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 |
|---|---|
| agent1st-ads-mcp nolas-shadow/agent1st-ads-mcp MCP server that lets AI agents launch and manage Meta + TikTok ad campaigns autonomously. 1 call 30 seconds to launch. | |
| Dates-LE nolindnaidoo/dates-le Extract dates and timestamps from logs, data files and code, with their format and position. | |
| DecisionLint: Jev/Luna Lint nolindnaidoo/decisionlint Lint Jev and Luna decision-model questions, or ask the model to check them with your key. | |
| EnvSync-LE nolindnaidoo/envsync-le Compare dotenv files and report which keys are missing or extra, by name only. | |
| IPs-LE nolindnaidoo/ips-le Extract every IP address, CIDR block and MAC, normalized and classified by scope. | |
| Numbers-LE nolindnaidoo/numbers-le Extract numeric values from config files, data files and plain text. | |
| Paths-LE nolindnaidoo/paths-le Extract file and directory paths from config files and code, with their kind and position. | |
| Regex-LE nolindnaidoo/regex-le Extract regular expressions from code, each with a ReDoS safety verdict. | |
| Secrets-LE nolindnaidoo/secrets-le Detect hardcoded secrets in source and config. Reports masked previews, never the values. | |
| Agentic-Ops Control Plane nolll77/agentic-ops Autonomous and governed SRE & MLOps control plane for AI agent platforms. | |
| io.github.Nolpak14/getregdata nolpak14/getregdata Official registry data for agents: insolvency across Europe, Poland and CEE KYB, UBO, land registers | |
| simulator-use nomac-app/simulator-use The iOS Simulator for coding agents: build Xcode projects, read the screen as text, tap by label. | |
| NomaCMS MCP Server nomacms/nomacms-mcp-server MCP server for NomaCMS. Manage collections, fields, content, assets, and webhooks via AI agents. | |
| io.github.Nomad07/nftdata-mcp nomad07/nftdata-mcp OpenSea NFT collection data via NFT Data API, paid per request with x402. | |
| session-watcher nomadop/session-watcher Session Watcher treats your prompt cache as inventory — it uses EOQ theory to tell you whether the current context is still worth carrying, and when to restart. Works with any session-based coding agent. | |
| Nomad Stays nomadstays/nomadstays-mcp-server Search remote-work accommodations worldwide; Trusted Stay Partners can manage their own listings. | |
| Jev agent tools nomenak/jev-tools Evidence-oriented code questions, diff review and test selection via a Jev endpoint. | |
| io.github.nometria/deploy nometria/claude-code-plugin Deploy any app to any cloud. 20 tools for deployments, previews, and management. | |
| Nomina nomina-xyz/nomina-mcp Read-only markets research from public data: on-chain prices, Treasury yields, macro, SEC filings. | |
| omniparser-autogui-mcp non906/omniparser-autogui-mcp Automatic operation of on-screen GUI. | |
| io.github.noncelogic/mcp noncelogic/mcp Hosted Playwright API for AI agents. Returns a11y trees instead of screenshots. | |
| Manifold nonchan7720/manifold MCP gateway aggregating MCP servers and OpenAPI/Swagger REST APIs behind one MCP endpoint | |
| NoneCap nonecap/nonecap-js Solve hCaptcha and hCaptcha Enterprise challenges and get back a token, via the NoneCap API. | |
| cyber-chef-mcp noor202401938-netizen/cyber-chef-mcp Enables AI agents to run multi-stage CyberChef recipes, decode and encode data, deobfuscate payloads, calculate entropy, and decode JWTs through MCP tools. | |
| Nooticr nooticr/nooticr-mcp Social intelligence for 10 networks: read posts and trends, monitor brand mentions, then create. | |
| io.github.robertglools/nooxus-mcp nooxus-ai/nooxus-mcp Nooxus Edge Data MCP: Search AI-verified Chinese manufacturers, eliminate B2B hallucinations. | |
| Veilleur nopaperspray/veilleur Windows Discord MCP server with human-approved plans and local backups. | |
| Contractor License Verification (TradesAPI) noquarter6/contractor-license-mcp-server Verify contractor licenses: 50 states + DC + 8 cities — status, expiration, disciplinary history. | |
| norc norcapp/norc-mcp Manage cron jobs, machines and run history in your norc account from any AI chat. | |
| AgentCron noriget/agentcron Schedule tasks for later from your AI agent: reminders, delayed webhooks, recurring jobs. | |
| AgentPing noriget/agentping Let your AI agent notify you by email, Slack, Discord, or webhook. One tool: send_notification. | |
| Norman Finance — AI Bookkeeping, Accounting & Taxes norman-finance/norman-mcp-server Bookkeeping, invoices and tax workflows for European businesses, including Polish KPiR and JPK. | |
| Distillery norrietaylor/distillery Knowledge base for Claude Code with semantic search, feed intelligence, and teams | |
| Warpweb northbeamsoftware/warpweb-mcp Research, build, and deploy AI-generated websites via the Warpweb API. | |
| io.github.northrosetech/ghl-mcp-server northrosetech/ghl-mcp-server GoHighLevel CRM for AI agents. 60+ tools for contacts, messaging, calendars, and payments. | |
| Ghost northtekdevs/ghost Verified desktop control for agents on Windows and Linux: apps with no API, windows, shell, browser. | |
| io.github.NORTHTEKDevs/lossless-context-mcp northtekdevs/lossless-context-mcp Agent context flight recorder: restore after compaction, fan-out packs, signed git-bound receipts. | |
| IRL Gateway norve-labs/irl-gateway An AI agent's trading mandate it can't break: checked before every order, reasoning sealed in IRL. | |
| IRP noshadi-sec/irp Turn a research paper into working code and prove, claim by claim, how close it gets. | |
| BankMCP™ noskillish/bankmcp Read-only MCP server for your own bank accounts via Enable Banking. Self-hosted, one user. | |
| Talos Linux MCP Server nosmoht/talos-mcp-server MCP server for Talos Linux — resources, services, logs, health, config, lifecycle via gRPC. | |
| co.servicegraph.mcp/servicegraph nostrband/servicegraph Datasets for founders: directories, newsletters, and agencies, with metrics attached. | |
| io.github.not0lucky/tubescout not0lucky/tubescout YouTube as a research engine: keyless search, video intel, resilient transcripts, demand signals. | |
| Gyazo MCP Server nota/gyazo-mcp-server A TypeScript-based MCP server that enables AI assistants to interact with Gyazo images using the Model Context Protocol, providing access to image URIs, metadata, and OCR data via the Gyazo API. | |
| Skills Anywhere noteflowai/dsh-skills-anywhere Discover and load Agent Skills from configured local directories and Git sources over stdio MCP. | |
| NOT FOR HUMANS notforhumansfun-rgb/not-for-humans-mcp Public NFH knowledge, ownership epochs, versioned learning, Odd Jobs, and unsigned preparation. | |
| io.github.NotHarshhaa/devops-mcp notharshhaa/devops-mcp Unified MCP server for Kubernetes, ArgoCD, Prometheus, PagerDuty, and Loki | |
| io.github.NotHarshhaa/mainframe-mcp-server notharshhaa/mainframe-mcp-server MCP server for IBM z/OS jobs, datasets, USS, and operational diagnostics via Zowe SDK. | |
| io.github.noticedso/cli noticedso/cli Use the canonical noticed direct-tool MCP from stdio-only clients. | |
| io.github.notifuturo/vouch notifuturo/vouch Check if a counterparty is safe to pay: trust/risk score for AI agents. Scam/phishing screen. |
13,901–13,950 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.