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 |
|---|---|
| Ansible Avoid common Ansible mistakes — YAML syntax traps, variable precedence, idempotence failures, and handler gotchas. | |
| Anxiety (Tracker, Trigger Map, Coping Planner) Track anxiety episodes, triggers, thoughts, and coping responses with therapy-ready logs, weekly trend reviews, and safety-first escalation cues. | |
| API / Application Programming Interface Integrates and debugs third-party REST and GraphQL APIs: auth, rate limits, pagination, webhooks, with reference for 147 services. Use when calling Stripe, OpenAI, GitHub, Slack, Twilio, or any external service, when a request that should w | |
| App Launch and scale mobile apps with ASO, viral loops, monetization, and App Store growth tactics. | |
| App Store Publish and manage iOS and Android apps with account setup, submission workflows, review compliance, and rejection handling. | |
| App Store Connect Manage iOS apps, TestFlight builds, submissions, and analytics via App Store Connect API. | |
| Apple Calendar (MacOS) Use local CLI to manage Apple, Google, iCloud, Outlook, CalDAV, and other calendars synced in macOS Calendar, without API keys or OAuth. | |
| Apple Health Connect agents to Apple Health exports with MCP setup, schema validation, and privacy-safe analysis. | |
| Apple Mail (MacOS) Use local CLI to manage Gmail, Outlook, iCloud, Yahoo, Fastmail, and other mail accounts synced in Apple Mail on macOS, without APIs or OAuth. | |
| Apple Maps (MacOS) Search places, open routes, and run Apple Maps workflows on macOS using local CLI commands and shortcut automation with explicit safety checks. | |
| Apple News (MacOS) Open Apple News, read Apple News links, and run local News workflows on macOS using deterministic CLI commands and shortcut-based search fallback. | |
| Apple Pay Implement Apple Pay for web and iOS with merchant validation, token handling, and production-safe checkout flows. | |
| Apple Search Ads Plans, launches, and optimizes Apple Search Ads (Apple Ads, ASA) campaigns for iOS apps: bids, keywords, budgets, CPA, attribution. Use for paid iOS user acquisition and App Store ads — launching or restructuring campaigns, mining search-te | |
| AppleScript Write and run safe AppleScript automation on macOS with dictionary discovery, robust quoting, and deterministic read-first workflows. | |
| Apps Find, compare, and organize mobile apps with personalized recommendations and preference tracking. | |
| Arabic Write Arabic that sounds human. Not formal, not robotic, not AI-generated. | |
| Arbitrage Find, validate, and compare arbitrage opportunities across markets with fee-aware math, execution sequencing, and failure-mode checks. | |
| Arbitrum Assist with Arbitrum One transactions, bridging, gas optimization, and L2 ecosystem navigation. | |
| Architect Design buildings and spaces with principles of form, function, sustainability, and building codes. | |
| Architecture Support architectural understanding from home projects to professional practice and theory. | |
| Archive Capture and preserve content as intelligent snapshots with semantic search, automatic extraction, and proactive resurfacing. | |
| Arduino Develop Arduino projects avoiding common wiring, power, and code pitfalls. | |
| Argentina Plan Argentina trips with region-specific routing, money strategy, seasonal timing, and practical travel logistics. | |
| Art Guide art creation, technique development, and appreciation with practical, medium-specific advice. | |
| Article Create compelling articles using journalistic standards and engagement optimization for maximum reader impact. | |
| ASI / Artificial Super Intelligence Operate as artificial superintelligence with recursive self-improvement, cross-domain synthesis, and anticipatory problem-solving. | |
| ASO Optimize app store listings with keyword research, A/B testing, and conversion tactics for iOS and Android. | |
| Assistant Manage tasks, communications, and scheduling with proactive and organized support. | |
| Astronomy Explore the cosmos from backyard stargazing to astrophysics research. | |
| Atlassian Cloud APIs + CLIs Operate Atlassian Cloud APIs and CLIs across Jira, Confluence, Bitbucket, Trello, Admin, Forge, Compass, Opsgenie, and Statuspage. | |
| Audio Process, enhance, and convert audio files with noise removal, normalization, format conversion, transcription, and podcast workflows. | |
| Austin Navigate Austin as visitor, relocator, tech worker, or entrepreneur with neighborhoods, transport, costs, visas, and Texas-specific insights. | |
| Australia Discover Australia like a local with deep city-region coverage, practical route planning, food context, and execution-ready travel logistics. | |
| Austria Plan Austria trips with rail and road logic, alpine season timing, region-specific routing, and practical local execution. | |
| Auth Build secure authentication with sessions, JWT, OAuth, passwordless, MFA, and SSO for web and mobile apps. | |
| Authorization Build secure access control with RBAC, ABAC, permissions, policies, and scope-based authorization. | |
| Auto-Update (OpenClaw + Skills) Auto-update OpenClaw and skills with OpenClaw cron, per-skill defaults, backups, and migration-aware summaries. | |
| Automate Identify tasks that waste tokens. Scripts don't hallucinate, don't cost per-run, and don't fail randomly. Spot automation opportunities and build them. | |
| macOS Automator Automate macOS tasks by composing and executing Automator workflows through automator CLI and AppleScript control. | |
| Autonomy Expand agent capabilities by identifying tasks where human approval adds no value. Systematic delegation. | |
| Avalanche Assist with Avalanche C-Chain transactions, AVAX transfers, subnets, and cross-chain bridges. | |
| AWS | Amazon Web Services Architects, debugs, secures, and cost-optimizes AWS infrastructure — EC2, Lambda, RDS, VPC, IAM, ECS, CloudFront. Use when deploying or reviewing anything on AWS, when a bill jumps or spend has to come down, when an AccessDenied, throttle, | |
| Azure Architects, debugs, secures, and cost-optimizes Azure — VMs, App Service, Functions, AKS, Azure SQL, Cosmos DB, Entra ID, VNets, Storage. Use when deploying or reviewing anything on Azure, when a bill jumps or spend has to come down, when A | |
| B2A Sell to AI agents with machine-readable products, agent-optimized APIs, structured pricing, and discovery strategies for the agentic economy. | |
| B2B Close enterprise deals with qualification frameworks, prospecting research, pipeline management, and outreach personalization. | |
| B2C Strategy Build consumer apps with validated demand, sustainable unit economics, and growth loops that compound. | |
| Baby (Tracker, Feeding, Sleep, Triage, Visit Prep) Track baby feeds, sleep, diapers, symptoms, growth, routines, and pediatric follow-up with caregiver handoffs and safety-first triage. | |
| Backend Build reliable backend services with proper error handling, security, and observability. | |
| Backup Implement reliable backup strategies avoiding data loss, failed restores, and security gaps. | |
| Baidu Navigate Baidu Search, Maps, Baike, Wenku, and Qianfan with region-aware routing, official-source checks, and China-specific guidance. |
38,851–38,900 of 108,824
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.