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 |
|---|---|
| hackerone-mcp axiomsec/hackerone-mcp-server A local, read-only MCP server that connects your HackerOne researcher account to Claude Desktop and Claude Code, helping you find targets, analyze program scopes, review reports and earnings, and draft bug reports. | |
| motor.mcp_server axiomzero-qed/daxqo-motor Enables harnesses to explore and navigate GUI applications, maintain persistent app maps, verify actions, cancel operations, and use pluggable device adapters over MCP. | |
| DAXQO Trajectory Collector MCP Server axiomzero-qed/daxqo-trajectory-collector Enables harnesses to record supplied GUI actions, inspect trajectory statistics, and export privacy-filtered datasets through MCP tools without executing device actions. | |
| Manufacturing Inference Advisor MCP axiovex/manufacturing-inference-advisor Enables agents to plan on-site AI inference deployments with vendor-neutral hardware sizing, specification-first BOMs, sourcing evidence screening, compliance review, and staged deployment plans. | |
| MCP Server Starter axis-data-labs/mcp-server-starter A minimal, production-ready starter for building Model Context Protocol servers in TypeScript, supporting both stdio and streamable HTTP transports with optional bearer-token auth. | |
| AGI Feeder axisassists/billionaire-mindset-agi-feeder An MCP server that routes tasks to the best AI models, aggregates responses with confidence scoring, and applies billionaire thinking frameworks for strategic decisions. | |
| ExpenseTracker MCP Server axitmakwana45-cloud/expense-tracker-remote-mcp A lightweight MCP server that lets LLM clients track, query, and summarize personal expenses using a local SQLite database. | |
| jev_triage axiumine/jev-claude-code Enables Claude to cheaply bulk-screen 30 or more short items (repo blurbs, issue titles, log lines, grep hits, test names) against one crisp yes/no criterion, using Jev to sort them into clear_yes, uncertain and clear_no buckets instead of | |
| Safari MCP Server axivo/mcp-safari Enables visual web access and browser automation through Safari, with tools for navigation, screenshots, element interaction, and tab management. | |
| Banana Accounting MCP Server axlabs/banana-mcp-server Exposes the Banana Accounting Plus Integrated Web Server API V2 to LLMs, enabling reading accounts, balances, journals, reports, and VAT data, and creating new accounting files from a local Banana Accounting instance. | |
| bioretrieval-mcp axle962/bioretrieval-mcp Enables LLM agents to search EMDB cryo-EM maps, look up UniProt proteins, compute ESM-2 sequence embeddings, retrieve cryo-EM maps from a protein sequence via a two-tower model, and search GEO DNA-methylation arrays, all through typed tools | |
| Microsoft To Do MCP axlolo/microsoft-todo-mcp Enables coding agents to manage Microsoft To Do lists and tasks through Microsoft Graph, with optional support for checklist items, linked resources, attachments, and delta synchronization. | |
| Axme-code axmeai/axme-code Persistent project memory + architectural decisions + pre-execution safety hooks for Claude Code. Local-only storage, multi-repo workspace, automatic knowledge extraction via background auditor. | |
| Binance Trading Agent MCP Server axmetov999/binance-trading-agent-mcp Connects LLM agents to Binance Spot API for safe market data access and testnet trading with built-in risk controls. | |
| tplink-mcp axo4xo/tplinkcli Enables AI agents to manage TP-Link routers by listing clients, checking status, controlling Wi-Fi, and rebooting via natural language. | |
| anamnesis axobase001/anamnesis MCP server that serves a structured belief graph extracted from Claude conversation history, enabling on-demand retrieval of personal context, projects, preferences, and relationships. | |
| Axolot MCP Server axolotdevelopment/axolot-mcp Enables AI assistants to interact with Axolot CMS for content, design tokens, media, and module management with site context awareness. | |
| mcp-home-server axolotlpi/mcp-home-server Self-hostable MCP server that gives Claude tools to run shell scripts and read files on a home server, deployed via Multipass VM and Cloudflare Tunnel. | |
| ai-distiller-mcp axonempire/ai-distiller-mcp Provides filesystem access to Claude via the MCP protocol, enabling local file operations through natural language. | |
| Axonity Flow MCP Server axonityai/axonity-mcp Enables AI agents to author and manage workflows, agents, tools, skills, policies, and reference docs in an Axonity tenant via the public REST API, with guardrails preventing direct publishing and secret exposure. | |
| MCP-MCSTATUS axorm/mcp-mcstatus Provides tools for retrieving Minecraft Java and Bedrock server status via the mcstatus.xyz API. It also includes advanced network diagnostic features such as DNS resolution, GeoIP lookups, and BGP/ASN provider information. | |
| memory-bank-mcp axrbarsic/verifiable-memory-bank Provides a read-only MCP interface to query and retrieve verifiable evidence from a local memory bank, supporting search, dossier, chronology, source, and evidence tools. | |
| Tessera axroux/tessera Exposes eight typed tools that let an agent read a messy supplier message and then safely work payment incidents on the Airwallex sandbox—deferring, replacing, escalating or certifying a transfer—while code-enforced exactly-once guarantees | |
| uk-company-check axrs37/uk-company-check Enables AI agents to query the free official UK Companies House registry through four tools: searching companies by name, retrieving merged profiles with status, registered office, SIC codes, and current officers, pulling filing history, an | |
| web-presence-audit axrs37/web-presence-audit An MCP server that lets agents run free, keyless lead-leak audits on UK local service businesses — detecting form platforms and their outreach implications, checking whether phone numbers are tappable tel: links, comparing phone numbers acr | |
| deer-flow-mcp axsapronov/deer-flow-mcp Connects MCP-compatible clients to an already-deployed DeerFlow instance over its HTTP API, exposing deep research runs, model listing, and thread, run, and artifact control as callable tools. It acts as a thin stateless adapter, so clients | |
| Uapi Mcp axt-team/uapi-mcp Official MCP server for the uapis.cn API platform, providing over 100 endpoints for network lookups, text utilities, image processing, social queries, translation, and search. | |
| MemMCP axtontc/memmcp A Byzantine fault-tolerant MCP Memory server that uses SQLite write-ahead logging and FAISS hybrid vector search for deterministic, secure memory operations. | |
| arch-viewer axumquant/arch-viewer Provides AI-powered architecture analysis and visualization of codebases, exposing 17 MCP tools for querying components, dependencies, and generating interactive diagrams. | |
| feishu-cli-mcp axunrun/feishu-cli-mcp Exposes the official lark-cli as an MCP server, enabling agents to execute arbitrary CLI commands, query API schemas, and manage authentication. | |
| 问津 axxed12/wenjin-rag Enables programming agents to retrieve internal R&D documentation with traceable, reproducible evidence through the MCP protocol, supporting multi-corpus routing and access control. | |
| Rechtspraak MCP Server axyr/rechtspraak-solr-mcp-server MCP server for searching and analyzing Dutch case law with advanced search, faceted filtering, and citation analysis. | |
| touchdesigner-agent-mcp axysar/touchdesigner-agent-mcp Enables LLMs to directly control, introspect, and build TouchDesigner networks in real-time through a Model Context Protocol server. | |
| OpenShift 4 MCP Server ay-garg/openshift-mcp-server A comprehensive Model Context Protocol (MCP) server that exposes 216 tools, 7 resources, and 10 runbook prompts for every OpenShift 4 cluster operation an SRE, developer, or operator could need — all driven by an LLM. | |
| TrendRadar MCP ay08siliang/trendradar Provides AI-powered public opinion and trend monitoring with multi-platform aggregation, RSS subscriptions, keyword filtering, translation, sentiment analysis, and trend prediction, all accessible via natural language conversations and able | |
| TruthGate ay7627514-dotcom/truthgate A fail-closed preflight, approval, evidence, and verification runtime for agents, preventing unsupported output from being treated as verified completion. | |
| Apple MCP - Enhanced Edition ayaanisthebest/applemcp Enables AI assistants to interact with native Apple applications including Messages, Notes, Contacts, Mail, Reminders, Calendar, and Maps. Features smart contact resolution, priority-based search, and comprehensive Apple ecosystem integrati | |
| YouTube Transcript MCP Server ayaanisthebest/mcp-tool-for-youtube- Enables fetching, searching, and summarizing YouTube video transcripts with multi-language support. | |
| linkedin-discovery-mcp ayaankhan0111/linkedindiscoverymcp Enables discovering public LinkedIn profiles via natural-language criteria, using DuckDuckGo search snippets to return a ranked shortlist with match reasoning, without logging into LinkedIn. | |
| EduChain MCP Server ayaanshaheer/educhain-mcp-server Integrates the EduChain library to generate educational content including multiple-choice questions, lesson plans, and flashcards for subjects like Python programming and Algebra using Grok's free-tier LLM. | |
| NAV 2015 FastMCP Server ayabenz/nav_2015_mcp Provides read-only analytics and metadata exploration for Dynamics NAV 2015 databases, enabling user details, permissions, table schemas, and autonomous SQL queries. | |
| Assets Generation MCP Server ayaka209/assets-gen-mcp An MCP server for AI image generation with dual-provider support for OpenAI-compatible models and Google Gemini. It returns standard MCP ImageContent blocks. | |
| Local DevOps MCP Server ayala-yagelnik/local-devops-mcp Enables Docker container management through natural language conversations, including deployment, health monitoring, dependency resolution, auto-redeployment on file changes, and environment snapshots. | |
| weather-Israel ayala679/weather--mcp Enables retrieving Israeli weather forecasts through real browser automation and answering user questions conversationally via Gemini. | |
| File Organizer MCP ayalaongit/mcpfolderorganizer An intelligent MCP server that analyzes folder contents to automatically categorize files and suggest meaningful naming conventions based on file types and content. It enables users to organize messy directories into structured topic-based | |
| TapeDeck ayanbhardwaj1/tape-deck-mcp Enables market-data analysis and quantitative research over a local Parquet lake with tools for bars, indicators, scans, backtests, and safe SQL queries. | |
| Smart Warehouse MCP Agent ayancodes2003/claude-mcp-agent-for-supply-chain Claude-powered warehouse management system that coordinates inventory, AGVs, and order processing through specialized agents using Model Context Protocol patterns. | |
| tiny-notion-mcp ayanot1/tiny-notion-mcp A lightweight Notion MCP server that minimizes token usage by returning Markdown instead of raw JSON, enabling efficient read/write operations on Notion pages. | |
| edisnote-mcp ayareago/edisnote-mcp Enables AI agents to browse and read notes and view images saved via a browser extension, including note text, source links, and selected images, all read-only and locally. | |
| ego-browser-hermes ayase0307/ego-browser-hermes Provides Hermes with an isolated Chromium browser task space enabling structured navigation, semantic snapshots, form interaction, screenshots, uploads, and downloads. |
32,151–32,200 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.