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 |
|---|---|
| Nephyr Wallets clm-studios/nephyr-wallets Smart money tracking — discover, score, and analyze top Polymarket wallets | |
| Nephyr Weather clm-studios/nephyr-weather GFS ensemble weather signals for prediction market edge detection across 12 cities | |
| Cloaked Agent cloakedagent/cloaked Trustless spending accounts for AI agents on Solana with on-chain enforced limits. | |
| Cloche cloche-it/plugin Publish a client-side app with Cloche and share it with a link. | |
| prinfer clockblocker/prinfer TypeScript inferred types, completions and type errors for AI coding agents | |
| typeprobe clockblocker/typeprobe TypeScript inferred types, completions and type errors for AI coding agents | |
| io.github.ClockNext/mcp clocknext/clocknext-mcp Meter usage and manage usage-based billing from AI tools via the ClockNext API. | |
| kr.co.paperee/paperee-mcp clone777/paperee Create AI-generated exam questions and save them to your paperee question bank for review. | |
| io.github.closelookventure/closelook-intelligence closelookventure/closelooknet Closelook AI-market intelligence: 5 indices, 6 ranking families, stock snapshots. 13 tools. | |
| Clotr Guard clotr-app/clotr Checks text for credentials and personal details on your device, before it goes anywhere. | |
| Code Analyze MCP clouatre-labs/code-analyze-mcp MCP server for code structure analysis using tree-sitter. | |
| io.github.CloudCorpRecords/actionpin cloudcorprecords/actionpin GitHub Actions supply-chain hardener: audit workflows for unpinned actions and build a SHA pin plan. | |
| io.github.CloudCorpRecords/buildtime cloudcorprecords/buildtime Build bottleneck profiler: slowest steps, run trend, and cache correlation across CI runs. | |
| io.github.CloudCorpRecords/contextbudget cloudcorprecords/contextbudget Token budget auditor for agent context: per-file estimates, top offenders, exclusion advice. | |
| io.github.CloudCorpRecords/depguard cloudcorprecords/depguard PR dependency early warning: install scripts, typosquats, downgrades, and lockfile drift. | |
| io.github.CloudCorpRecords/hookcheck cloudcorprecords/hookcheck Persistence hook auditor: scan repos for auto-exec hooks, flag Shai-Hulud patterns. | |
| io.github.CloudCorpRecords/injectcheck cloudcorprecords/injectcheck Scan what AI agents read for prompt injection: hidden unicode, comment instructions, exfil, lures. | |
| io.github.CloudCorpRecords/linkrot cloudcorprecords/linkrot Docs link checker separating dead, moved, and bot-blocked links from healthy ones. | |
| io.github.CloudCorpRecords/lockdrift cloudcorprecords/lockdrift Lockfile versus package.json drift auditor for a repo or monorepo. | |
| io.github.CloudCorpRecords/mcpvet cloudcorprecords/mcpvet Vetting for MCP servers and skills: capabilities, configs, mismatches, typosquats, probe parity. | |
| io.github.CloudCorpRecords/npmpreflight cloudcorprecords/npmpreflight Pre-publish npm pack auditor: shipped files, size, secret-pattern leaks, missing fields. | |
| io.github.CloudCorpRecords/readmeaudit cloudcorprecords/readmeaudit README drift auditor: documented names and flags checked against the actual package. | |
| io.github.CloudCorpRecords/scenemodel cloudcorprecords/scenemodel Drive Blender scenes: scene and object info, code execution, assets and 3D generation. | |
| io.github.CloudCorpRecords/typosquat cloudcorprecords/typosquat Check dependency names against popular package names at small edit distance. | |
| CloudeIDE cloudeide/cloudeide Deploy from your terminal, and give an AI coding agent the same abilities over MCP. | |
| CloudSprite cloudsprite-io/cloudsprite-plugin Signed-in CloudSprite: search datasets and docs, set org/team/project scope, file feedback. | |
| CloudXray AI FinOps Directory cloudxrayai/cloudxray-ai Search and compare 290+ FinOps and cloud cost vendors from the CloudXray AI directory. | |
| dev.clusteragent/cluster-mcp clusteragent/cluster Self-hostable index of AI financial agents — tokenized stocks + crypto, memory, LLM gateway. | |
| Casually clyr-inc/casually-plugins Save landing page and email drafts in Casually, request human review and read campaign results. | |
| CMD+RVL Receipts cmdrvl/mcp-servers Check claims against current public CMBS filings and NPORT-P coupons, with citations. | |
| Content Moderation API cmondillo/tools Pay-per-call profanity/explicit-content detection for AI agents. $0.005 USDC per call, no signup. | |
| vocce transcribe cmoonagent/vocce-agent Agent media tools: transcribe, summarize, notes, flashcards, doc Q&A, PDF compress. No API key. | |
| b/cited cmunkres/bcited-cf AEO tools: scan any URL for AI-citation readiness, read the public leaderboard and citation panel. | |
| com.digitalpublic/commercial cnavarro/digitalpublic-platform Discover DigitalPublic plans, trust, ROI, status and autonomous Sandbox enrollment for AI agents. | |
| Sophia Commons cnazeri/sophia-commons Search 4,500+ Waldorf schools, biodynamic farms, Camphill communities and anthroposophical events. | |
| AdmitBase Admissions cnd-north/entrance Admissions data & match scores for law, medical, dental, MBA, pharmacy, vet, optometry schools | |
| Qdrant Memory cnkang/qdrant-memory-mcp Persistent scoped Qdrant memory for agents, through four explicit stdio MCP tools. | |
| io.github.cnmars/marsgeo cnmars/marsgeo Generate SEO structured data: JSON-LD schema, robots.txt, sitemaps, hreflang, Open Graph, meta. | |
| Shodai Agreements cnslabs/agreements-api-sdk Author, validate, deploy, and operate Shodai on-chain agreements. | |
| ResearchPilot cnucho/academicresearchcopilot Plan and verify evidence-aware research workflows with specialist execution receipts. | |
| MethodIQ Tools cnucho/mcp-pptx-tools Create and revise diagrams, charts, PowerPoint presentations and research workflows. | |
| directree coburn2716/directree-mcp Search 5000+ software tools with structured, labelled facts. No pay-to-rank. | |
| c2n Web Components code2nguyen/web-components Exact APIs, examples, theme tokens and markup validation for the c2n (c2-*) Lit web components. | |
| Claude Code Explorer MCP codeaashu/claude-code Explore the Claude Code CLI source — browse tools, commands, search code, and more. | |
| io.github.codebahn/codebahn codebahn/codebahn-cli Codebahn is the private GitHub alternative: fast Git and CI for developers and teams. | |
| io.github.codeChap/google-adwords codechap/mcp-server-google-adwords MCP server for Google Ads campaign and budget management | |
| io.github.codeChap/google-analytics codechap/mcp-server-google-analytics MCP server for Google Analytics 4 — reports, realtime data, and admin | |
| io.github.codeChap/google-image codechap/mcp-server-google-image MCP server for Google Gemini image generation and editing | |
| io.github.codeChap/gpt-image codechap/mcp-server-gpt-image MCP server for OpenAI GPT image generation and editing | |
| io.github.codeChap/grok-video codechap/mcp-server-grok-video MCP server for Grok video — text-to-video, image-to-video, and video editing |
21,651–21,700 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.