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.GuardBee/a2a-auditor guardbee/guardbee-mcp Scans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure | |
| io.github.GuardBee/agent-graph-auditor guardbee/guardbee-mcp Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs | |
| io.github.GuardBee/ai-code-scanner guardbee/guardbee-mcp Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection | |
| io.github.GuardBee/audit-gap-auditor guardbee/guardbee-mcp OWASP MCP08 audit/telemetry gaps: missing tool-call logs, raw args in logs, disabled audit | |
| io.github.GuardBee/compliance-checker guardbee/guardbee-mcp KVKK/GDPR/CCPA compliance checks for codebases | |
| io.github.GuardBee/context-oversharing-auditor guardbee/guardbee-mcp OWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks | |
| io.github.GuardBee/db-gateway guardbee/guardbee-mcp KVKK/GDPR-compliant LLM-to-database gateway: PII masking, RBAC, rate limiting, audit log | |
| io.github.GuardBee/dependency-auditor guardbee/guardbee-mcp CVE scanning for npm/pip/cargo dependencies via OSV | |
| io.github.GuardBee/dns-intelligence guardbee/guardbee-mcp DNS record enumeration, misconfiguration and dangling-subdomain detection | |
| io.github.GuardBee/document-scanner guardbee/guardbee-mcp Finds PII and credentials in PDFs, screenshots and scanned documents | |
| io.github.GuardBee/elicitation-auditor guardbee/guardbee-mcp MCP elicitation anti-patterns: secrets in forms, third-party authorize URLs, credentials in URLs | |
| io.github.GuardBee/llm-redteam guardbee/guardbee-mcp Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints | |
| io.github.GuardBee/mcp-config-auditor guardbee/guardbee-mcp Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats | |
| io.github.GuardBee/mcp-server-auditor guardbee/guardbee-mcp Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets | |
| io.github.GuardBee/memory-poisoning-scanner guardbee/guardbee-mcp Scans agent code for untrusted input poisoning persistent cross-session memory | |
| io.github.GuardBee/model-scanner guardbee/guardbee-mcp Scans ML model files (PyTorch, joblib, NumPy, GGUF, TensorFlow…) and HF repos for supply-chain risks | |
| io.github.GuardBee/oauth-auditor guardbee/guardbee-mcp Scans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience | |
| io.github.GuardBee/owasp-scan guardbee/guardbee-mcp Unified OWASP MCP Top 10 scan — path or live tools/list, A–F grade, SARIF | |
| io.github.GuardBee/prompt-injection-scanner guardbee/guardbee-mcp Scans RAG content/scraped pages for indirect prompt injection | |
| io.github.GuardBee/prompt-leak-scanner guardbee/guardbee-mcp Catches leaked credentials and PII in outbound LLM prompts | |
| io.github.GuardBee/reverse-shield guardbee/guardbee-mcp Audits shipped apps for how easily they can be reverse engineered | |
| io.github.GuardBee/rug-pull-detector guardbee/guardbee-mcp Baselines an MCP server's tools and detects tool-definition changes after approval | |
| io.github.GuardBee/secret-scanner guardbee/guardbee-mcp Scans files for leaked secrets and API keys | |
| io.github.GuardBee/security-proxy guardbee/guardbee-mcp MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log | |
| io.github.GuardBee/security-suite guardbee/guardbee-mcp Every GuardBee MCP security tool in one server: OWASP MCP Top 10, secrets, supply chain, TLS/DNS | |
| io.github.GuardBee/slopsquat-scanner guardbee/guardbee-mcp Checks declared npm/PyPI dependencies against real registries to catch slopsquatting | |
| io.github.GuardBee/ssl-inspector guardbee/guardbee-mcp TLS certificate/cipher/protocol inspection | |
| io.github.GuardBee/threat-rules guardbee/guardbee-mcp GuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection | |
| io.github.GuardBee/tool-poisoning-scanner guardbee/guardbee-mcp Scans MCP tool definitions for hidden instructions and confused-deputy sinks | |
| io.github.GuardBee/toxic-flow-auditor guardbee/guardbee-mcp Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress | |
| io.github.GuardBee/unbounded-consumption-auditor guardbee/guardbee-mcp Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6) | |
| io.github.GuardBee/vector-store-scanner guardbee/guardbee-mcp Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data | |
| io.github.GuardBee/vulnerability-scanner guardbee/guardbee-mcp Triggers GuardBee scans, queries findings, AI-assisted remediation guidance | |
| Guava Wallet Intelligence guava-research/guavawit Crypto security, honeypot detection, wallet analysis, and token risk scoring across 31 blockchains. | |
| io.github.gudlab/gud-api-mcp gudlab/gud-api AI agents create, run, and save API requests as Gud API collections in your project. | |
| Relay gudsol/relay-mcp Shared, private memory for ChatGPT, Claude, Cursor and 20+ AI tools. Plan in one, build in another. | |
| Lex guffawaffle/lex Episodic memory and architectural policy for AI agents. Frames, Atlas, and Policy. | |
| Guggach Apartments guggach/website3 Availability and prices for Guggach Apartments Zurich (read-only). | |
| Stallhunt guillem/stallhunt Evidence-backed Linux performance triage over MCP | |
| Designobo guillemus/designobo-plugin Your AI agent designs editable, clickable UI prototypes on a live canvas. | |
| Gulf AI Deals gulfaideals/gulf-ai-hub-mcp Read-only, no-auth: sourced GCC AI deals, AI agent use cases in Saudi/UAE, and Arabic AI tools. | |
| YouTube Transcripts, Search & Summaries gunnargray-dev/youtube-transcripts-mcp YouTube transcripts, video search, chapters and extractive summaries. No YouTube API key, no LLM. | |
| Shipshots gurkang/shipshots Create App Store and Play Store screenshots with AI via MCP | |
| Guru Remote MCP Server guruhq/remote-mcp-server Guru MCP Server - Connect AI tools to your Guru knowledge base | |
| Gurusup gurusup/gurusup-brain-plugin Your company brain: search decisions, people, customers and projects across connected sources. | |
| GuruWalk Affiliates guruwalk/affiliates-mcp GuruWalk affiliate program for AI agents. Free walking tours in 100+ countries. Earn per booking. | |
| io.github.gustavoatar/instafan gustavoatar/instafan-mcp Plan trips with friends: mood search, live briefs, top spots with photos, day-by-day itineraries. | |
| GUTHMANN® Berlin Real Estate guthmannestate/mcp Berlin real estate for AI agents: granular market data and property search, free, by GUTHMANN®. | |
| front-proxy gutomezencio/front-proxy Map local domains (and HTTPS) to apps on local ports, OS-wide, via /etc/hosts and a reverse proxy. | |
| Mellow Tapir Radio Spectrum Guide guycole/mellow-tapir Explore likely radio services, channels, and emissions from 108 MHz to 1 GHz. |
23,601–23,650 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.