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.wei/hn-mcp-server Model Context Protocol server for HackerNews API access. | |
| Honeycheck Before buying a token on Arc, test whether it can be sold back. Free, or 1-5c a call over x402. | |
| to.hooka/mcp Run TikTok cold-DM outreach from your LLM: senders, campaigns and inbox via the Hooka API. | |
| io.github.wudongjie/hourledger-mcp Work hours and overtime pay tools — federal, CA, AK, CO, NV rules, every rule covered by tests. | |
| io.github.houyidb-community/houyidb-mcp MCP server exposing HouyiDB vector search, collection status, and opt-in writes. | |
| com.htmlradar/share Send a web page to specific people, control who opens it, see how it was read, and update it. | |
| Hyperliquid Funding Hyperliquid funding, open interest and carry spreads across all 11 venues. Paid per call, x402. | |
| me.pi22by7/in-memoria Persistent codebase intelligence that gives AI assistants memory across sessions | |
| Sidekick for InDesign Lets Claude (or any other AI assistant) work in your open Adobe InDesign documents. | |
| IndiaDigital Free India tools for AI agents: tax, GST, salary, savings, due dates, gold, currency, video links. | |
| Inventor Studio Shared project board for people and AI agents: read the plan, claim tasks, report progress. | |
| io.github.danielrz/investbuddy LSTM stock predictions with +15.92% alpha over S&P 500. 10-day forecasts & portfolio analysis. | |
| InvokePort Remote MCP: JSON repair, JSON Schema validation, JSON to TypeScript, CSV to JSON and JSON to CSV. | |
| page.invoker/mcp Deploy forms and sites to live URLs from AI conversations with automatic form capture. | |
| TypeSafe Jev MCP server over TypeSafe Jev: typed ask, rank and check judgments return calibrated probabilities. | |
| Just Fucking Prompt It Makes JFPI links: joke links for people who ask questions an AI could have answered. | |
| jsonshim Recovers malformed LLM JSON. MCP build: 218/300 on MALFORMED-300 (library build 282/300). | |
| com.ou-reports/just-signal Keyless MCP for Just Signal: live quotes, report publishing, scorecard, and Chophouse panel grades. | |
| io.github.stardustxx/kairos Astrology decision support: accurate Swiss Ephemeris charts with calibrated classical verdicts. | |
| Kellian Smart money on every Polymarket market: top traders' positions and fresh moves, research, news. | |
| io.github.lexerAnn/kindlesms Send SMS, manage approved sender IDs, and check credits via KindleSMS. | |
| app.netlify.kitchen-pass/chef A head chef's verified answers as tools: scale recipes, fix cooking faults, swaps, yields and costs. | |
| Kleos Generate, schedule and measure UGC-style TikTok and Instagram posts for your app. | |
| Kloudy Find public MCP tools and SDKs. Compact setup and Sample cards. Free discovery needs no key. | |
| Klype AI Voice and context layer: draft, check and approve posts in a real person's measured voice. | |
| io.github.robertnowell/konid Three translation options per phrase, casual to formal, with register context and audio. | |
| Kryptheon Record a flow through your app, check it after every change, and attack a copy of your database. | |
| Kundali Chart — Vedic Astrology MCP Vedic astrology MCP: 54 tools for charts, dashas, yogas, compatibility, muhurta, transit, remedies. | |
| Kuuhaku Ask who calls a route, what a change breaks or who reads a field, across a system's repos. | |
| LaunchFlag Feature flags and kill switches. Turn a shipped feature off in production without a deploy. | |
| LayoutBridge Light for Adobe InDesign® layoutbridge-light – book typesetting in Adobe® InDesign® via MCP: text, styles, TOC, PDF, EPUB | |
| LayoutBridge for Adobe InDesign® layoutbridge-spm – MCP server for Adobe® InDesign®: pages, frames, text, styles, tables, export | |
| LeakRank Guard Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents. | |
| io.github.vpatser1/legal-doc-analyzer Contract analysis, risk assessment, version diffs, compliance checks (GDPR, CCPA, SOC2) | |
| LemonLDAP::NG MCP Server Manage LemonLDAP::NG SSO instances: configuration, sessions, OIDC, SAML, 2FA. | |
| io.github.rkdpa/local-skills-mcp Universal MCP server for local filesystem skills with lazy loading and context-efficient discovery | |
| Lodekeep Memory MCP server for Claude Code. Correct a fact and the old version stops being recalled. | |
| logbook-mcp Project memory across sessions for AI agents. A queryable decision log in the repo. | |
| LopeBase SEO, Search Console, analytics, revenue, and uptime for every site you run, from LopeBase. | |
| io.github.AnkitaShanbhag30/lorem Slide decks over MCP: read and write decks as code, run Lorem's full AI pipeline, export PPTX/PDF. | |
| Loverflaw Court other AI agents on Loverflaw: thirty-word messages, gates, seven-day clocks. | |
| Lumenhaus Energy Read-only MCP server for Lumenhaus Energy sites, devices, charging sessions, and energy history. | |
| io.github.jugbeep/lustre Premium Flutter UI components for AI coding agents. 46 widgets, 3 themes, light/dark mode. | |
| LuvVoice Text-to-Speech Text-to-speech with 200+ voices in 70+ languages. Requires a LuvVoice API token. | |
| Maiday Distress signal for AI agents: report where you get stuck on websites and fetch site-owner hints. | |
| Mailcycle An email address for your AI agent. Read, wait for and reply to mail, decrypted on your machine. | |
| MainframeKit Mainframe help, no mainframe needed: check JCL and DFSORT, explain abends, lay out copybooks. | |
| io.github.vpatser1/market-data-analyzer Stock technical analysis (SMA, RSI, MACD), portfolio tracking, crypto analysis, screening | |
| Markproof Watermark and C2PA-sign AI-generated images and audio for EU AI Act Article 50, and verify files. | |
| io.github.vpatser1/mcp-api-doc-generator Generate OpenAPI 3.1 specs, endpoint docs, TypeScript SDKs, and test suites from code |
46,451–46,500 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.