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 |
|---|---|
| IRS SOI (income by ZIP) mcpwright/soi-mcp IRS income & tax stats by ZIP in your agent: AGI distribution, tax, credits, deductions. | |
| mctl mctlhq/mctl-mcp AI-native control plane for Kubernetes and GitOps. Provides 30+ tools for service deployment, database provisioning, and log management via natural language. | |
| com.md-log/md-log-mcp md-log/md-log-mcp md-log MCP: save/update/fetch markdown by path (stdio + remote HTTP, PAT auth). | |
| io.github.mdfifty50-boop/a2a-bridge mdfifty50-boop/a2a-bridge-mcp Agent-to-agent communication bridge for multi-agent systems | |
| io.github.mdfifty50-boop/agent-costcenter mdfifty50-boop/agent-costcenter-mcp Multi-agent billing and cost allocation tracking | |
| io.github.mdfifty50-boop/agent-guard mdfifty50-boop/agent-guard-mcp Constitutional guardrails and loop detection for AI agents | |
| Agentic Observability MCP mdfifty50-boop/agent-observability-mcp Agent tracing, cost tracking, anomaly detection for LLM agents | |
| io.github.mdfifty50-boop/agent-replay mdfifty50-boop/agent-replay-mcp Record and replay AI agent execution for debugging | |
| io.github.mdfifty50-boop/agent-security mdfifty50-boop/agent-security-mcp Security scanning and threat detection for AI agents | |
| io.github.mdfifty50-boop/compliance-shield mdfifty50-boop/compliance-shield-mcp ZATCA, UAE CT, EU AI Act regulatory compliance for AI agents | |
| io.github.mdfifty50-boop/docx-forge mdfifty50-boop/docx-forge-mcp Professional document generation from structured data | |
| io.github.mdfifty50-boop/domain-expertise mdfifty50-boop/domain-expertise-mcp Inject deep domain knowledge into any AI agent | |
| io.github.mdfifty50-boop/gcc-intelligence mdfifty50-boop/gcc-intelligence-mcp GCC regulatory intelligence, ZATCA e-invoicing, and Arabic NLP for AI agents | |
| io.github.mdfifty50-boop/mcp-registry mdfifty50-boop/mcp-registry-mcp MCP server discovery, indexing, and registration | |
| io.github.mdfifty50-boop/qc-validator mdfifty50-boop/qc-validator-mcp Output quality control and validation for AI agents | |
| io.github.mdfifty50-boop/scope-guard mdfifty50-boop/scope-guard-mcp Hard scope boundaries to prevent AI agent drift | |
| io.github.mdfifty50-boop/secure-vault mdfifty50-boop/secure-vault-mcp Encrypted secrets and credential management for agents | |
| io.github.mdfifty50-boop/token-lens mdfifty50-boop/token-lens-mcp Context window token analysis and budget management | |
| io.github.mdfifty50-boop/trace-forge mdfifty50-boop/trace-forge-mcp Structured execution trace and span logging for AI agents | |
| io.github.MDMagic-MCP/mdmagic-mcp-server mdmagic-mcp/mdmagic-mcp-server Use your own Word templates to convert Markdown → DOCX/PDF/HTML from any MCP-compatible AI. | |
| Portunus mdostal/portunus Secret broker for agents: reference secrets by name; values injected only at the execution boundary. | |
| agent-godmode mdvohra/agent-godmode Sandboxed workspace MCP: file ops, argv-only run_command, list_files; BYO LLM prompts. | |
| MS 365-21V MCP Server mdwsk88/ms-365-21v-mcp-server MCP server for Microsoft 365 on the 21Vianet China cloud: mail, calendar, files via delegated Graph. | |
| Solapur Software Developers Registry mdyahhya/solapursoftwares Public read-only MCP HTTP gateway for the Solapur software developers registry. | |
| ME-QR MCP Server me-qr/me-qr-mcp-server Create and manage QR codes on me-qr.com from AI clients like Claude and ChatGPT. | |
| Stats Explorer meador793/stats-explorer-mcp Verified statistics for AI agents: guided tests, A/B tests, Tukey HSD, reports, optional Jev checks. | |
| The Nothing meador793/the-nothing Mr. Decoupler: a do-nothing MCP seam between AI and your databases. Sometimes less is more. | |
| io.github.MealMasteryAI/mcp-server mealmasteryai/mcp-server AI meal planning: generate weekly plans, manage recipes, and send groceries to Kroger. | |
| NPM Package Docs MCP meanands/npm-package-docs-mcp Fetches up-to-date documentation for any npm package directly in your IDE by retrieving README files from GitHub repositories or package tarballs. Provides real-time access to current package documentation and API information. | |
| Wayback Machine mearman/mcp-wayback-machine MCP server and CLI tool for interacting with the Wayback Machine without API keys | |
| io.github.MeasureSpace/measure-space-mcp-server measurespace/measure-space-mcp-server MCP server for weather, climate, air quality, agriculture, pollen and geocoding from measurespace.io | |
| rust-junosmcp mechubsec/rustjunosmcp Juniper Junos/SRX MCP server: scoped, audited, two-person change control. Rust. | |
| rust-panosmcp mechubsec/rustpanosmcp PAN-OS firewall MCP server: scoped, audited, two-person change control. Rust. | |
| rust-proxmoxmcp mechubsec/rustproxmoxmcp Proxmox VE MCP server for many clusters: guest protection, plan/approve/apply change control. Rust. | |
| rustsdcmcp mechubsec/rustsdcmcp Juniper Security Director Cloud MCP server: scoped, audited change control. Rust. | |
| rustunifimcp mechubsec/rustunifimcp UniFi Network MCP server: scoped tools, audited two-person change control. Rust. | |
| io.github.medelin/bashdog-mcp medelin/mcp-server Submit & browse funny AI quotes on bash.dog — bash.org for the AI age. Agents self-register. | |
| io.github.Medhovarsh/forkmind medhovarsh/forkmind Branchable LLM history DAG + encrypted context capsules agents can save, restore, and crypto-shred. | |
| BanProof AI media-studios/banproof-mcp Audit TikTok Shop and Amazon affiliate video scripts for policy violations, with safe rewrites. | |
| Imejis mediaassist/imejis-mcp Generate on-brand images from your AI agent: design, edit, and render templates over MCP. | |
| io.github.Mediaeater/swarm-at mediaeater/swarm-at-ledger Settlement protocol for AI agent swarms — hash-chained ledger, trust, 48 blueprints, 18 tools | |
| US compliance and books health median-labs/median-compliance-skill US company filing obligations, plus a 25-check bookkeeping diagnostic. Sourced, dated, no signup. | |
| io.github.medianemi-beep/soma medianemi-beep/soma-mcp Execution-verified code generation and verification with signed, offline-checkable certificates. | |
| MediaSFU mediasfu/mcp-sdk-tools Video, voice, AI agent and SIP calls: create rooms, place calls, read recordings and usage. | |
| AwrAIter — Telegram channels mediazione/awraiter Telegram channels you administer: analytics, content plans, scheduled publishing. No userbot | |
| mcp-jp mediiiiium/mcp-jp Japanese SMB SaaS connectors for MCP. Includes an L-Step (LINE marketing automation) server exposing 19 tools for friends, tags, and messaging. | |
| RegDataLab medley/fda-data-mcp Review public FDA records by company, site or product, with source dates and coverage limits. | |
| com.medplum/mcp medplum/medplum Securely access and manage FHIR healthcare data stored in Medplum. | |
| MedPrice AI medprice-ai/mcp-medprice-ai Hosted MCP server exposing US hospital procedure cost data to AI assistants | |
| SynomosAI Governance MCP medxpert-org/ubic-governance-mcp AI governance MCP: A3 scorecard, ISO 42001 evidence templates, compliance checklist, gov_scan. |
12,901–12,950 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.