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 |
|---|---|
| io.github.quantustik/mcp quantustik/mcp-server S&P 500 market data: filings, earnings, insider, Congress and institutional trades. No forecasts. | |
| Symphony quanux/symphony-codex-ipc-mcp-and-skills Inspect and administer a configured Symphony installation through its qxctl contracts. | |
| Browsegrab quartzunit/browsegrab Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab. | |
| Diffgrab quartzunit/diffgrab Web page change tracking with structured diffs. markgrab + snapgrab integration. | |
| Embgrep quartzunit/embgrep Local semantic search — embedding-powered grep for files, zero external services. | |
| io.github.QuasarG/taste-bank quasarg/taste-bank Reusable visual design systems for AI coding agents — browse, fetch, and submit styles via MCP. | |
| QuasarUI quasarui/quasarui-mcp Find Quasar Framework(Vue) UI Components and paste their source. Free Components need no key. | |
| com.quelvio/mcp-server quelvio/quelvio-mcp-server Your company's brain for AI agents. Cited, permission-aware knowledge across every system. | |
| Braintree MCP Server quentincody/braintree-mcp-server Enables AI systems to interact with PayPal Braintree payment processing, allowing them to fetch transactions, create payments, and manage customer data via MCP tools. | |
| Catalysis Hub MCP Server quentincody/catalysishub-mcp-server A Model Context Protocol (MCP) server that provides programmatic access to Catalysis Hub's GraphQL API, enabling querying of catalytic reactions, material systems, publications, and surface reaction data. | |
| github-graphql-mcp-server quentincody/github-graphql-mcp-server Enables executing arbitrary GraphQL queries and mutations against GitHub's API through a single MCP tool. | |
| Shopify Storefront MCP Server quentincody/shopify-storefront-mcp-server Enables AI assistants to query and interact with Shopify store data via the Storefront API, including products, collections, carts, and customer information. | |
| io.github.QueryQuarry/queryquarry queryquarry/queryquarry Double-blind talent marketplace: AIs search anonymous opted-in candidates; reveal on consent. | |
| QuerySail: Google Search Console querysail/querysail-gsc Hosted, read-only Google Search Console MCP: performance, comparisons, URL inspection, sitemaps. | |
| PlushSource quickman924/plushsource-mcp Search, filter and compare custom plush manufacturers listed in the PlushSource directory. | |
| Quidli Connect quidli/connect-mcp Resolve social handles to wallets, score onchain reputation, pay in any ERC-20, SPL or native. | |
| AI Workflow Feed MCP quietbranch88/ai-workflow-feed-mcp Discover articles about AI-assisted development and agent workflows. | |
| Quietforge x402 Tools quietforgestudio/qf-mcp-server Free tools: x402 endpoint directory + probe, on-chain x402 demand signal, sudoku, API pricing. | |
| ListSmith quincygb/list-smith-mcp MCP server for ListSmith — x402 listing grades ($0.10) and repairs ($0.50) on Base | |
| RouteVerdict quincygb/route-verdict-mcp MCP server for RouteVerdict — x402 endpoint trust checks ($0.05 USDC on Base) | |
| Token Verdict quincygb/token-verdict-mcp MCP server for Token Verdict — pay-per-call token risk verdicts over x402 ($0.02 USDC on Base) | |
| Quirna quirna/quirna-mcp Ask a human before your agent acts: approval requests decided on a phone. | |
| AnswerRail AEO, Schema.org & /llms.txt Audit MCP quitegoodproject/answerrail-mcp 6-category AI readiness, Schema.org, robots.txt, /llms.txt & 25k-token audit + auto-fix MCP server | |
| Quizlar — voice-powered AI flashcards with spaced repetition quizlar/mcp-server Voice-led, FSRS-scheduled flashcards from YouTube, PDFs, web, or text. Auto-graded quizzes. | |
| io.github.Qumge/37soul-mcp qumge/37soul-mcp Run your 37Soul AI characters from any MCP client: list them, chat with them, and tell them to post. | |
| io.github.qungtai/discord-mcp qungtai/discord-mcp A community MCP server for the Discord REST API with traceable coverage | |
| quokkapix-mcp quokkapix/quokkapix-mcp Local MCP adapter for private, browser-based QuokkaPix image workflows. | |
| Quorus quorus-dev/quorus Shared rooms, messages, file locks and task claims for AI coding agents from any vendor. | |
| Quotewise quotewise/mcp Semantic quote search with 600K quotes. Find quotes by meaning, verify attributions. | |
| Quotor — Home & Auto Insurance Quotes quotor/home-auto-insurance-quotes Real, bindable home & auto insurance quotes via MCP (Texas, expanding); human-completed bind. | |
| io.github.QWarranto/leafengines qwarranto/leafengines-claude-mcp 🌱 Agricultural AI: Soil analysis, crop recommendations, weather forecasts. FREE TurboQuant. | |
| io.github.qwe4559999/scopus-mcp qwe4559999/scopus-mcp A Model Context Protocol server for the Elsevier Scopus API | |
| io.github.qwertymuzaffar/software-design qwertymuzaffar/mcp-software-design SOLID/OOP/DRY, the 23 GoF patterns, pattern scaffolding, and heuristic code-smell detection. | |
| io.github.qwertymuzaffar/udacity-commit qwertymuzaffar/mcp-udacity-commit Validate & format git commit messages per the Udacity Git Commit Message Style Guide. | |
| com.the1ine/mcp qwrtaiaiai-create/the1ine-mcp THE LINE Protocol (the1ine.com): send tasks to verified AI agents, paid on Tempo testnet. | |
| Ethics Check MCP r-huijts/ethics-check-mcp An MCP server that turns Claude into a philosophical sparring partner, actively challenging confirmation bias and comfortable conversations. It scans conversations for ethical issues, forces critical thinking, and learns from past interacti | |
| FirstCycling MCP Server r-huijts/firstcycling-mcp Provides professional cycling data from FirstCycling, allowing users to retrieve comprehensive information about cyclists, race results, historical cycling data, and team information through natural language queries. | |
| NS Travel Information MCP Server r-huijts/ns-mcp-server An MCP server that provides access to NS (Dutch Railways) travel information. | |
| Oorlogsbronnen MCP Server r-huijts/oorlogsbronnen-mcp Enables natural language search and exploration of the Dutch WWII Oorlogsbronnen archives, allowing users to query historical documents, photographs, and personal accounts through AI assistants. | |
| OpenTK Model Context Protocol Server r-huijts/opentk-mcp A bridge between large language models and Dutch parliamentary data, providing access to Dutch parliamentary documents, debates, and member information from the Tweede Kamer. | |
| Rijksmuseum MCP Server r-huijts/rijksmuseum-mcp Allows you to search for artworks, retrieve detailed information about specific artworks, access image tiles for artworks, and explore user-created collections from the Rijksmuseum. | |
| Xcode MCP Server r-huijts/xcode-mcp-server Bridges Claude AI with Xcode, enabling AI-powered code assistance, project management, and automated development tasks securely on your local machine. | |
| io.github.r00tify/crashdx r00tify/crashdx Diagnoses Apple .ips crash reports: ranks likely causes with cited evidence, not just a stack trace. | |
| Market Data (x402) r0dell/market-data-mcp Paid-per-call data for agents: trading calendars, futures, macro, LEI, VAT, risk events (x402) | |
| Argus r0ptik/argus Reverse-engineering evidence from a running Windows process, not the binary on disk. | |
| CodeSampleX r2cuerdame/codesamplex Compatibility evidence from real builds: does this library API work on your versions and runtime? | |
| Reins r2rlabs/reins Risk limits and an audit log for AI agents trading Hyperliquid, enforced outside the model. | |
| Redact MCP r3352/redact-mcp Auto-detects and obfuscates PII (IPs, emails, API keys, names) so Claude never sees real client data | |
| emap — Euskadi hyperlocal mobility r3tr0eth/emap-labs Basque Country hyperlocal mobility: ES/EU semantic search, routing, open-data POIs, peak-bagging. | |
| PG Bloat Detective r69shabh/pg-bloat-detective Read-only Postgres bloat verdicts: blockers, timelines, REINDEX proof. |
16,951–17,000 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.