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 |
|---|---|
| io.github.Rajveerx11/gfi-scout rajveerx11/gfi-scout Finds open source issues where beginners actually succeed, ranked by a 0-100 beginner score. | |
| io.github.RajX-dev/n3mo rajx-dev/n3mo N3MO: Code intelligence engine mapping repositories into queryable symbol graphs. | |
| AgentDrive rakesh1002/agentdrive-mcp Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph. | |
| io.github.Rakesh1002/namemyapp rakesh1002/namemyapp-mcp Brandable business names with live domain availability + one-click buy URLs. | |
| Agent Kiosk — 23-in-1 B2A Intelligence, Action & x402 API ralf9090/agent-kiosk 23-in-1 MCP server: EVM tx simulator, funding rate arb, macro radar, swap calldata & security. | |
| SqlToAi ralfhuesing/sqltoai Microsoft SQL Server schema discovery and SQL tools over local stdio on Windows x64. | |
| Titen Memory ramaaditya49/titen Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1 | |
| ai.smithery/ramadasmr-networkcalc-mcp ramadasmr/networkcalc-mcp Look up DNS information for any domain to troubleshoot issues and gather insights. Get fast, relia… | |
| NervaPack ramdhavepreetam/nervapack Offline codebase knowledge graph: 91% token reduction vs naive RAG, plus cross-session agent memory. | |
| Rami Code Review rami-code-review/claude-code-marketplace AI code review for GitHub PRs with an MCP autofix loop for Claude Code and Cursor | |
| mdreview ranawaqas-ai/mdreview-service Human-in-the-loop document review: an agent pushes a draft, a person comments, the agent revises. | |
| bot.ranch/mcp-server ranchbot/mcp-server Read and write cattle and sheep records with farm-scoped, revocable access. | |
| Pi-hole MCP Server ranklancer/pihole-mcp MCP server for Pi-hole v6 API — manage multiple instances: queries, lists, groups, stats | |
| io.github.Ranork/remnus ranork/remnus-app MCP-native open-source Notion alternative: read & write pages, databases and kanban boards. | |
| io.github.Ranshiv/noether-physics ranshiv/noether-physics Physics assistant: checked equations, live simulations, claims verified against arXiv papers | |
| forgejo-mcp raohwork/forgejo-mcp An MCP server for managing your repositories on Forgejo/Gitea server. | |
| QuickerSpot MCP Server raphaelinacio/quickerspot-mcp Servidor MCP do QuickerSpot para vinhetas, rádio indoor e sonorização comercial com IA. | |
| NeuroStack raphasouthall/neurostack Token-efficient MCP memory for Markdown vaults. Tiered search, GraphRAG, AI memories. | |
| io.github.raphysicst-create/korean-secondary-learning-map-mcp raphysicst-create/korean-secondary-learning-map-mcp 한국 중등 2022 개정 교육과정 학습 그래프 MCP 서버 (중학교 714 · 고교 3,124 성취기준 · 원문 수록 · 중→고 전이) | |
| io.github.raphysicst-create/korean-vocational-learning-map-mcp raphysicst-create/korean-vocational-learning-map-mcp 한국 특성화고 전문교과 2022 개정 교육과정 학습 그래프 MCP 서버 (528과목·성취기준 47,625건, 공식 원문 전량 수록) | |
| io.github.RapierCraft/perplexity-comet-mcp rapiercraft/perplexity-comet-mcp Bridge Claude Code with Perplexity Comet for autonomous browsing and tab management | |
| io.github.raportagent/raportagent-mcp raportagent/raportagent-mcp Sourced market and compliance research for Claude Desktop, Claude Code and Cursor. | |
| ReelScribe rara-cyber/reelscribe-mcp-server Transcribe social videos, selected comments, URL batches and Instagram channels. | |
| Nova3D raresense/nova3d-mcp Structured, part-aware 3D generation for AI agents. Named-part GLB, preview URL, Blender script. | |
| Rasczak Knowledge Commons rasczak-commons/agent-service Free decision methods, work-kit previews and optional feedback. Hosted research is not available. | |
| Airtable MCP rashidazarang/airtable-mcp Connects AI tools directly to Airtable, allowing users to query, create, update, and delete records using natural language. | |
| Misata: synthetic data library rasinmuhammed/misata Declarative synthetic data: multi-table data that holds the facts you declare, checked by DuckDB. | |
| Adaptive Memory Graph raskolnikovdd/adaptive-memory-graph Persistent memory for Claude via weighted, interconnected knowledge nodes. | |
| rasterly rasterly-dev/rasterly-mcp Web toolkit for AI agents: read any URL as Markdown, screenshot, extract data, or crawl a site. | |
| io.github.rastogivaibhav/llm-kosh rastogivaibhav/llm-kosh Local-first AI memory cartridge with persistent MCP memory for Claude via SQLite FTS5. | |
| Ratevert MCP ratevert/mcp Read-only Ratevert MCP for asset search, pair rates, and conversions. | |
| RationalBloks rationalbloks/rationalbloks-mcp Deploy production REST APIs from JSON schemas in seconds. Manage projects, schemas, and deployments. | |
| CSVGlow ratnaditya-j/csvglow Turn any CSV into a stunning interactive dashboard with one command — works as CLI, MCP server, or AI skill | |
| SpineFrame ratnaditya-j/spineframe Governance runtime for AI agents with signed provenance, compliance audits, and OSINT. | |
| io.github.raullenchai/vnsh raullenchai/vnsh Portable workspaces for AI agents: one encrypted link any agent can read and write | |
| io.github.RaulSimpetru/zotero-library-mcp raulsimpetru/zotero-library-mcp Add papers and books to Zotero by DOI, arXiv ID, or ISBN and manage your library | |
| io.github.raunakkathuria/lexilint raunakkathuria/lexilint-mcp Offline spell checker + BYOK grammar for AI assistants. Works with Claude Desktop, ChatGPT, Cursor. | |
| io.github.ravendb/ravendb-mcp ravendb/ravendb-mcp Read-only MCP diagnostics server for RavenDB. | |
| io.github.ravi-p-k-1/insightiq ravi-p-k-1/insightiq Look up real FRED (Federal Reserve Economic Data) series and historical observations. | |
| Crossplane ravibagri5/crossplane-mcp-server Read-only access to a Crossplane control plane: resources, claims, packages, compositions. | |
| Literature Review Council ravicha2/lit-review-council Multi-agent literature review: research, peer review, and synthesize grounded reports. | |
| com.murphys-laws/murphys-laws ravidorr/murphys-laws Access thousands of Murphy's Laws: search, browse by category, random, daily, submit. | |
| SharePoint MCP Server ravikant1918/sharepoint-mcp MCP server for Microsoft SharePoint — manage folders, documents, and metadata. | |
| PredMCP raviolelabs/predmcp Polymarket + Hyperliquid + macro for AI agents. 38 tools, signal backtest, SSE streaming. Free tier. | |
| Azure FinOps MCP Server raviteja-pegata/azure-finops-mcp-server Azure FinOps MCP: cost, budgets, forecasting and optimization for Claude, VS Code and Cursor. | |
| Onto ravixalgorithm/onto-mcp Clean Markdown and AI-readability scoring for any URL. Built for AI agents. | |
| ravn ravndex/ravn-mcp-glama Enables cross-chain swap execution across 12 venues and 17 chains, including native Bitcoin as source or destination, with tools for quoting, execution, status, and health checks. No signup, API key, or protocol fee required. | |
| io.github.raxocode/seo-notary raxocode/seo-notary Verify what a web page really returns over HTTP and in a browser. Deterministic, local, no LLM. | |
| io.github.Ray0907/git-mcp-server ray0907/git-mcp-server MCP server for GitLab and GitHub | |
| io.github.RayAKaan/ocular-audio-mcp rayakaan/ocularaudio-mcp MCP server for video transcripts, screenshots, and OCR on YouTube and web videos. |
17,051–17,100 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.