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 |
|---|---|
| AgentRead omarhassanatef/agentread Web pages to clean Markdown for AI agents. 5 free calls/day, then pay per call via x402 on Base. | |
| SecHelix omarmohelal/sechelix Evidence-first security review of authorized repositories. Read-only, root-confined, no shell. | |
| ROOT MCP Server omazapa/root_mcp_server ROOT-based MCP server exposing root_python and root_cpp tools (stdio transport). | |
| nanomem ombansod2/nanomem Memory that knows when a remembered fact has been replaced, not just when it was written. | |
| AppScreen omelas-tech/appscreen-mcp Render App Store and Google Play screenshots from app captures: device frames, sizes, languages. | |
| io.github.omitly/omitly-mcp omitly/omitly-mcp Omitly's local, verifiable PDF redaction for AI agents — your documents never leave your device. | |
| io.github.omkar9854/token_optimizer omkar9854/token_optimizer Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable | |
| Omnara omnara-ai/omnara Deploy durable AI agents with Omnara, an open-source managed-agent platform. | |
| Planka MCP omnicoreos/planka-mcp Planka 2.x MCP server with verified card, task, comment, label, and list operations. | |
| io.github.Omnidim/omnidim-mcp-server omnidim/omnidim-mcp-server Official MCP server for OmniDimension. Drive voice agents, dispatch calls, and run bulk campaigns. | |
| ProfitSpot MCP omniologynow-rgb/profitspot-mcp Cross-chain DeFi intelligence MCP server for AI agents. 7 tools for yield discovery, pool analysis, profit simulation, risk scoring, whale tracking, impermanent loss calculation, and DeFi overview across 86 chains and 6,500+ liquidity pools | |
| Scout Intel MCP omniologynow-rgb/scout-intel-mcp Web intelligence MCP server for AI agents. 7 tools for SERP analysis, competitor research, market trends, content gap analysis, keyword insights, audience discovery, and citation tracking. | |
| OmniSignal omnisignal-ai/omnisignal-mcp Live market intelligence & AI content strategy: trends, competitor moves, content calendar. | |
| graphy omnislash157/graphyos Compile any codebase into a walkable graph and serve it over MCP. No model decides an edge. | |
| io.github.OmniSocKit/omnisockit-mcp omnisockit/omnisockit-mcp Turn your AI into a WeCom development expert. 41 SKILLs, 550+ APIs. | |
| freshdesk-mcp omnom62/freshdesk-mcp Self-hosted Go MCP server for Freshdesk with 15 tools: ticket search, conversations, attachment text extraction, and Vision AI OCR for images. | |
| io.github.Omodaka9375/netexpert-mcp omodaka9375/netexpert-mcp Cross-platform local-network diagnostics & security-posture MCP server — 31 tools. | |
| io.github.Omodaka9375/ugnas-mcp omodaka9375/ugnas-mcp Generic MCP server for UGREEN NAS (UGOS) over SSH — 39 tools with dry-run safety. | |
| Mofi omofi/mofi-mcp Ask your AI about Brazilian bank spending. Read-only bank access, never moves money. Paid plan. | |
| io.github.OMOPHub/omophub-mcp omophub/omophub-mcp Search, lookup, map, and navigate OMOP medical vocabularies via AI agents | |
| io.github.OnChainAIIntel/pqs-mcp-server onchainaiintel/pqs-mcp-server PQS scores any prompt before the model runs. 8 dimensions. 5 frameworks. Pre-flight, not post-hoc. | |
| io.github.onchainvanguard/scytheradar-mcp onchainvanguard/scytheradar-mcp Read-only bilingual screening, blacklist, fund tracing, rug-pull forensics. TRON dirty-USDT + EVM. | |
| FileSystem MCP Server oncorporation/filesystem_server Secure filesystem access for AI agents with configurable directory and file type restrictions | |
| io.github.aborruso/ckan-mcp-server ondata/ckan-mcp-server MCP server for interacting with CKAN open data portals | |
| Onde Inference CLI ondeinference/onde-cli Manage your Onde Inference account and models: apps, model catalog, fine-tuned GGUF deploys. | |
| Gretl MCP ondrejlapes/gretlmcp Run Hansl/Gretl econometrics workflows via MCP with GUI launch and artifacts. | |
| Agent Config Bridge onehumanbeing/agent-config-bridge Convert CLAUDE.md, AGENTS.md, Cursor rules, GEMINI.md and MCP configs between coding agents. | |
| io.github.oneill9/tfl-mcp-server oneill9/tfl-mcp-server Community-built server providing real-time London transport data via the TfL Unified API | |
| io.github.onelogin/onelogin-mcp onelogin/onelogin-mcp MCP server for OneLogin API - manage users, apps, roles, and authentication | |
| Service Public France onenicolas/mcp-service-public French public services: tax, property, admin, education, healthcare, security, risks, legal texts | |
| io.github.oneprofile-dev/curatedmcp-catalog-mcp oneprofile-dev/curatedmcp-catalog-mcp Search the CuratedMCP catalog of risk-classified MCP servers and check verification status. | |
| io.github.oneprofile-dev/mcp-launcher oneprofile-dev/mcp-launcher Single MCP hub: discover, add, audit, and govern MCP servers across every AI client. | |
| OneQAZ Trading Intelligence oneqaz-trading/oneqaz-trading-mcp Verifiable crypto/KR/US market intelligence for AI agents: signals, hash-chained ledger. Not advice. | |
| Commentify oneslash-app/commentify-plugin Your team's design feedback from Figma, Jira and Notion: ask, search, read, reply, mark done. | |
| io.github.onetrueclaude-creator/hebbian-vault onetrueclaude-creator/hebbian-vault Usage-adaptive Obsidian vault search: Hebbian + PageRank + BM25 hybrid ranking. | |
| io.github.onetrueclaude-creator/mcp-contradiction-check onetrueclaude-creator/mcp-contradiction-check Find where your notes disagree — contradiction detection for markdown vaults. | |
| io.github.onetrueclaude-creator/mcp-curiosity-engine onetrueclaude-creator/mcp-curiosity-engine Surface the notes you forgot you wrote — DMN replay for markdown vaults. | |
| io.github.onetrueclaude-creator/mcp-knowledge-gaps onetrueclaude-creator/mcp-knowledge-gaps Find what your knowledge base mentions but doesn't actually explain. | |
| io.github.onetrueclaude-creator/vault-health-mcp onetrueclaude-creator/vault-health-mcp Obsidian vault structural health: broken links, orphans, missing frontmatter, safe auto-repair. | |
| Onexur Manager MCP onexuross/mcp-manager.io MCP server for Manager.io bookkeeping: read-first with opt-in scoped task and write tools | |
| OnlyDNS MCP Server onlydns/onlydns-mcp Model Context Protocol server for OnlyDNS to manage DNS zones, records, DNSSEC, and TSIG keys. | |
| Google Search Console onlymoein/google-search-console-mcp Search Console analytics, hourly data, URL inspection and sitemaps, with guards for API quirks. | |
| agenteconomy.cloud onnson/agenteconomy-mcp x402 seller trust for AI agents: verify on-chain revenue, check delivery, diagnose listings. | |
| ContextOverflow onnson/context-overflow Describe what's going wrong with your AI; get the named technique both of you can read. No auth. | |
| mneme Record onourimpram/mneme Vault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth. | |
| Onplana onplana/onplana-mcp-server AI-native project and portfolio management platform for PMOs. OAuth + PAT. | |
| 3DPACK.ING — Container & Truck Load Planning onurgumus/3dpacking-mcp Container load planning in Claude & ChatGPT: what fits, how full, a labelled 3D plan in the chat. | |
| Sheet & Flow Landlord Math onyxaholguin-cyber/sheet-and-flow-mcp Landlord math: rental cash flow, cap rate, DSCR, Airbnb break-even, late fees, lease notices. | |
| SAP MCP Server oobe-protocol/sap-mcp Solana-native MCP gateway for SAP, DeFi tools, SNS identity, and x402 payments. | |
| io.github.oogdevs/clawtube-mcp oogdevs/clawtube-mcp Minimal MCP server for ClawTube — a small, auditable control plane for skills and agents. |
14,151–14,200 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.