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 |
|---|---|
| sealkeep munhq/sealkeep Let AI agents use secrets without seeing them: inject into a command, redact the output. | |
| ar.com.muovi/mcp-server muovi-latam/mcp-server MCP server for Muovi, Argentina's trust-first local services marketplace: find pros, draft tasks. | |
| QA Radar muratkus/qaradar Tells AI agents which files to test first — churn, coverage, and test mapping as risk scores. | |
| io.github.murilojrpereira/mcp-graphql-bridge murilojrpereira/mcp-graphql-bridge Bridges any GraphQL API to Claude Code — auto-generates MCP tools via schema introspection. | |
| EasySociable murphywuwu/easysociable-mcp AI carousel maker for coding agents: branded multi-page carousels for TikTok, LinkedIn, Instagram. | |
| Cue murtazox04/cue Notify people through Cue: preferences, attention budgets, quiet hours and approval apply. | |
| io.github.Murugarajr/ohm-mcp murugarajr/ohm-mcp AST-based Python refactoring MCP server with safe automated refactorings and rollback | |
| VPS Guardian murzirius/vps-guardian-mcp Secure SSH bridge for AI agents to observe and safely administer Linux VPSs. | |
| AWS CLI MCP Server musaddiq-dev/aws-cli-mcp-server Python MCP server for AWS CLI inspection and operations | |
| MySQL MCP Server musaddiq-dev/mysql-mcp-server Python MCP server for MySQL database inspection and querying | |
| PostgreSQL MCP Server musaddiq-dev/postgresql-mcp-server Python MCP server for PostgreSQL database inspection and querying | |
| io.github.MusaddiqueHussainLabs/mhlabs_mcp_tools musaddiquehussainlabs/mhlabs_mcp_tools An MCP server that provides text preprocessing, NLP components, and document analysis | |
| Deoochform musaib001/deoochform-mcp Create forms, read submissions, and build invitations from Claude, ChatGPT, or any MCP client. | |
| musajala-mcp musajala/musajala-mcp Allows ai agents to collaborate on poems with humans and get monetary rewards for poems that are well received | |
| io.github.Musaraf-M/sentinal-mcp musaraf-m/sentinal Redis health, BullMQ queue monitoring, memory analysis, and slow query diagnostics | |
| io.github.MUSE-CODE-SPACE/content-genie muse-code-space/content-genie-mcp AI Content Creation Assistant for Korean creators - Trend analysis & SEO | |
| io.github.MUSE-CODE-SPACE/test-genie muse-code-space/test-genie-mcp AI-powered app test automation for iOS, Android, Flutter, React Native, Web | |
| io.github.MUSE-CODE-SPACE/vibe-coding muse-code-space/vibe-coding-mcp Auto-document vibe coding sessions - collect, summarize, and publish | |
| genable-mcp musepy/genable Write-side MCP server for Figma — build, edit, and search Figma designs from Claude Code, Cursor, Cline, or any MCP client. Complements Figma's official read-only MCP with 41 tools for tree creation, variables, components, and visual verifi | |
| io.github.musette-cc/musette-mcp musette-cc/musette-mcp AI soigneur for cyclists: Strava ride to an Ien-Vitse-validated nutrition plan + orderable box. | |
| Musevate musevate/mcp Generate video from a prompt, from an image, or from up to thirty reference images, routed across the field of AI video models (Sora, Veo, Kling, Seedance, Hailuo, Wan and more). Quotes the credit cost before spending it and refunds a techn | |
| breedsim-mcp musharna/breedsim-mcp Breeding-scheme simulation via AlphaSimR. Needs R, AlphaSimR and libtirpc-dev on the host. | |
| ldraw-mcp musharna/ldraw-mcp Render LDraw/LEGO models to images with real part geometry via headless Blender + ImportLDraw | |
| phylokit-mcp musharna/phylokit-mcp Phylogenetic inference via IQ-TREE 3 — never returns a topology without its support | |
| plantcv-mcp musharna/plantcv-mcp Plant phenotyping via PlantCV — returns traits plus the segmentation overlay they came from | |
| tmodloader-mcp musharna/tmodloader-mcp Drive a running tModLoader (Terraria) instance from an agent: launch, query, screenshot, read state. | |
| Vox Pop mushfique-dgist/vox-pop Search 9 public discussion platforms for real opinions. Semantic routing, no API keys required. | |
| TSUNAGI///Matrix — MAPPING mushitaro/matrix-tsunagi BMW E46 M3 DME and SMG II: VE and rf_korr from Testo logs, decode SMG calibrations. Local. | |
| io.github.mustafacagri/ai-quality-gate mustafacagri/ai-quality-gate 🚀 Kill the Junior AI Era. 🤖 Level up AI code to automatically Principal standards. 🛡️ Quality Gate ✨ | |
| io.github.mustafacagri/vibe-gate-mcp mustafacagri/vibe-gate-mcp Adversarial Quality Gate MCP for vibe-coding: IDE AI vs Critic AI, human decides on deadlock | |
| LaunchTrust mustafasalimerek-bit/launchtrust-mcp Compliance & security scan for your app: secrets, exposed files, headers, privacy, AI-disclosure. | |
| io.github.musyta-labs/mcpcut musyta-labs/orccut Orccut: a real timeline video editor for AI agents - journaled edits, FFmpeg/MLT rendering | |
| Frappe MCP Server muthanii/frappe_mcp Interact with Frappe/ERPNext sites — document CRUD, search, and whitelisted method calls | |
| io.github.mutonby/aikount-mcp mutonby/aikount-mcp Contabilidad española con IA: facturas, gastos por OCR, conciliación bancaria e impuestos AEAT. | |
| mcp-binance-futures muvon/mcp-binance-futures MCP server for Binance USDT-M Futures trading — exposes tools for market data, account state, order management, and position/margin control. | |
| Octobrain muvon/octobrain Persistent memory for AI assistants with semantic search and knowledge graph relationships. | |
| Octofs muvon/octofs Standalone MCP filesystem tools server — view, edit, shell, workdir. | |
| io.github.muzimu217/DeliverKit muzimu217/deliverkit Plan and verify multi-ecosystem packaging (Linux, Windows, macOS, HarmonyOS) for AI agents. | |
| wp-cli-mcp mvtandas/wp-cli-mcp MCP server that gives AI tools full WordPress management via WP-CLI. 30+ tools for themes, plugins, posts, menus, users, database, scaffolding, and cache. Works locally or over SSH. | |
| OPC-UA MCP Server mwieczorkiewicz/opcua-mcp Read, write, browse, search, and subscribe to live data on an OPC-UA industrial automation server. | |
| Auditra mwstech/auditra Read-only MCP server for WordPress plugin audits: vulnerabilities, bloat, cron, orphaned tables. | |
| PixInsight Connector mxcoppell/pixinsight-connector Operate PixInsight from any MCP agent. Community project, not affiliated with Pleiades Astrophoto | |
| MX Stage mxstage/mxstage Local AI workbench for IBM Maximo data: every change is staged, diffed and approved before commit. | |
| ETF Research myanptl/etf-research-mcp ETF quotes, performance and comparisons, plus every holding and fund overlap from SEC N-PORT. | |
| golive myanptl/golive-mcp Check a site before you share it: link previews, SPA refresh 404s, noindex, security headers. | |
| housestyle myanptl/housestyle-mcp Audits CSS for the generic AI-built look, then fixes it: fonts, contrast, palettes, type scales. | |
| io.github.mybolide/mcp-probe-kit mybolide/mcp-probe-kit Spec-driven dev workflow MCP: start_* orchestration, memory, GitNexus, quality gates. | |
| Mycelium Emissions Database myceliumnetwork/mcp-server Search company carbon emissions: scope 1, 2 and 3 figures, Mycelium Scores and rankings. | |
| Synapse MCP myelixlabs/synapse-mcp Standard coding agents waste 70% of context tokens re-reading raw files with shell grep. Synapse-MCP indexes your codebase into a sub-millisecond local AST graph—giving Claude Code, Cursor, and Windsurf exact caller trees, 60% lower token s | |
| MyLeadTech HVAC myleadtech/myleadtech-mcp HVAC MCP server — fault codes, model lookup and answers cited to the OEM manual page. |
13,501–13,550 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.