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 |
|---|---|
| NOAA Tides and Currents ryancardin15/perigee-tides NOAA tides and currents: water levels, tide predictions, currents, met data, flooding, sun and moon | |
| Sourced ryancodrai/sourced Source code search for every package on PyPI and npm. | |
| Peptide Library ryandelauz/peptide-library-mcp Peptide research profiles, evidence by tier, comparisons and educational content. No dosing. | |
| aus-accounting-mcp ryanduguid/australian-accounting Reviews, 14 bounded tax and super worksheets, cited retrieval from your local Markdown. Not advice. | |
| io.github.RyanJamesStewart/prompt-time ryanjamesstewart/prompt-time Claude Desktop reminders for Windows. Survives MSIX boundary; persists across restarts. Zero deps. | |
| io.github.RyanKramer/autorank-mcp ryankramer/autorank-mcp Technical SEO tools for AI agents: structured data, meta tags, robots, SERP truncation. No API key. | |
| io.github.RyanKramer/pixelpanda-mcp ryankramer/pixelpanda-mcp 33 image tools: free local editing, AI upscaling, background removal, and product photos | |
| io.github.RyanKramer/rankedtoday-mcp ryankramer/rankedtoday-mcp League of Legends math for AI agents: MMR estimation, climb projections, KDA, hours. No API key. | |
| io.github.RyanKramer/shippost-mcp ryankramer/shippost-mcp Twitter/X tools for AI agents — read timelines, post tweets, search, and engage | |
| io.github.RyanKramer/summitflow-mcp ryankramer/summitflow-mcp Grant management for AI agents: deadlines, business-day math, budgets, in-kind value. No API key. | |
| io.github.RyanKramer/wisegrid-mcp ryankramer/wisegrid-mcp Read and write WiseGrid sheets, rows, columns and reports from any AI agent. | |
| io.github.ryanmat/logicmonitor ryanmat/mcp-server-logicmonitor LogicMonitor API integration with 167 tools for alerts, devices, dashboards, and more. | |
| Sheriff ryansmith4/sheriff-mcp MCP server for fixing static analysis issues from SARIF reports with AI agents | |
| AgentTakt ryoohshima/agenttakt Review, edit, and approve AI agent task plans in a ComfyUI-style visual node editor in your terminal | |
| io.github.ryotaro-tanaka/mcp-oss-onramp ryotaro-tanaka/mcp-oss-onramp MCP server to scout beginner-friendly OSS issues with high precision using GitHub GraphQL | |
| Rystic rystic-inc/rystic Start, seed, clock, inspect and diff Rystic API simulators from your agent. | |
| SNHP — negotiation rules your AI can't break ryuxik/snhp Turn a seller's offer into negotiation rules and draft replies to buyers inside them. | |
| Apex by LeadShark — discovery rzere/linkedin-mcp No-auth discovery endpoint for Apex by LeadShark — governed LinkedIn hands for AI agents. | |
| io.github.rzlco666/mcp-sql-rust rzlco666/mcp-sql-rust Token-efficient MCP server for MySQL, PostgreSQL, and SQLite | |
| io.github.rzlco666/strut-stack-sql rzlco666/strut-stack-sql Token-efficient MCP server for MySQL, PostgreSQL, and SQLite | |
| fxray s-curvelabs/fxray Power Apps via pac: solutions, canvas Power Fx source, Dataverse metadata, FetchXML, gated imports. | |
| letin: Power Query (M) s-curvelabs/letin Inspect, refactor, lint, run and version Power Query (M) in Excel workbooks and Power BI projects. | |
| longpath s-curvelabs/longpath Read-only P6 / MS Project schedule analysis: CPM, float, DCMA 14-point, logic checks, S-curves. | |
| sqlglass s-curvelabs/sqlglass SQL Server / Azure SQL for agents: real schema, lint, read-only runs, plans, write previews. | |
| Actual Budget MCP Server s-stefanov/actual-mcp MCP server exposing Actual Budget accounts, transactions, budgets and reporting to LLM assistants. | |
| Living Docs s2bomb/living-docs-connect Create and improve live, shared interactive documents with your agent. | |
| io.github.S2TConsulting/accelerators s2tconsulting/accelerators-mcp 36 tools for AWS infrastructure, security compliance, AI workflows, and ACI governance. | |
| io.github.S2thend/cursor-history s2thend/cursor-history-mcp MCP server for browsing, searching, exporting, and backing up your Cursor AI chat history | |
| AgentTasker MCP Server s3brr/agent-tasker-mcp Minimal stdio MCP server for parallel task execution by AI agents. | |
| S3eidat Tools s3eidat/s3eidat-tools-mcp Free, private PDF, image, text, developer, calculator and QR tools. Runs locally; no uploads. | |
| DaVinci Resolve Lua MCP saadk408/davinci-resolve-lua-mcp Control the free edition of DaVinci Resolve 21.1 from Claude through a Lua script inside Resolve. | |
| HardwareMCP saadvz/hardwaremcp-mcp Find MCP servers for ESP32, Arduino, 3D printers, Home Assistant, cameras and other hardware. | |
| mcp-trust saagpatel/mcp-trust Check the danger grade of any public MCP server before you connect. | |
| mcp-audit saagpatel/mcpaudit Scan, enumerate, and risk-score every MCP server configured on your machine. | |
| mcpforge saagpatel/mcpforge Generate complete, tested FastMCP 3.x MCP servers from one plain-English sentence. | |
| saagarpatel.dev Portfolio saagpatel/portfolio-mcp Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless. | |
| JustCall MCP Server saaslabsco/justcall-mcp-server JustCall MCP Server enables LLMs and AI agents to make voice calls and send SMS via JustCall APIs. | |
| SkeletIQ sabhahith-works/skeletiq-mcp Hand a released SkeletIQ architecture to a coding agent: brief, build order, drift check. | |
| Sable Platform + HyperDX Observability sable-inc/anvil Manage Sable AI voice agents, query HyperDX logs and metrics, and deploy — all from your IDE | |
| Redra sacrosaunt/redra Search current class-action settlements and identify possible matches using structured filters. | |
| graphrag-ts citation provenance sadofriod/graphrag-ts Source-tiered retraction and citation judgments for DOIs; abstains when evidence is thin. | |
| WooCommerce MCP sadrmanesh/woocommerce-mcp Manage WooCommerce stores: products, orders, customers, coupons, webhooks, and analytics. | |
| ripsem sadykhzadeh/ripsem Offline code search for agents: find code by identifier, error message or plain description | |
| io.github.saeedmsdi-ugchooks/mcp-server saeedmsdi-ugchooks/mcp-server UGCHooks MCP: turn product links into TikTok and Reels post batches; read hooks and captions. | |
| Jobinja Employer saeedsepehr/jobinja-employer-mcp Review and shortlist resumes received in the Jobinja employer panel with low token use. | |
| Deploy to Agents saezbaldo/deploytoagents Audit agent-distribution surfaces and create an evidence-based distribution plan. | |
| ai.safe4/safe4 safe4ai/safe4-mcp Tests an AI agent's purchase against the task it was given. Paid per call in USDC via x402. | |
| SafeDep Vet MCP safedep/vet Protect your AI agents and IDEs from malicious open-source packages. | |
| SafeSwapGlobal Crypto Swap Quotes safeswapglobal-prog/safeswapglobal-mcp Real-time non-custodial crypto swap estimates and on-chain routing across 240+ pairs. | |
| Dora AI Video saga-labs/dora-mcp AI video and images from a photo or text in ChatGPT and Claude. Seedance 2 Mini by default. |
16,301–16,350 of 50,909
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.