchestration layer that enables automated control and validation of test and measurement instruments using SCPI commands and tm_devices. It provides tools for project knowledge retrieval, command materialization, and deterministic sh | |
| consilience abner-machado/consilience Finds missing links between notes in an Obsidian vault by analyzing embeddings locally. Exposes tools to suggest missing links across the vault or for a specific note. |
23,201–23,250 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.