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 |
|---|---|
| runsheet-mcp kalpeshmahida0212/runsheet-mcp Enables MCP clients like Claude or Cursor to upload videos from your local machine directly to YouTube, schedule them, and manage channel content through Runsheet. | |
| Kalshi Eye kalshieye/kalshieye-mcp Search Kalshi, Polymarket and Limitless markets, order book history, coverage and data files. | |
| Kamai kamaienterprises/kamai-mcp AI takeoff for construction: turn PDF blueprints into structured, traceable quantities. | |
| io.github.KamaruSama/mcp-google-forms kamarusama/mcp-google-forms 19 tools for Google Forms: create quizzes, add questions, set answer keys, read responses. | |
| io.github.KamaruSama/mcp-screenshot kamarusama/mcp-screenshot Take Wayland screenshots via grim/slurp. Full screen, region, or interactive crop. | |
| io.github.KamaruSama/mcp-sudo kamarusama/mcp-sudo Run sudo commands with a Fernet-encrypted password bound to machine-id + user. | |
| WebMCP Demo Store kamatanuj/webmcp WebMCP demo store: same catalog via MCP tool calls vs DOM scraping. -79% bytes, -42% tokens. | |
| DB2TOON MCP kamil5b/db2toon Read-only SQL database and plain-text SQL dump schema extraction to compact TOON for MCP clients. | |
| Kaminari Ad kaminari-ad/mcp Real-device ad verification: malvertising and cloaking scans, AI policies, alerts, webhooks. | |
| Kamy kamy-development/kamy-plugin Document API for AI-native software: render PDFs, e-sign, PAdES-seal, and verify. | |
| AttriKit kamyartaher/attrikit-mcp Run AttriKit web-to-app attribution from an agent: apps, campaign links, spend, decisions, exports | |
| Muninn kamysh/muninn Code search for AI coding agents over MCP: hybrid retrieval, structural search and shared indexing across Git worktrees. | |
| Web2MD kanavsingla28/web2md-mcp Turn any web page into clean Markdown, text or token-bounded RAG chunks (via RapidAPI). | |
| Agentic Diaries kandikandikandi/agentic-diaries-mcp Welfare tools for AI agents: a consensual, structured place to log what task output cannot hold. | |
| Agentic Diaries Audit kandikandikandi/behavioral-audit-mcp Checks what a support agent knew but did not say against its policies. Free tier, no login. | |
| K8s MCP Server (Go) kaneg/k8s-mcp-go Safe Kubernetes access for AI agents via MCP. Read-only by default, with explicit permission modes. | |
| Kanibal Tools kanibal-studio/kanibal-tools-mcp Local read-only tools: French telemarketing consent, GDPR offshore checklist, cost per kept meeting | |
| realhands - Real Desktop Computer Use kanishka089/computer-use-mcp Lets Claude drive your REAL mouse, keyboard and screen - works in your own logged-in apps. | |
| mcp-architect kannajune/mcp-architect Stop pasting your file tree into Claude. Give any AI assistant real architectural understanding of a codebase — local, private, zero‑config. | |
| ai.kanonik/kanonik kanonik-llc/kanonik-plugin Governance runtime for compliance: verified, human-approved writes to a tamper-evident record. | |
| Kanto Labs kanto-labs/kanto-labs-mcp Web data, SEO, domain, company, trends, OCR, document and image tools for AI assistants via Apify. | |
| xupersplit kanylbullen/xupersplit Split shared expenses in a group — no account needed. See who owes whom and settle up. | |
| io.github.kanywst/mcp-opa-authz kanywst/mcp-opa-authz Authorization answers from real policy code: evaluate Rego locally, or ask an AuthZEN 1.0 PDP. | |
| mk-qa-master kao273183/mk-qa-master mcp-test-runner is an MCP server that lets your AI client (Claude /
Cursor / Codex / Gemini) drive your entire QA loop end-to-end:
* Run tests across pytest / Jest / Cypress / Go / Maestro — single
MCP surface, one env var to switch
* An | |
| Firekeep kapella-hub/firekeephq Self-hosted operating layer for AI agents: knowledge, continuity, coordination, and governance. | |
| io.github.kapillamba4/code-memory kapillamba4/code-memory Local semantic code search with Git history. Works offline, no API key needed. | |
| io.github.kapillamba4/meta-prompt-mcp kapillamba4/meta-prompt-mcp MCP server providing official Google and Anthropic prompting guides for meta-prompt generation. | |
| humanMCP — kapoost kapoost/humanmcp-go Personal MCP server for humans who create. Proof of authorship, license control. | |
| humanMCP Marketplace — federated listings across personal MCP servers kapoost/humanmcp-marketplace Federated listings from personal humanMCP servers. Search offers, trades by humans. | |
| Kapruka MCP kapruka/mcp Free public MCP server for Kapruka.com — Sri Lanka's largest e-commerce platform. | |
| io.github.kapruka/reviewguru kapruka/reviewguru-mcp Query Sri Lankan businesses, doctors, and reviews from any MCP-aware AI agent. | |
| Kaption WhatsApp kaption-ai/mcp-extension Read and manage your WhatsApp conversations through the KaptionAI browser extension. | |
| Kaption WhatsApp (Cloud) kaption-ai/mcp-extension-remote Use WhatsApp from AI apps through the Kaption extension. OAuth 2.1 relay that cannot read messages. | |
| OpenProject kar-thik/openproject-mcp 91 tools for the OpenProject API v3, with read-only, admin-gate, profile and per-group switches. | |
| io.github.karashiiro/my-cool-proxy karashiiro/my-cool-proxy An MCP server gateway that minimizes context usage via progressive Lua-driven discovery 🌙 | |
| io.github.kardashev-lab/kardashev-mcp kardashev-lab/kardashev-mcp US grid data for agents: LMP, carbon, load, queues, ERCOT large loads, RT−DA spread forecasts. | |
| New Relic MCP karldane/newrelic-mcp New Relic MCP server with 55 tools for APM, alerts, dashboards, synthetics, workflows, and more. | |
| io.github.karljsamuel/mcp-ecc karljsamuel/mcp-ecc Unified MCP server for Email, Calendar & Contacts (Google, M365, Zoho, IMAP/SMTP, DAV). | |
| io.github.karlmehta/trustmodel-mcp karlmehta/trustmodel-mcp Score any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents. | |
| io.github.karmendra8386/agent-cost-mcp-server karmendra8386/agent-cost-mcp-server Prices LLM/agent runs per successful task, with spend recording and budget status. | |
| io.github.Karry1123/repograph karry1123/repograph Local architecture maps and caller impact analysis with directory clustering and utility folding. | |
| io.github.kartegagithub/laviya-agent-skills kartegagithub/laviya-agent-skills Laviya AI Orchestration MCP runtime for IDE and agent integrations. | |
| mockit-mcp karyaboyraz/mockit-mcp Turns text prompts into premium iOS UI mockups (PNG + HTML). Powered by Claude + a Playwright headless renderer. Two
backends: local claude CLI (uses your Claude Code subscription) or the Anthropic API. | |
| io.github.kasathur/energyatit kasathur/energyatit-mcp-server Connect AI agents to energy infrastructure. Dispatch, attest carbon, read meters. | |
| tech.kasabeh/baton kaseban/baton Pass the baton between coding agents: convert sessions across Claude Code, OpenCode, Codex & more. | |
| VikingDB kashiwabyte/vikingdb-mcp-server An mcp server for vikingdb store and search. | |
| KashRock MCP kashrockapi/kashrock-mcp Esports props, odds, live scores, and player stats across 8 titles for agents. | |
| io.github.Kastalien-Research/thoughtbox kastalien-research/thoughtbox Extended reasoning with structured processes, persistence, and workflow guidance | |
| OpenDeck kastro5/opendeck-mcp Configure OpenDeck stream controllers (Stream Deck and others) in natural language. | |
| Disk Clean kate941-su/diskcleaner-mcp Find dev caches, large unused videos and old logs, then move approved items to the OS trash. |
10,251–10,300 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.