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 |
|---|---|
| Feishu MCP Self-hosted Single-owner Feishu MCP: run your own service, configure your app, authorize your Feishu account. | |
| Weather Data MCP Server 17 weather tools, no API keys: forecasts, alerts, air quality, marine, radar, lightning, wildfires | |
| 3DAPI 3D print on demand through the 3DAPI API: quotes, orders, products, stock, wallet and webhooks. | |
| DarkKnight Cave Motion Library Search attributed motion recipes and prepare prompts for your coding agent. No API key required. | |
| Databasin Explore Databasin data, run read-only queries, and manage your support tickets with secure sign-in. | |
| VerifyRef AI agent recruiting: talent pool match, reference checks, credit packs via Stripe MPP | |
| DataNexus MCP Public data intelligence for AI agents — CVE, compliance, patents, contracts, domains. | |
| tech.dataoil/mcp Query Data Oil via AI: SQL, schema discovery, search and ingestion. sandbox.dataoil.tech/ 3 in 1 | |
| Redshift MCP Server Secure, read-only access to Amazon Redshift with schema introspection and smart sampling | |
| com.dealsurface/dealsurface Insurance go-to-market intelligence: ranked prospects, evidence, buying committees and outreach. | |
| Decionis Commerce Gate MCP Commerce preflights, D365 authorization; opt-in agent writes require authorized backend connectors. | |
| DemoMagic Guides for making interactive videos & AI product demos that answer viewers' questions. | |
| Denik Book appointments, check availability, list services and create payment links for a Denik business. | |
| GrazieChef Kitchen Tools Restaurant math for AI assistants: food cost, menu price with VAT, recipe scaling, EU 14 allergens. | |
| DevSpeak Improve or correct developer writing, or turn rough notes into technical specs, from your agent. | |
| com.7275/adwhiz Read-only MCP access to your DEXUN AdWhiz account: ad accounts, AI recommendations, savings. | |
| DidWork Verify that an agent's claimed outcome actually happened, using independently gathered evidence | |
| io.github.dishui/motion-mcp-public Remote MCP server bridging Motion to Claude | |
| DiviMail Give your AI agent its own email address: send, receive and read email. $0.01 USDC per send. | |
| Control AutoCAD MCP Server Control AutoCAD with AI: commands, read/edit/write drawing database, AutoLISP, scripts, PDF plots. | |
| CADBridge MCP Server for AutoCAD Control AutoCAD with AI: commands, read/edit/write drawing database, AutoLISP, scripts, PDF plots. | |
| Control AutoCAD MCP Server Control AutoCAD with AI: commands, read/edit/write drawing database, AutoLISP, scripts, PDF plots. | |
| io.docmill/mcp-server Generate PDF, DOCX, and XLSX documents from JSON data and create reusable templates via Docmill | |
| MantisBT MCP Server MantisBT MCP server – manage issues, notes, files, tags, and relationships. With semantic search. | |
| io.github.dynamicupgrade/chromedebug Record browser bugs - frames, clicks and console logs - and hand them to your AI over MCP. | |
| Genealogy Reads and edits local GEDCOM/BegatAll over stdio. Living people shown unless you hide them. | |
| Easy Labs MCP Server Payments data, revenue workflows, and merchant-application guidance for AI agents, by Easy Labs. | |
| EU E-Invoice API Validate, parse and generate EU e-invoices: XRechnung, ZUGFeRD, Peppol BIS, KSeF, FatturaPA. | |
| io.github.IndirectTek/mcp-server Elixium AI — XP-native agile platform. TDD-gated stories, team decisions, learning loop. | |
| Émile MCP server for the Émile wine cellar — list, add, recommend, scan and search 100k+ wines. | |
| SEV — Company Discovery from SEC Filings Ask a research question; in seconds get ranked companies, vetted 10-K/10-Q passages and financials. | |
| Eusend Send transactional email and manage domains, audiences, and broadcasts from any MCP client. | |
| ezStats MCP Privacy-first website analytics MCP server for ezStats with analytics, SEO, goals, and MCP tools. | |
| io.github.fablenator/tiled-mcp Inspect, validate and surgically edit Tiled map files (.tmx/.tmj) — byte-preserving, 12 tools. | |
| Faldaro Forms, submissions, workflows and reports in Faldaro, exactly as privileged as your API key. | |
| io.github.fasteningcode/claudetest Playwright & Appium test automation for Claude. Generate tests, diagnose failures, open fix PRs. | |
| io.github.fcon-tech/portolan Portolan: an MCP server that charts codebases - Chart store, Harbor expeditions, Chart Room. | |
| io.github.fennecstudio/x-tkn-mcp Lets an AI agent hand a secret to a person as a one-time link, with no way to read it back. | |
| io.github.Mahfod-dev/flowcontent Connect Claude, Cursor, or any MCP client to your FlowContent account | |
| FlyDocs Spec-driven development workflow: your agent works issues, sessions and the status lifecycle. | |
| Forkbit Nutrition data for AI agents: search foods, look up nutrients, parse meals, analyze recipes. | |
| Formmy Run WhatsApp AI agents: manage agents, conversations, CRM contacts, orders and RAG docs. | |
| Frappe Inspector Static analysis tools for Frappe Framework and ERPNext projects via local stdio MCP. | |
| CSE MCP MCP server for Colombo Stock Exchange data | |
| com.gaudiolab/mcp-developers Gaudio Lab Audio AI — Stem Separation, DME Separation, AI Text Sync | |
| Gessa: game asset generation for AI agents Generate game-ready 3D models, textures, and audio from natural language, over MCP. | |
| Bourdon Recognition-first cross-agent memory federation. One shared memory across all your agents. | |
| Edge Gives your agent the right public skill for each task and loads it on demand. | |
| Mikie Focused repository context for Claude Code and Codex, with per-session token usage receipts. | |
| Gheima Deploy and run apps, databases and storage on the Gheima platform, billed in MAD. |
46,001–46,050 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.