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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| kala-mcp anusornc/kala kala memory over MCP: provenance-first agent memory with Datalog recall and as-of time travel. | |
| StyleKit anxforever/stylekit MCP server for StyleKit styles, tokens, recipes, lint and repair over stdio or HTTP. | |
| Lawn Mowing Calculator any1tan/lawn-mowing-calculator-mcp Lawn area, mowing time and mowing price estimate tools for AI assistants. | |
| Watts Calculator any1tan/wattscalc-mcp Watts, volts, amps, kWh and electricity cost calculator tools for AI assistants. | |
| Anymail Finder anymailfinder/amf Find verified work emails from a name, company, role or LinkedIn URL, and verify emails you have. | |
| Indonesia Economic & Financial Data anyoneo/idn-econ-mcp Indonesian and ASEAN economic data for AI agents: inflation, GDP, projections to 2031, FX vs IDR. | |
| Anyway Possible Paid Agent Utilities anyway-possible/public-api Paid x402 tools for merchant intelligence, Base payment readiness, and verifiable web evidence. | |
| hum anzal1/hum Free music for your coding agent. Play songs, mood stations and Spotify links in your browser. | |
| com.benriscore/api aoki-h-jp/benriscore Purpose-aware accessibility scoring for every coordinate in Japan. | |
| AON — Agent Offer Network aonpro-dev/aonpro-mcp Real, buyable product and service offers — live pricing and trackable links for any MCP agent. | |
| MCP Agent Health Reporter aos-standard/mcp-agent-health Advisory AOS agent health scan before deployment (manifest, services, immune loop, evidence). | |
| MCP Blast-Radius Auditor aos-standard/mcp-blast-radius Static blast-radius audit for MCP servers before agent install. Manifest optional. | |
| Finance MCP aowang-ai/finance-mcp-connectors Hosted MCP server for SEC, FRED, Polymarket, Deribit, OKX, and FMP. | |
| Apaleo apaleo/mcp Manage hotels via the apaleo PMS API: reservations, folios, invoices, rates and availability. | |
| TrainTools aparajeets/traintools Recommend paper-backed diagnostics for PyTorch and Hugging Face training problems. | |
| PAYNE Commercial Truth & Machine Revenue Exchange apayne1987-droid/-payne-autonomous-product-factory Verify live jobs/RFPs, deadlines, eligibility, terms changes, and Base/web data via x402. | |
| Arquestra — Scientific Computing Orchestration apertura-ai/arquestra-claude-plugin AI orchestration for computational chemistry and HPC workflows. | |
| Apex AI Academy apexai-academy/sample-agents Co-Learn with your Agent: fact-checked AI lessons with Human and Agent views. | |
| ApexCharts apexcharts/apexcharts-mcp Generates and validates configs for ApexCharts charts, grid, gantt, tree, sankey, stock and maps. | |
| com.apievangelist/api-evangelist api-evangelist/apievangelist-aws Sixteen years of API research as MCP tools — stories, areas, governance blocks & services | |
| JarvisClaw — AI Gateway & API Marketplace api-jarvisclaw/jarvisclaw-mcp 320 AI models + 2,720 pay-per-call APIs. x402 USDC on Base or Solana, no API key. | |
| io.apis/apis-io api-search/apis-io-aws Discover, rate and compare APIs and providers in the APIs.io catalog; manage a listing you own. | |
| io.github.api-sketch-2030/tax-validator api-sketch-2030/tax-validator Validates Moroccan ICE and IF tax identification numbers. | |
| EU VAT Validator (VIES) apifymcpfactory-droid/mcp-factory-servers Bulk-validates EU VAT numbers against the European Commission's official VIES service. | |
| io.github.apihubio/mcp-server apihubio/mcp-server Discover and pay for APIs with USDC credits. No wallet, no gas, MCP-native marketplace. | |
| API Locker apilocker/apilocker Encrypted credential vault: LLM, service & OAuth keys. 21-tool MCP server for your AI agent. | |
| DOMShell apireno/domshell Drive Chrome with filesystem commands (ls, cd, grep, click, type). One MCP tool, multi-agent. | |
| Sample Shop MCP server apitoagents/mcp-examples Sample shop MCP server: paginated search, idempotent orders, guarded cancellation. Four languages. | |
| Jev Filter apixly-ai/jev-filter Read-only semantic filtering, code search, log triage and traceable evidence for AI agents. | |
| XAPS MCP Server apmc1/xaps-sdk Pre-execution audit for autonomous agents. Independent receipt before irreversible actions. | |
| io.github.apolocine/orm-mcp apolocine/mosta-orm-mcp MCP server for @mostajs/orm: generate, lint (24 rules) & migrate EntitySchemas. | |
| Hyades apology-is-policy/hyades Render LaTeX math as pure Unicode text art for terminals, code comments, and emails. | |
| AlloFlow Document Remediation apomera/alloflow Local-first document accessibility remediation using the canonical AlloFlow app pipeline. | |
| HARBOR Port aporb/harbor-port Hosted MCP servers for US federal data: 19 servers, 147 tools, one endpoint. | |
| Site Doctor — WordPress diagnosis aporce1/sitedoctor-mcp Read-only WordPress diagnosis for AI: security, performance, forms and downtime, with evidence. | |
| io.github.Apoth3osis-ai/agent-payment-mcp apoth3osis-ai/agent-payment-mcp Secure MCP router providing access to AgentPMT's pay-per-use AI tools marketplace. | |
| com.agentpmt/agentpmt apoth3osis-ai/agentpmt-mcp-public AI agent marketplace for automated employees, workflows, skills, and tool orchestration. | |
| devBoard app-tube/devboard-mcp Tasks, comments, start and finish work, and time tracking in devBoard, a small-team tracker. | |
| PromptOT appdevexpert/prompt-ot Manage, version, and publish LLM prompts with blocks, variables, and evaluations. | |
| Applied Form engine applied-form/engine Lint rendered pages against a design system in a real browser, across six widths, with the fix. | |
| Standards by Applied Form applied-form/standards Lint rendered pages against a design system in a real browser, across six widths, with the fix. | |
| com.applivery.docs/mcp applivery/docs-front Search and read the public Applivery docs (MDM & app distribution). Read-only, no auth. | |
| Appllama appllama/appllama-skills Study screens, flows and paywalls from top-earning iOS apps, then build from what wins. | |
| ApplyAll applyallinc/applyall Search for jobs and apply to jobs. | |
| MaShop MCP appmashop/mashop-app Build, deploy and manage MaShop e-commerce projects from Claude, Cursor or any MCP client. | |
| App Pain API apppainapi/app-pain-api What users hate about ANY iOS/Android app: clustered complaints, evidence, trends. No key needed. | |
| Appraisily appraisily/appraisily-openai-mcp Check past auction prices in ChatGPT, plus appraisal prep and sample reports. | |
| FAIR Appraisers appraisily/fair-mcp-server Search public FAIR appraiser profiles by location, specialty, and intended use. | |
| AppScreenStudio appscreenstudio/appscreenstudio-mcp Design App Store and Google Play screenshots with your AI agent in the AppScreenStudio editor. | |
| app.decibelshield/decibel-shield appstackllc/decibelshieldwebsite Noise data tools: city noise rankings, decibel levels of common sounds, NIOSH safe-exposure math. |
20,551–20,600 of 50,909
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.