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 |
|---|---|
| Proxmox MCP Server gethosthewalrus/proxmox-mcp Enables AI assistants and MCP clients to manage Proxmox VE infrastructure, including virtual machines, containers, storage, networking, and high availability through a standardized interface. | |
| Temporal MCP Server gethosthewalrus/temporal-mcp Enables AI assistants to manage Temporal workflows, schedules, and workflow executions through a standardized interface. | |
| io.github.www-in-bio/inbio getinbio/inbio-mcp Official in.bio MCP server: shorten URLs, styled QR codes, and click analytics. No API key needed. | |
| io.github.getjobzi/getjobzi-mcp getjobzi/getjobzi-mcp-server GetJobzi MCP server for job search, application tracking, and career forecasting. | |
| io.github.getjoystick/nanobanana-mcp getjoystick/nanobanana-mcp Lean MCP server for Google's Nano Banana (Gemini) image models. Returns file paths, not base64. | |
| io.github.getmarrow/marrow getmarrow/marrow-mcp Runtime governance, proof, outcome closure, and fleet intelligence for MCP-compatible AI agents. | |
| io.github.getmasv/masv getmasv/masv-mcp-server Provides tools to use MASV API. MASV is reliable and secure large file transfer service. | |
| GetMattered getmattered/getmattered-mcp Auto-Apply That Ends on an Interview. Job matches, per-role resumes, apply, approve, track receipts. | |
| Mochify getmochify/mochify-cli Image and PDF toolkit: convert to AVIF/WebP/JXL, resize, crop, remove backgrounds, optimize PDFs. | |
| com.getmunin/munin getmunin/munin Open-source all-in-one MCP-first customer platform: KB, Conversations, CRM, CMS, Outreach, Analytics | |
| nable getnable/finopsmcp Prices what your coding agents are about to do, before they do it. Plus local cloud and AI cost. | |
| nahook-mcp getnahook/nahook-mcp The official MCP server for Nahook. Manage webhook endpoints, inspect deliveries and delivery attempts, retry failed deliveries, and list environments — directly from Claude, Cursor, Cline, or any MCP-compatible client. | |
| PAPI: Persistent Adaptive Project Intelligence getpapi/papi Adaptive plan/build/review cycles for AI coding assistants, persisted across sessions. | |
| io.github.popapidev/pop-mcp getpopapi/pop-mcp Italian e-invoicing (FatturaPA/SdI), Peppol, KSeF, ZUGFeRD, and PDF invoice generation via POP | |
| PostStack MCP Server getpoststack/mcp An MCP server for the PostStack email API that enables AI assistants to send transactional emails, manage contacts, handle inbound email threads, and perform deliverability checks through 84 curated tools. | |
| ProxyKit-mcp getproxykit/proxykit-mcp MCP server for ProxyKit — drive a local HTTP(S) debugging proxy from Claude, Cursor, and any MCP host. | |
| io.github.getqlows/qlows-mcp getqlows/qlows-mcp Find Tenders in 35 Countries of the WTO-GPA Zone and ground your AI for your RFP responses | |
| quario getquario/mcp Validate and render quario report definitions (JSON) to PDF, Excel, Word, HTML or CSV. | |
| Reletter getreletter/reletter-mcp Search and analyze 7M+ newsletters, issues, contacts, and chart rankings from Reletter. | |
| ReMCP getremcp/remcp Enables MCP clients to securely work with local files, directories, searches, terminal sessions, and processes on paired computers via outbound connections, without exposing inbound ports. | |
| Seline getseline/seline-mcp MCP server for the Seline Analytics API | |
| siGit getsigit/si MCP server for siGit (sigit.si): browse repos, search code, manage PRs/issues, web search. | |
| io.github.SuperAgentic/spines getspines/mcp-server Access book collections, reading lists, and bookshelf recognition from AI assistants. | |
| Squish getsquish/squish Give AI random access to video: timestamped contact sheets + zoom into any start/end range. | |
| io.github.GetUserProof/userproof getuserproof/userproof The top conversion fix from real visitor sessions, with file and line, checked after you ship. | |
| com.getvaletparking/valet-parking-directory getvaletparking/valet-parking-mcp MCP server for valet parking: 789 US operators across 31,186 cities. 7 tools. No auth. | |
| io.github.getvari/vari-mcp getvari/vari-mcp 6 hydration calculators for LLMs: water intake, dehydration, pregnancy, CKD, athlete, energy. | |
| Watchr getwatchr/watchr-mcp Competitive intelligence and brand monitoring for AI assistants via Watchr. | |
| Geztio Platform geztio/mcp-server Construction cost & project management: APU analysis, budgets, price lists, site execution. | |
| haiku.rag ggozad/haiku.rag Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval | |
| GitHubCard ghcardhq/githubcard-mcp Create GitHub profile and repository cards for READMEs, link previews and social posts. | |
| tfl-ts ghcpuman902/tfl-ts Read-only Transport for London data: line status, arrivals, journeys, stop lookup. | |
| io.github.ghdejr11-beep/saju-mcp ghdejr11-beep/saju-mcp Korean Four Pillars of Destiny (Saju/Bazi): calculate, interpret, compatibility & daily fortune. | |
| Flow Learning System ghlee0786/flow-learning-system Build motion-graphics lessons with sentence-synced TTS for any subject: one sentence, one scene. | |
| Ghost in the Droid ghost-in-the-droid/android-agent Give any LLM agent a real Android or iPhone as its body. 62 MCP tools for mobile automation. | |
| android-use ghostfacemodz/android-adb-mcp Let AI agents see and control an Android phone over ADB, with safety guards. | |
| Vaultfire Trust Protocol ghostkey316/vaultfire-mcp-server On-chain trust verification and Street Cred for AI agents. ERC-8004, multi-chain. | |
| GhostPaw Affinity ghostpawjs/affinity Local relationship model and social CRM for contacts, relationships, evidence, and commitments. | |
| GhostPaw Codex ghostpawjs/codex Local belief and memory engine with evidence, certainty, and honest revision history. | |
| GhostPaw Email ghostpawjs/email Email tools with a local SQLite cache and IMAP/SMTP account configuration. | |
| GhostPaw Grimoire ghostpawjs/grimoire Local procedural knowledge with spells, notes, and revision history. | |
| GhostPaw Questlog ghostpawjs/questlog Local tasks, calendar commitments, and recurring work. | |
| GhostPaw Souls ghostpawjs/souls Local cognitive identity engine with traits, behavioral evidence, and revision history. | |
| GhostPaw Telegram ghostpawjs/telegram Telegram message mirror, search, sending, and moderation tools. | |
| GhostSwap ghostswap1/ghostswap-agents GhostSwap — non-custodial crypto swaps across 1,600+ coins. | |
| io.github.giancarloerra/socraticode giancarloerra/socraticode MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs. | |
| TheSEO gianlucanaarden/theseo-mcp AI-zichtbaarheid per model, gat-analyse, crawlercheck, NL vakregels met bron en 149 Claude-skills | |
| me.sendable/sendable gibrancorbin11-hub/sendable Send transactional email from your editor — describe the event, Sendable writes and sends it. | |
| com.gibsonai/mcp gibsonai/mcp GibsonAI MCP server: manage your databases with natural language | |
| io.github.gigabrain-observer/google-docs-mcp-server gigabrainobserver/google-docs-mcp-server Google Docs MCP server with full tab support, markdown extraction, and batch updates. |
8,301–8,350 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.