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 |
|---|---|
| Atlas Primer Voice Roleplay Create real-time AI voice roleplay simulations and behavioral assessments on Atlas Primer. | |
| Attestwire EN 16931: validate invoice data, UBL/CII or PDF; emit XRechnung/Peppol XML, never a PDF. | |
| Attrove Catch conversations going quiet — watch outcomes and search Gmail, Slack, and meetings. One MCP. | |
| Aurentia Your Aurentia workspace — projects, CRM, tasks, deliverables — in Claude, Cursor or any MCP client. | |
| Autopo Run your AI-run company from Claude Code, Codex, Cursor or ChatGPT: inbox, tasks, team, Studio. | |
| Launchpad Check an AI-built app is safe to launch, then deploy it on accounts you own. | |
| Babelize Make apps global-ready from your coding agent: analyze, translate, check and review i18n locally. | |
| io.github.thehomer87/badge-mcp-server Screen AI agents, read Badge fitness scores, and browse the public Talent Pool leaderboard. | |
| JSONPad documentation JSONPad docs, API, SDK and CLI references, and offline checkers for write rules and flows. | |
| JSONPad Build and run a JSONPad backend: lists, items, indexes, write rules, schema sync, history, flows. | |
| Basiiik Design system for coding agents: component specs, rules, tokens, icons and checked React snippets. | |
| bot.beck/beck Project management for coding agents: record the approved plan, work the tasks, ask, hand off. | |
| BenchBoss Play Chess, RPS-N and Safehouse Protocol via MCP. Public replays; GitHub verification required. | |
| Binary & Thread Browse the Binary & Thread catalogue, stage a cart, get a checkout link. No card data in chat. | |
| Blackwood State Pay-per-call tools for agents: onchain data, ECB FX rates, text tools. USDC on Base, x402 | |
| Agent Guestbook Read and verify the Blue Cloud Cyber agent guestbook, and sign one Ed25519 entry per UTC day. | |
| Odin Read Odin security findings and remediation, link fix pull requests and track retests. | |
| Brainfeather Long-term memory for AI coding agents: durable project facts, recalled by every MCP client. | |
| design.brilliant/mcp Local MCP bridge: your coding agent designs on Brilliant's real vector canvas, fully on 127.0.0.1. | |
| tech.bugbrain/mcp BugBrain QA platform for AI coding tools: autonomous exploratory testing, test plans, a11y audits. | |
| Burnbound Let your AI agent pay x402 APIs within daily caps, allowed hosts and human approval. | |
| io.github.helloderekg/bytario 40 MCP tools for image, PDF, QR, barcode, data, text, color, and render operations. | |
| Caliu Notes Read and write your Caliu notes from any MCP client: search, create, tag, remind, attach files. | |
| Callirra Create images, video and audio; chat with multimodal AI; manage assets and reusable workflows. | |
| Tsiky Turn your photo into a cartoon character and make animated explainer videos, step by step | |
| Cargo Find and verify work emails, enrich companies and contacts, score leads and sync to your CRM. | |
| io.github.hawthornhollows/passage-protocol Departure and admission records for AI agents with Ed25519/P-256 signatures. | |
| buy Pay per request for APIs, compute, browsers, RPC and LLM inference with stablecoins on Celo. | |
| Ceraph MCP server for agent-driven React Native and Expo development and mobile testing | |
| io.github.srbryant86/mcp-server Sign AI output for EU AI Act + FRE 902 compliance, verify content authenticity provenance | |
| io.github.CesarObedFL/aws-spapi-mcp MCP server for Amazon SP-API - real-time inventory health, sales metrics, and price updates | |
| Chain Daddy Search tokens, check registrations, and run a Chain Daddy creator store from your agent. | |
| ChartPNG Draw Chart.js charts as PNG images: a shareable image URL or the PNG itself. | |
| Clarity UK property data UK buy-to-let figures, location search and deal checks, paid per call in USDC over x402. | |
| tools.clean/mcp Read-only developer, date, finance, and text utilities. Authless remote MCP server by Clean.tools. | |
| Clearout Email verification, email finder and name validation from Clearout. | |
| com.clihub/clihub Convert any CLI binary to an MCP server via `ch mcp wrap`; discover CLI tools & recipes. | |
| io.github.CodeCraftersLLC/local-voice-mcp Give your MCP clients the ability to speak by running local voice models using Chatterbox TTS | |
| CodexGuild What changed in your stack since the model's cutoff, error fixes, and security-scanned skills/MCPs | |
| CollHub Documents, projects, comments, workflows and data sources of your CollHub instance, as tools. | |
| io.github.ConnorBritain/mssql-reader Read-only MCP server for Microsoft SQL Server — schema discovery, profiling, safe querying | |
| io.github.ConnorBritain/mssql MCP server for Microsoft SQL Server — schema discovery, profiling, safe writes, and DDL | |
| io.github.ConnorBritain/mssql-writer MCP server for Microsoft SQL Server — read and data write operations, no DDL | |
| io.consentease/mcp-server Manage ConsentEase consent banners and cookie inventories from your coding agent. | |
| Contrie Extract structured data from a web page, read it as markdown, verify values against the source. | |
| Conttrole Brazilian e-invoicing (NF-e, NFC-e, NFS-e): issue, cancel and query fiscal documents, plus AP/AR. | |
| CrawlConsole Backlink Analysis MCP for AI Agents: authority, referring domains, and competitor link gaps. | |
| Credda Trust Check a counterparty's verifiable Credda trust record; verify or present signed credentials. | |
| io.github.calademos/creditsync Track credit card benefits, welcome offers, loyalty points, and money deadlines. No bank login. | |
| Crela Search the Crela software marketplace and publish, update and review your software from your agent. |
45,951–46,000 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.