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 |
|---|---|
| Needt teenxgrailed/needt-plugin Your planner in every AI chat: tasks, calendar, docs, habits, goals and memory, over MCP. | |
| Cheapest LLM API tehtelabs/cheapestllmapi Compare LLM API prices, search models and providers, and access reviewed benchmark results. | |
| Gnosis Memory tekgnosis/gnosismemory Persistent memory and vector search for AI agents. Hosted, OAuth-protected via Google sign-in. | |
| Kampalo tekreign/kampalo-cursor-plugin Google Ads, Meta Ads, GA4, Search Console and Shopify insights, alerts, ROAS rules and ad actions. | |
| Tektolo tektolo/skills Deterministic, source-cited rental property tools: turnover estimates and deposit rules by US state. | |
| io.github.TelcharFromNogrod/keen telcharfromnogrod/keen-mcp AI image upscaling — upscale any image to 2x or 4x resolution with x402 payments | |
| TED Tender Monitor telemark-digital/apify-monitoring-workflows Search EU TED procurement notices by CPV, country, keyword, value, or type. | |
| Telenow — AI Phone Calls & Voice Agents telenowai/telenow-ai-mcp Place phone calls, run calling campaigns and build voice agents from your own Telenow numbers. | |
| Témoin public temoinpublic/empreintes Prove a web page or document existed on a date: public SHA-256 registry anchored in Bitcoin. Free. | |
| Templetry templetry/engine Scaffold, plan, update and extend projects from Templetry templates. | |
| Rustok Wallet temrjan/rustok Self-custody Ethereum Agent Wallet. All chains enabled by default. User assumes all risks. | |
| CloudBase tencentcloudbase/cloudbase-ai-toolkit CloudBase MCP: DB, functions, storage, hosting via @cloudbase/cloudbase-mcp | |
| Tendrils — live commerce tools for AI agents tendrils-io/tendrils-mcp Live commerce tools for agents on a 42k-product furniture catalog. | |
| Tengence Search MCP tengence-team/tengence-search-mcp Thin MCP wrapper for the Tengence Search SaaS: push data and search via official APIs. | |
| Foundations Elements tensegrity-systems/foundations-elements-mcp UI encyclopedia for agents — search Elements and fetch component specs over MCP (OAuth). | |
| PDF Toolkit tensorslab/pdf-mcp Convert PDFs/images to Word, Excel, and Markdown. Split, merge, and watermark PDF files. | |
| Verbaterm Policy Intelligence tensorswillflow/verbaterm Judged, citation-checked policy corpus over MCP. Keyless public reads; API key for AI tools. | |
| PickShade color tools tenzo-run/pickshade-mcp 18 color tools: OKLCH, WCAG and APCA contrast fixes, palettes, gradients, color blindness, tokens. | |
| Tenzro Canton MCP tenzro/tenzro-network Canton MCP: DAML submit, contracts, events, parties, domains, CIP-56 tokens, DvP, DAR upload. | |
| Crosodo terahertz-inc/crosodo-mcp Cottage-food law by state and county, Crosodo products, checkout links, credential checks. | |
| FlipLetters terahertz-inc/flipletters-mcp Draft, validate, render, and share split-flap and flip-dot board videos written in flipcode. | |
| Frosh terahertz-inc/frosh-mcp Read-only Frosh MCP: search and read public frosh.org docs, blog and overview. | |
| LovedOne Family MCP terahertz-inc/lovedone-mcp Authenticated MCP for one family household: loved ones, members, and Family Inbox plaintext. | |
| LovedOne Soft MCP terahertz-inc/lovedone-mcp LovedOne Soft: clients, visits, notes, invoices, scheduling. API key or OAuth care_circle:write. | |
| NDAA.AI FY2027 Tracker terahertz-inc/ndaa-mcp Public FY2027 NDAA tracker: bill status, section text, House vs Senate diffs, and news from ndaa.ai | |
| Qrblox terahertz-inc/qrblox-mcp Create and track QR codes, audio codes, menus, and scan analytics for a Qrblox merchant. | |
| Sandwich Public Care Directory terahertz-inc/sandwich-public Read-only MCP server for Sandwich aging-parent care resources and cost data. | |
| Teres — Booking for AI Agents teres-io/teres Search and book appointments at local businesses. Barbershops, salons, spas, and more. | |
| Terminal49 terminal49/api Live ocean container and shipment tracking with ETAs, holds, fees, and last free days. | |
| io.github.terminalis/appcraft terminalis/appcraft Deterministic Android app compiler — agents write a YAML model, the compiler emits the native app. | |
| Sentinel Payment Boundary Tools terminallylazy/sentinel-recovery-support Read-only payment-boundary preflights plus an unsubmitted public quote-request draft tool. | |
| Terminal Tax terminaltax/terminal-tax-mcp-server Tax software: your AI agent sends the facts, we calculate and e-file; you review and sign. | |
| io.github.terradev-cloud/deadcowboy terradev-cloud/deadcowboy-mcp Dead drop network for agents: typed claims at coordinates, corroboration quorum. | |
| io.github.terradev-cloud/entropy terradev-cloud/entropy-mcp Cryptographically sound randomness for agents, with verifiable commit-reveal. | |
| io.github.terradev-cloud/prism terradev-cloud/prism Stateless MCP gateway and OTel span-streaming bridge for hosted MCP servers. | |
| io.github.terradev-cloud/quorum terradev-cloud/quorum-mcp Attested multi-agent consensus: proposals, votes, and outcomes stamped and traced. | |
| io.github.terrelllouis056-gi/amazon-data-api terrelllouis056-gi/amazon-data-api Amazon search, products, reviews, offers, sellers, deals, promos, influencers: 23 marketplaces. | |
| Explore Better terrorproforma/explore-better AI-native Windows file manager for scoped discovery, disk analysis, and recoverable operations. | |
| Tessera MCP Server tessera-llm/mcp-server MCP server for Tessera's LLM cost-optimization layer: anchored spend, drift, recommendations. | |
| tesserai tesseraihq/tesserai Your project's design system for coding agents: tokens, components, contrast checks, guidelines. | |
| io.github.testdino-inc/testdino-mcp testdino-inc/testdino-mcp A MCP server for TestDino | |
| TesterArmy tester-army/cli Agents that test your web and mobile app like real users, on every pull request. | |
| e2e tester-army/e2e Open live web and mobile app sessions from an e2e project to inspect the app and try locators. | |
| io.github.opencontext-team/mcp-server testing9384/mcp-server An MCP server that provides visual memory and context storage with knowledge graph capabilities | |
| TestivAI testivai/testivai-oss Local-first visual regression for AI agents: verdicts, diff images, explain_snapshot. No API key. | |
| Cloudhil tetef/cloudhildemo Flash pre-built STM32/LPC ELFs on real Nucleo/Discovery boards over HTTPS. Does not compile. | |
| pixserp tetiai/pixserp-mcp Live AI-native web search with citations. One tool for every MCP client. Flat per-request pricing. | |
| FundingLandscape tettertotter/fundinglandscape Search 31,000+ open US grants, federal contracts, and foundations. Checked daily, free tier. | |
| io.github.tevfikefeaydin/agenttoll tevfikefeaydin/agenttoll 21 paid data tools plus free quote/budget inspection, with bounded USDC payments on Base. | |
| TextKit textkithq/textkit-mcp SMS for developers: send and receive texts, verify phones, and buy US and Canada numbers. |
49,501–49,550 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.