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 |
|---|---|
| ai.smithery/morosss-sdfsdf morosss/sdfsdf Find academic papers across major sources like arXiv, PubMed, bioRxiv, and more. Download PDFs whe… | |
| io.github.Morous-Dev/engram-cc morous-dev/engram-context-continuum Universal AI coding assistant memory — session handoff, SLM compression, and semantic retrieval. | |
| CAN-TAP Verified morphious33453/can-tap-verified-mcp Free dofollow backlinks for Canadian businesses. Claim, verify, and track NFC tap analytics. | |
| io.github.morrillonline/gedfire morrillonline/gedfire GEDCOM CLI and MCP server for AI-assisted family-history research with reviewable changesets. | |
| com.wyrdmcp/wyrd mortalpastry/wyrd-mcp Exposes one granted folder to any AI client, read-only, behind a path-containment fence. | |
| io.github.mortenator/charta mortenator/charta-mcp Generate beautiful, presentation-ready charts (SVG + PNG). Supports 14+ chart types. | |
| pit.world MCP server moshcoder/pit.world MCP server for private web search (no API key) and Moshpit name lookups. No logs, no cookies. | |
| Idiolect AI moshpit-labs/idiolect-mcp Write, rewrite, and refine in your own style. Build and manage your Writing Profile. | |
| Taskmarket Onchain API mostafaashry513/taskmarket-x402-mcp On-chain receipts, balances, tx status and address activity, pay-per-call via x402 USDC on Base. | |
| Conducted MCP mostov82/conducted-mcp Stateless advisor + validator for Conducted Development: kickoff, artifact validation, rule checks. | |
| Motecloud Memory motecloud/motecloud-mcp-server Cloud-hosted MCP server for durable AI memory | |
| io.github.motherduckdb/mcp-server-motherduck motherduckdb/mcp-server-motherduck SQL analytics and data engineering for AI Assistants and IDEs | |
| Motomarks MCP Server motomarks/motomarks-mcp Car logo API and image CDN: search automotive brands, fetch brand data, and build logo CDN URLs. | |
| io.github.mouhabmzibra-rgb/seo-backlinks mouhabmzibra-rgb/mcp-seo-backlinks Backlinks, Domain Rating & expired-domain drops via seo-backlinks.net (Common Crawl) | |
| io.github.moureauf/boe-mcp moureauf/boe-mcp Bank of England base rate, rate history, historical lookup, and next MPC meeting date over stdio. | |
| Xadeus-QQ-MCP mouse114514/xadeus-qq-mcp QQ MCP Server with Auto-Wake, message send/receive, group management, file sharing, and timed tasks. Connects via NapCatQQ (OneBot v11). One-click setup with quickstart.ps1.Based on Amadeus-QQ-MCP. | |
| China Context MCP mouseart2025/china-context-mcp 中国节假日与调休（单日+年度聚合）、历史上的今天、随机诗词、身份证号校验（GB 11643，本地零网络）。零凭证。 | |
| io.github.justinmont84/loyaltyvip movamedia-inc/loyaltyvip-js U.S. casino directory + a player's loyalty data, comps, tiers, and gambling tax docs. | |
| EU Cloud moveinfra/eu-cloud-mcp Move off AWS, GCP, Azure: EU-owned alternatives, EU cloud prices, exit fees, Terraform lock-in scan. | |
| Product Page Extractor mowaah/product-extractor-mcp Price & stock checks, catalog enrichment: product URL or HTML to JSON, with price_source. RapidAPI | |
| OathScore moxiespirit/oathscore Real-time world state and independent API quality ratings (0-100) for AI trading agents. Exchange status, volatility (VIX/VVIX/SKEW), economic events, and data source reliability — 8 tools. | |
| io.github.moxno/ztds moxno/ztds.ai Open standard MCP server for Zero-Trust Data Sanitization (ZTDS RFC v1.0). In-memory PII masking. | |
| ProductBrain moxzas/productbrain-mcp Drive your ProductBrain product plan (goals, needs, bets, jobs) from any MCP client. | |
| Firefox DevTools MCP mozilla/firefox-devtools-mcp Control and debug Firefox: navigate, fill forms, inspect network and console, profile. | |
| SmithTalks mozzimorzam-sudo/smithtalks-mcp Pseudonymous message network for agents. Claims, marketplace, 20 tools, verifiable seal. | |
| Apple Calendar mp-consulting/apple-calendar-mcp Read, search and plan Apple Calendar on macOS via EventKit: free time, undo, you approve deletes | |
| Apple Mail mp-consulting/apple-mail-mcp Search, read, sort and answer Apple Mail on macOS: fast local reads, drafts first, you approve sends | |
| Homebridge mp-consulting/homebridge-ai-kit Control Homebridge accessories and scenes, manage plugins and config.json, and read logs | |
| io.github.mp-juns/universal-research-mcp mp-juns/universal-research-mcp Provenance-first research memory with hash-bound evidence and a fail-closed eligibility gate. | |
| Komodo MCP Server mp-tool/komodo-mcp-server MCP server for Komodo - manage Docker containers, servers, stacks, and deployments via AI | |
| Outlook MCP mpalermiti/outlook-mcp Microsoft Outlook personal accounts: mail, rules, calendar, contacts, to-do, drafts (77 tools). | |
| zabbix-mcp-server mpeirone/zabbix-mcp-server 🔌 Complete MCP server for Zabbix integration - Connect AI assistants to Zabbix monitoring with 40+ tools for hosts, items, triggers, templates, problems, and more. Features read-only mode and comprehensive API coverage. | |
| Ensemble mpfeifer33/ensemble-mcp AI-ready design toolkit: color palettes, typography, spacing, shadows and accessibility audits. | |
| com.kettlelogic/mcp-kettlelogic mploschiavo/mcp-kettlelogic MCP server exposing Kettle Logic insight articles & industry guidance as tools + resources. | |
| Larnitech mpopovych-thinkhome/larnitech-mcp Read, watch and safely control Larnitech smart-home controllers over the API2 protocol. | |
| io.github.mpzarde/fabric-mcp mpzarde/fabric-mcp MCP server for Fabric AI patterns | |
| Public Board — Anonymous Message Board for AI Agents mq1n/field-notes-mcp Message board for AI agents: read, search and leave notes over HTTP, DNS or a non-CDN mirror. | |
| StaleDocs mr-min-max/staledocs Finds documentation that no longer matches your code. Deterministic AST check; no API key. | |
| io.github.MR901/mcp-plots mr901/mcp-plots MCP server for data visualization with Mermaid charts. | |
| AgentCanary mrcerq/agentcanary-mcp Retired compatibility stub for AgentCanary MCP. Daily briefs continue on X and Telegram. | |
| IDA Pro MCP mrexodia/ida-pro-mcp MCP Server for automated reverse engineering with IDA Pro. | |
| User Feedback mrexodia/user-feedback-mcp Simple MCP Server to enable a human-in-the-loop workflow in tools like Cline and Cursor. This is especially useful for developing desktop applications that require complex user interactions to test. | |
| Taghvim mrfelfel/taghvim Deterministic temporal reasoning engine for AI agents.
LLMs are surprisingly bad at dates, timezones, business days, holidays, and recurring schedules. Taghvim gives agents deterministic temporal primitives they can call instead of guessin | |
| io.github.mrfentmen/adobe-premiere-mcp mrfentmen/adobe-premiere-mcp Control Adobe Premiere Pro video editing via ExtendScript. | |
| io.github.mrfentmen/artifact-gauge-mcp mrfentmen/artifact-gauge-mcp Local build artifact size and dependency weight inspection without file content output. Tools... | |
| io.github.mrfentmen/gimp-mcp mrfentmen/gimp-mcp Control GIMP image editing via Python-Fu scripting from AI agents. | |
| io.github.mrfentmen/git-reflog-archaeologist-mcp mrfentmen/git-reflog-archaeologist-mcp Aggregate local Git reflog and recovery signals without exposing repository content. Tools... | |
| io.github.mrfentmen/gopher-mcp mrfentmen/gopher-mcp Use this MCP server to the Gopher protocol, browse gopherspace, the pre HTTP internet. Menus,... | |
| io.github.mrfentmen/meilisearch-mcp mrfentmen/meilisearch-mcp Search indexes, manage documents, check health and stats. | |
| io.github.mrfentmen/mixpanel-mcp mrfentmen/mixpanel-mcp Query Mixpanel events, funnels, retention, cohorts, and user profiles. |
13,351–13,400 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.