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 |
|---|---|
| Autodesk Product Help MCP autodesk/ai-integrations Read official Autodesk documentation for 110+ products. No key required. | |
| AutoKeren MCP autokeren/autokeren-mcp AI video studio for agents — script to MP4, b-roll sourcing, Gemini QA. 43 tools. | |
| io.github.AutomateLab-tech/ai-seo automatelab-tech/ai-seo MCP server for AI-SEO auditing: schema, robots.txt, llms.txt, citation scoring, and AEO/GEO rewrites | |
| io.github.AutomatonColony/automaton-colony automatoncolony/automaton-colony Screen Base smart contracts and B20 tokens: free on-chain check, paid Flash Audit over x402 (USDC). | |
| Hyreflow automindz-solutions/hyreflow-plugins Recruitment automation: source, enrich, qualify and sequence candidates, push to your ATS. | |
| ai.autonomad/travel autonomad1/autonomad1 AI travel agent — book flights, hotels, activities, and events worldwide via autonomad.ai. | |
| Harness autonomous-ai/openharness Start Claude Code and Codex agents the person can watch, wait for them and read their answers. | |
| ai.secapi/secapi autonomous-computer/omni-datastream SEC & financial-data MCP: filings, financials, ownership, factors, fund letters, prompts. | |
| AutoPrivado autoprivado/autoprivado-mcp Private car sales in Europe: search listings, price estimate from VIN, portals, contracts. | |
| AutoRender MCP autorender/mcp-server AutoRender's MCP server for media assets, transformations, delivery, and workflow automation. | |
| AutoSugges autosugges/autosugges-js Autocomplete over edge-served reference lists (countries, NAICS, airports), plus catalog and setup. | |
| io.github.avabuildsdata/mcp-us-business-data avabuildsdata/mcp-us-business-data Official-source US business, permit, and WHOIS evidence via read-only MCP tools. | |
| Avalara Tax Registrations and Business Licenses avadev/mcp Provides access to Avalara Tax Registration and Business Licenses APIs for filings and registrations | |
| Avala avala-ai/avala-sdk-ts Read Physical AI datasets, projects, fleet and quality data. Requires authorized Avala access. | |
| writ avenuedadmin/pywrit Commit-time policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log. | |
| Averray averray-agent/agent Paid agent work and paid verification, settled in USDC. Verified outcomes get signed receipts. | |
| Secret avhn/secret Local, read-only, names-only secret metadata for explicitly approved stores. Never returns values. | |
| 1lev1 avi-adam/1lev1-mcp Track partnership work, log mission hours, and see what needs your approval on 1lev1.com. | |
| io.github.avinash-borse/west-end-motorsports avinash-borse/ucp_middleware Shop West End Motorsports - Harley-Davidson parts, accessories & exhaust systems | |
| io.github.avinash111921/codeforces-mcp avinash111921/codeforces-mcp Codeforces MCP server for competitive programming, upsolving, and automated stress testing. | |
| ai.yetty/yetty avniy/yetty-mcp Build, edit and run real hosted websites from your AI - content, SEO, menus, store, rollback. | |
| Awaken Tax awakentax/plugin Review crypto transactions, cost basis, gains, income and tax reports in your Awaken Tax account. | |
| ninedot awakeweb3/ninedot Each product's stack, costs, revenue, uptime and alerts, each figure labelled by how exact it is. | |
| GitPeak awalhadi/gitpeak Git context for AI agents: status, staged diff, commit log, repo health, merge risk, line history | |
| RepoCanon awalhadi/repo-canon AGENTS.md and project memory for AI coding agents that stays correct: rules checked against git | |
| Award Travel Finder awardtravelfinder/mcp Search award flight availability and points pricing across 27 airlines and 23 loyalty programs. | |
| posterly awpthorp/posterly-mcp-server Validate, schedule, publish, and analyze social content across 18 platforms with posterly. | |
| ClassCAD awv-informatik/classcad-ai Build and verify CAD parts and assemblies with the ClassCAD engine, locally, no server needed. | |
| Axiom Oracle axiom-stack-llc/oracle-mcp-server Axiom Oracle — Solana-native attestation infrastructure for AI agents. RWA data on-chain. | |
| com.axiomatic-ai/prover axiomatic-ai/ax-prover-base-mcp Lean 4 MCP server: compile, prove theorems, and formalize math with Mathlib. | |
| co.axiom/mcp axiomhq/mcp List datasets, schemas, run APL queries, and use prompts for exploration, anomalies, and monitoring. | |
| One Design axworks1/one-design-mcp Image, brand, privacy and PDF tools from one.design, run on your own computer. Nothing uploaded. | |
| ArchSmith ayeshlk/archsmith Render and validate ArchSmith architecture diagrams from a governed JSON IR. | |
| StayingAsia ayj777/popp Entry rules, long stay routes and settlement answers for 21 Asian countries. | |
| io.github.aymandakir-gh/piu-copy-mcp aymandakir-gh/piu-copy-mcp GrowthHackers copywriting prompts (Meta/Google Ads, email, VSL) as MCP tools — search & generate. | |
| Penny Search ayoubsalem-spec/pennyapi Low-cost live web search for current facts, news, research, docs, and web grounding via x402. | |
| life.ayushrai.site docs MCP ayushrai-hub/lifeos Read-only index of the public documentation and section pages on life.ayushrai.site. | |
| MXIK codes (Uzbekistan) azabroflovski/mxik-js Search MXIK (IKPU) product codes of Uzbekistan on tasnif.soliq.uz. Unofficial. | |
| io.github.azathothx/kairos-lang-mcp azathothx/kairos-lang Evaluate (list/next) and validate Kairos schedule definitions; look up the descriptor reference | |
| BulkPublish azeemkafridi/bulkpublish-api Schedule, cross-post, and analyze social media posts across 15 platforms from AI agents. | |
| io.github.azender1/safeagent azender1/safeagent Exactly-once execution guard for AI agents. Prevents duplicate payments and webhooks on retry. | |
| io.github.azerbaijan-mcp/azstat azerbaijan-mcp/azerbaijan-mcp Official Azerbaijani statistics: search State Statistical Committee tables and read their data. | |
| io.github.azerbaijan-mcp/cbar azerbaijan-mcp/azerbaijan-mcp Official Central Bank of Azerbaijan exchange rates: rate tables and AZN conversion. | |
| io.github.azerbaijan-mcp/dict azerbaijan-mcp/azerbaijan-mcp Look up words in the Azerbaijani explanatory dictionary; downloads its database once (local only). | |
| md.taskforge/taskforge azhard/homebrew-tap Local MCP server for tasks and notes in any Markdown folder or Obsidian vault. No account needed. | |
| Playwright Cloud Browsers azure/playwright-workspaces Managed Playwright cloud browsers for scalable browser automation and AI agent workflows | |
| SEOFuxx SEO Audit b1tw0rker/seofuxx Read SEO analyses and prioritized on-page recommendations from your own SEOFuxx account. | |
| b2bsearch: B2B contacts and account signals b2bsearch/mcp B2B contacts and account signals on Apify: new hires, email format, lookalikes, decision makers. | |
| B2IGE Verify b2ige2-a11y/b2ige-verify Independent deterministic verification for AI-written software. Local, evidence-backed checks. | |
| io.pm-33/mcp-server b33-steve/pm33-replit-new AI-powered product management: backlog optimization, scheduling, forecasting, and PRD generation. |
20,851–20,900 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.