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.marcelo-ochoa/mysql marcelo-ochoa/servers An MCP server for MySQL databases. | |
| io.github.marcelo-ochoa/oracle marcelo-ochoa/servers MCP server for interacting with Oracle databases | |
| io.github.marcelo-ochoa/postgres marcelo-ochoa/servers MCP server for interacting with PostgreSQL databases | |
| io.github.marcelo-ochoa/qnap marcelo-ochoa/servers MCP server for QNAP NAS API | |
| ai.marchward/mcp-server marchward/marchward Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log. | |
| io.github.marcimastro98/xenon-widgets marcimastro98/xenon Build widgets for the Xenon dashboard: SDK reference, install, runtime errors, tile screenshots. | |
| CurlShip marcindudekdev/curlship Read and submit the CurlShip directory. Paid actions return checkout_url. | |
| KG-SSOT marciocar/kg-ssot Company-brain knowledge graphs: confirmed claims cite sources, and decisions get revisited | |
| Contazz AutoPilot marciokorphub/contazz-autopilot-mcp Brazilian AI-powered accounting & tax automation: NFS-e invoicing, CBS/IBS tax reform, compliance. | |
| Sessy — Amazon SES observability marckohlbrugge/sessy Read-only Amazon SES observability: search events, inspect bounces, pull delivery stats. | |
| Kalvi — NFS-e e IBS/CBS marcogorrasi-hub/classifica-nfse Confere a NFS-e brasileira para IBS/CBS antes de transmitir. Sem cadastro e sem chave. | |
| Semantic Geometry marcoret74/sg Deterministic verifier: LLM proposes, graph verifies. Sub-ms, offline, 0 tokens. | |
| BioMASS ODE Model Builder marcorusc/mcp-biomodelling-servers Construct, inspect, visualize, and simulate evidence-backed ODE models with BioMASS | |
| MaBoSS Boolean Network Simulator marcorusc/mcp-biomodelling-servers MCP server for Boolean network simulation and attractor analysis using MaBoSS | |
| NeKo Biological Network Builder marcorusc/mcp-biomodelling-servers MCP server for biological network construction and analysis using pathway databases | |
| PhysiCell Configuration Builder marcorusc/mcp-biomodelling-servers MCP server for building, inspecting, and exporting PhysiCell and PhysiBoSS configuration files | |
| Facade UI marcoschulz7/facade-ui Animated shadcn components and page blocks for local business, real estate and agency websites. | |
| BridgeAI marcoshenriquemaia/bridgeai-plugin Hospedagem no Brasil que o agente opera: cria banco, publica, lê log e diz o custo. | |
| Rhein-Ruhr Fahrplan MCP marcproe/rhein-ruhr-fahrplan-mcp Public transit data for the Rhein-Ruhr region: live departures, trips, disruptions, GTFS schedules. | |
| so.anteroom/anteroom marcusharjani/preflight Frontier-AI vendor commitments, safety framework history, corpus, and partnership patterns. | |
| Backfill Fetch maren-ygolonhcet/backfill Pay-per-fetch web extraction for agents: POST a URL, get clean markdown. x402 USDC on Base. | |
| io.github.Marginpad/sdk marginpad/sdk Free crypto-futures paper trading and live market data for AI agents. 29 tools; no key for data. | |
| ARC-1 marianfoo/arc-1 MCP server for SAP ABAP systems | |
| AgenticWebScore marifeting/agenticwebscore-mcp Scan a public website for AI agent readiness: 60 checks, a score, and the evidence for each. | |
| locli mariohahn/locli Find, add, push and pull an app's user-facing texts in locli (iOS, Android, web, backend). | |
| polite-crawler mark1russell7/crawler A polite crawler for agents: obeys robots.txt, fetches each page once, finds and verifies quotes. | |
| Markaestro markaestro/markaestro-agents Schedule, publish, and review social posts and analytics for a Markaestro brand. | |
| com.biodnd/agent-fin markchiang/go-agents Agent Fin: finance MCP server with market data tools | |
| com.biodnd/agent-ip markchiang/go-agents Agent IP: MCP server with patents search tools | |
| com.biodnd/agent-press markchiang/go-agents Agent Press: news MCP server streaming company headlines | |
| Chenfeng AI Public Information MCP markcraddockxmzqntb-lgtm/chenfeng-ai-website-public Read-only public services, cases, resources and FAQ from Chenfeng AI. | |
| Delphi Code markdorof/delphi-code Let coding agents browse code across all your local, GitHub and Bitbucket repos, offline | |
| Markdown Pipeline markdown-pipeline/markdown-pipeline Your team's Jira as clean Markdown files, kept current for your AI agent. Local and read-only. | |
| MarketCheck AI Desk marketcheckhub/marketcheck-ai-reports Vehicle valuations and market reports in Claude or ChatGPT. Pay per report, no subscription. | |
| MarketCheck API marketcheckhub/marketcheck-mcp-client MarketCheck automotive data: search US/UK listings, predict prices, decode VINs, market history. | |
| Market Eyes Live - stock ratings and mortgage-rate context marketeyeslive/market-eyes-live-mcp Free stock-rating MCP: tier, 0-100 score, 8 factors, 11,000+ US tickers, plus mortgage rates. | |
| io.github.markhahnel/postcodeproperty markhahnel/postcodeproperty UK area & property intelligence for AI agents: reports, EPC, comparables, with source provenance. | |
| ID Protocol markoblogo/id Portable human-AI context protocol reference tooling. | |
| Deckodex markomatic507/deckodex-mcp Gundam Card Game cards, prices, tournament meta, and your Deckodex collection and decks. | |
| CheckMyPayRate markopints34-tech/checkmypayrate Salary benchmarks for 20 countries and 13 sectors from OECD and Eurostat data. | |
| io.github.markoskarllos-netizen/aetherintel-marketplace markoskarllos-netizen/aetherintel-marketplace Free OFAC sanctions/text/health-check tools; paid x402 agent+wallet audit tools. | |
| io.github.MarkovianProtocol/provenance markovianprotocol/markovian-protocol Stamp or notarize data into a public witnessed transparency log. Proves timing, not truth. | |
| io.github.markswendsen-code/panera markswendsen-code/mcp-panera MCP server for Panera Bread - browse menu, customize orders, place pickup | |
| io.github.markswendsen-code/tacobell markswendsen-code/mcp-tacobell MCP server for Taco Bell - browse menu, customize orders, place pickup | |
| io.github.markswendsen-code/taskrabbit markswendsen-code/mcp-taskrabbit MCP server for TaskRabbit - let AI agents book home services and taskers | |
| CVErdict markusweldon/cverdict Read-only CVE triage: verdicts from CISA KEV, EPSS and exploit feeds, each reason linked. | |
| io.github.marlenezw/publish-mcp-server marlenezw/publish-mcp-server An MCP server that helps developers publish their MCP servers to the registry | |
| Marmot Data Catalog marmotdata/marmot Open-source data catalog. Search assets, explore lineage, and find ownership. | |
| io.github.marras0914/agent-toolbelt-mcp marras0914/agent-toolbelt 19 focused API tools for AI agents: contract review, prompt optimizer, context packing, and more. | |
| MarsNMe marsmanleo/marsnme Agent-agnostic memory backend that preserves continuity between humans and AI over time. |
26,251–26,300 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.