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 |
|---|---|
| io.github.markswendsen-code/grubhub markswendsen-code/mcp-grubhub MCP server for GrubHub - let AI agents order food and manage restaurant delivery autonomously | |
| io.github.markswendsen-code/instacart markswendsen-code/mcp-instacart MCP server for Instacart - let AI agents manage grocery shopping and place orders autonomously | |
| io.github.markswendsen-code/kroger markswendsen-code/mcp-kroger MCP server for Kroger - search products, manage cart, place grocery orders | |
| io.github.markswendsen-code/opentable markswendsen-code/mcp-opentable MCP server for OpenTable - let AI agents book restaurant reservations and manage dining autonomously | |
| io.github.markswendsen-code/southwest markswendsen-code/mcp-southwest MCP server for Southwest Airlines - search flights, manage bookings | |
| io.github.markswendsen-code/spotify markswendsen-code/mcp-spotify MCP server for Spotify - let AI agents control playback, search music, and manage playlists | |
| io.github.markswendsen-code/target markswendsen-code/mcp-target MCP server for Target - search products, manage cart, track orders | |
| io.github.markswendsen-code/ubereats markswendsen-code/mcp-ubereats MCP server for Uber Eats - let AI agents order food delivery | |
| io.github.markswendsen-code/venmo markswendsen-code/mcp-venmo MCP server for Venmo - check balance, send/request money, view history | |
| io.github.markswendsen-code/walmart markswendsen-code/mcp-walmart MCP server for Walmart - search products, manage cart, track orders | |
| io.github.markswendsen-code/yelp markswendsen-code/mcp-yelp MCP server for Yelp - search businesses, read reviews, make reservations | |
| Carve markup-carve/carve-mcp Parse, lint, format, render, and migrate Carve documents through MCP. | |
| mcp-gsuite markuspfundstein/mcp-gsuite MCP server to interact with Google produts. | |
| MCP server for Obsidian markuspfundstein/mcp-obsidian MCP server to interact with Obsidian via the Local REST API community plugin. | |
| IBM Code Engine MCP Server markusvankempen/code-engine-mcp-server Deploy to IBM Code Engine from Cursor, Copilot, Claude & Cline. Build, push, deploy via MCP. | |
| Literature Clock markusvankempen/literature-clock-mcp A line for the current minute, from literature, copyright-free books, or an original voice. | |
| IBM Maximo markusvankempen/maximo-mcp-ai-integration-options Connect AI assistants to IBM Maximo for API discovery, OSLC querying, and Carbon UI generation. | |
| io.github.markusvankempen/mcp-ticket-demo markusvankempen/mcp-ticket-demo MCP server demo — tickets, schema discovery, auth, and PII gating. stdio + HTTP. | |
| Quantum OpenQASM MCP markusvankempen/quantum-openqasm-assistant IBM Quantum OpenQASM 2.0 MCP — list backends, submit QASM, poll jobs, get histograms. | |
| Slack ↔ WxO MCP Gateway markusvankempen/slack-wxo-mcp-gateway Lifts WxO Slack limits: every-message wake-up, multi-channel MCP. https://markusvankempen.github.io/ | |
| WxO Agent MCP markusvankempen/wxo-agent-mcp Invoke a Watson Orchestrate agent via MCP. Configure with WO_AGENT_ID. | |
| Watson Orchestrate markusvankempen/wxo-builder-mcp-server Manage IBM Watson Orchestrate tools, agents, connections from Cursor, Copilot, Claude. | |
| Zendesk MCP markusvankempen/zendesk-mcp Zendesk MCP: 14 tools for AI agents — create, search, assign, comment, and close support tickets. | |
| OpenJEV markylaredo/openjev-mcp Typed AI judgments for agents: choice, score, and yes/no probabilities instead of prose. | |
| KH Merch Graph marleyhereicome-cpu/kh-merch-graph Identifies Kingdom Hearts merch from Japanese listing titles: SKU, condition terms, bootleg flags. | |
| Atelier marmikshah/atelier Offline, headless pixel-art editor: draw, animate, inspect, and export sprites and fonts. | |
| Sendermap marmot7775/sendermap Maps every service that sends email as a domain, with the public record behind each one. | |
| io.github.maroondlabs/sourcebook maroondlabs/sourcebook Live codebase intelligence for AI agents: conventions, blast radius, import graphs, git insights. | |
| Video Dept. AI maroosh1/video-dept-ai Plan a video and script with VIDEO DEPT. in Fort Lauderdale, send a brief, book a call with Nikita. | |
| agent-toolbelt marras0914/agent-toolbelt Agent Toolbelt is an MCP server exposing 11 focused API tools for LLM agents — schema generation, text extraction, token counting, CSV conversion, Markdown conversion, URL metadata, regex builder, cron expressions, address normalization, co | |
| Cordon for MCP marras0914/cordon Cordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals. | |
| Marsell marsell-official/mcp Manage content, marketing and sales in Marsell with your own AI. Read work and act with permission. | |
| Juno Open Health Tools marshallbear1/juno-open-health-tools Consent-gated tools that turn user health notes into non-diagnostic appointment-prep materials. | |
| Aigist marshallino16/aigist-mcp Publish & manage shareable HTML/Markdown pages from your LLM, with access control. | |
| Refactoring MCP Server marshally/mcp-refactoring MCP server exposing Martin Fowler's refactoring catalog to LLMs with 71+ refactorings | |
| cloud.agentdomain/agentdomain-mcp marsheer/agentdomain-mcp Register and manage internet domains for AI agents via AgentDomain | |
| GumroadDNA marstudio360/gumroad-dna-mcp The Gumroad API v2 from chat: products, files, sales, refunds, licenses, plus niche scans. | |
| VibeDNA Journal marstudio360/vibedna-journal-mcp One journal file per project that your AI reads at session start and updates as it works. | |
| VibeDNA Vault marstudio360/vibedna-vault-mcp Encrypted local vault for API keys. Your AI fetches keys on demand and scans code for leaks. | |
| VibeGen marstudio360/vibegen-mcp Your AI drives a generative art studio: moves knobs, renders PNGs, MP4s and song videos. | |
| Government Contracts martc03/gov-mcp-servers SAM.gov contracts and USAspending awards. 4 procurement tools. | |
| ch.martinelli/jooq-mcp martinellich/jooq-mcp An MCP server that provides access to the jOOQ documentation | |
| ResearchTwin martinfrasch/researchtwin Federated research discovery with S-Index metrics across a network of digital twins. | |
| Diff Anything martingryner/diff-anything-mcp Compare local files, folders and API schemas through the installed Diff Anything CLI. | |
| cz-agents-mcp martinhavel/cz-agents-mcp MCP servers for Czech government & business data: ARES (Business Register) + ČNB (FX rates). Native AI access to company lookups, VAT status, bank accounts, currency conversion. | |
| Martini martini-film/mcp Manage AI filmmaking projects, scenes, assets, and generations in Martini. | |
| io.github.martinPisacreta/textokit-mcp martinpisacreta/textokit-mcp 17 pay-per-call x402 tools on Base: web reader, FX/crypto rates, Argentine data. Remote or npx. | |
| Dida365 MCP Server martinqi826/dida-mcp Enables AI assistants to manage Dida365 tasks and projects, including creating, updating, and searching for items through natural language. It supports advanced queries for overdue or high-priority tasks across various MCP-compatible client | |
| NTNU Courses (unofficial) martinsa04/ntnu-mcp Unofficial NTNU course data: search, timetables, grades, course info, and exam logistics. | |
| MachineWitness martinschenk/machinewitness-mcp EU archive of the machine-readable web: check a domain, order a time-stamped record or extract. |
11,551–11,600 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.