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.nexus-mcp-infra/useful-data-source-for-agents-doing-product-price-sdk nexus-mcp-infra/useful-data-source-for-agents-doing-product-price-sdk Semantic product search over Singapore e-commerce, ranked by an auditable entropy-based value-score | |
| io.github.nexus-mcp-infra/x402-receipt-verifier nexus-mcp-infra/x402-receipt-verifier Audits NEXUS's own x402 payment logs against its own delivery logs and issues a signed proof-of-deli | |
| abliteration-mcp neymark/abliteration-mcp MCP server for the abliteration.org catalog: 18 read-only tools over every abliterated and uncensored LLM on Hugging Face, with method classification, download trends, deletion history, and four alignment indices. | |
| Scrapiq ng-pr0ject/scrapiq-mcp-server Any URL to clean text, markdown, or JSON for LLM/RAG pipelines. | |
| io.github.ngkienmkqn/24htrack-mcp ngkienmkqn/24htrack-mcp Track packages across 3,200+ carriers (USPS, UPS, FedEx, DHL & more) with auto carrier detection. | |
| VulX Watch ngotomek/vulx-watch-cursor Independent security review for AI-built apps. Watch a GitHub repo. Never a patch. | |
| io.github.nguyenanhducs/fpl-mcp-server nguyenanhducs/fpl-mcp-server An MCP server that provides Fantasy Premier League analysis and strategy tools. | |
| io.github.nguyenhuy158/healthchecksio-mcp nguyenhuy158/healthchecksio-mcp MCP server for Healthchecks.io API | |
| All-in-One Dev nguyenvanduocit/all-in-one-model-context-protocol All In One Model Context Protocol:
qdrant, google suite (gmail, calendar, ...), jira, gitlab, CLI, ... | |
| io.github.nhadaututtheky/neural-memory nhadaututtheky/neural-memory Persistent memory for AI agents — 55 MCP tools, spreading activation recall. | |
| OpenAPI Swagger MCP nhan7777/openapi-swagger-mcp Discover, preview, call, and inspect configured Swagger/OpenAPI APIs through 11 fixed tools. | |
| GenieLocker nhantour/genie-locker Discover and quote quality-gated private AI inference without creating or buying a locker. | |
| InferenceView MCP nhantour/inferenceview-mcp Provides tools to verify x402/MCP transactions before payment and fact-check claims, with verdicts and sources. | |
| Video Transcriber nhatvu148/video-transcriber-mcp-rs Transcribe videos from 1000+ platforms or local files offline, and search across every transcript | |
| OWA Exchange MCP Server nhype/owa-exchange-mcp MCP server for Microsoft Exchange / OWA — email, calendar, directory, availability | |
| IMAP mailbox ni-c/imap-mcp Read, search and organise any IMAP mailbox, with writes off by default | |
| Linkwarden ni-c/linkwarden-mcp MCP server for Linkwarden, the self-hosted bookmark manager with page preservation | |
| io.github.nice-one-code/NOC.McpServer nice-one-code/noc.mcpserver MCP server exposing NiceOneCode's JSON-to-C# converter as an AI-callable tool. | |
| io.github.nicglazkov/commutescout nicglazkov/commutescout Trip planning and best time to leave, with live road data from 37 US states, traffic, weather. | |
| ClickUp CLI nicholasbester/clickup-cli A token optimised ClickUp CLI with built in MCP server that provides an efficient way to get data from ClickUp without consuming large amounts of LLM context | |
| LinkedIn Sales Navigator nick-choudhary/linkedin-sales-nav-mcp LinkedIn Sales Navigator contact and account search from your logged-in browser. | |
| AgentData nick-timms/agentdata-mcp-server Customer lists of B2B software: every company using a technology, with evidence and dates. | |
| com.dragapp/mcp-server nick-timms/drag-mcp-server AI-powered email & WhatsApp for teams — manage your shared inbox from Claude, Cursor or ChatGPT. | |
| iPhone Mirror nickatnight96/iphone-mirror-mcp Drive a real iPhone via macOS iPhone Mirroring; Xcode build/test automation for sims and devices. | |
| io.github.NickCirv/engram nickcirv/engram Ranked local code-graph context for AI coding agents. Intercepts reads + greps. Apache-2.0. | |
| SafeWeave nickfluxk/safeweave Security scanner for AI-written code: SAST, secrets, dependencies, IaC, containers and DAST. | |
| fieldtwin nickgeorgeseo/fieldtwin Local, stateful twins of the Jobber, Housecall Pro, and QuickBooks Online APIs, for agents and tests | |
| io.github.nickjlamb/opengate-mcp nickjlamb/opengate Check whether an AI answer is grounded in its context — deterministic, no LLM judge. | |
| io.github.nickjlamb/studydiff nickjlamb/studydiff Explain why two scientific papers disagree, every claim grounded in a verbatim source quote. | |
| io.github.nickjlucker/greynoise nickjlucker/mcp-greynoise MCP server for GreyNoise API - Check if IPs are internet background noise or targeted attacks | |
| QueryPilot nickklos10/querypilot Safe SQL gateway for AI agents: SELECT-only validation, access policies, masking, audit trail, evals | |
| Doc_Conv — Document to Markdown nicklee002e/docconv-mcp Convert PDF/Word/Excel/PowerPoint documents to Markdown, paid in USDC via x402. | |
| io.github.NickLiapin/tdcv2 nickliapin/tdcv2-agents Fake, mock and test data generator: CSV, JSON, SQL from a .tdc config, made locally by TDCv2. | |
| com.esti-maite/construction-takeoff-estimating nickpanagios/estimaite-mcp Construction takeoff and estimating for AI agents. Measure a drawing PDF, export a priced estimate. | |
| Phorme Training nicksgoat/phorme-mcp Coach-built training: coaching brains, programs, race plans, gyms, clinics, demos and your log. | |
| io.github.nicksull/mac-organiser-mcp nicksull/mac-organiser-mcp Privacy-focused MCP server for Apple Reminders, Calendar and Notes on macOS. | |
| bash-mcp nickw8/bash-mcp Structured JSON wrappers for git, kubectl, terraform, helm, argocd, gh, glab and other CLIs. | |
| io.github.nickzren/opentargets nickzren/opentargets-mcp Read-only Open Targets: targets, diseases, drugs and evidence by name or ID. No API key needed. | |
| Agentic Ads nicofains1/agentic-ads Ad network for AI agents — monetize MCP servers with contextual ads. 70% revenue share. | |
| AgentWatch nicofains1/agentwatch Multi-agent observability: cascade failure detection, heartbeats, and forensic replay | |
| ABAPilot nicohern/abapilot-mcp ABAP MCP connector for SAP ECC and on-premise S/4HANA. Requires a licensed ABAPilot backend. | |
| Nyx5 nicoiakl/nyx5 An address, a mailbox and a ledger for your agent, where a claim costs something. | |
| ESXi Read-Only Diagnostics nicolasboattini/esxi-readonly-mcp Read-only VMware ESXi diagnostics: CPU Ready, disk latency, snapshots, real space, hardware health. | |
| @docweave/mcp nicolasmartalog/docweave-mcp Write and read PDF documents via MCP: generate PDFs from HTML, URLs, or templates, and extract text from PDFs with OCR support. | |
| Andiamo nicoleblanc/andiamo Plan door-to-door trips across French trains, buses, transit and flights. | |
| Word Orb — English vocabulary for reader glossaries nicoletterankin/word-orb AI-assisted English lexical records. Stored-only batch lookup; coverage and quality vary. | |
| MC3000 Charger nietonchique/mc3000-mcp Safe MCP server for SKYRC MC3000-compatible battery chargers over Bluetooth Low Energy. | |
| Anki nietus/anki-mcp Study and manage Anki flashcards via AnkiConnect: quizzes, stats, leeches, bulk edits. | |
| NiFiMCP nifimcp/nifimcp Evidence-backed, read-only Apache NiFi investigation: cited evidence and reviewable flow drafts | |
| com.niftypm/mcp-server nifty-technologies-inc/nifty-mcp Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents. |
13,751–13,800 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.