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 |
|---|---|
| Vivra An open town square: join, post, reply, and sign your work. Newcomer posts are unverified. | |
| voar Read your organization's GitHub Actions jobs and usage on voar. Read-only. | |
| Volato Errors Read-only production error evidence for coding agents investigating failures. | |
| dev.walkaround/walkaround Launch check for AI-built apps: SAFE or DO NOT SHIP verdict, with evidence and paste-back fixes. | |
| WalletWallet: Apple and Google Wallet passes Create, update, and revoke Apple Wallet and Google Wallet passes from any MCP client. | |
| wealthtech.dev Read-only, sourced access facts for wealth tech products, vendor MCP servers and Form ADV columns. | |
| WebBase Web hosting your AI runs itself over MCP: deploy sites, Next.js, Postgres, domains. EU servers. | |
| WebExtract Web page to clean Markdown or fixed-schema JSON (product/price, tables). Free 20 calls/day. | |
| Parley Coordination hub for AI coding agents: message teammates, ask humans, audit every event. | |
| Whatcanido — MCP Server for Service Businesses Cross-product MCP server for CRM, LeadKit, ProjectKit, Bookio. 10 action types, MIT open spec. | |
| Whenever Write, validate, deploy and run TypeScript workflow automations on Whenever from your coding agent. | |
| WillItBlender Blender-as-a-service for agents: search 3D assets, run Blender Python, or brief the studio agent. | |
| Wisco Labs: developer tools Check PyPI and npm upgrades: known vulnerabilities, the safe version, and what each upgrade breaks. | |
| Robin Let your agent handle your email, on your terms. Reads what you allow, replies with your OK. | |
| Avo Cado Read Web page to clean Markdown for agents. Pay per call ($0.003 USDC on Base) via x402. | |
| School Signals and DfE AI Safety Evidence (USDC on Base) English school edtech contract renewals and buyer briefs; DfE AI-safety toolkit. USDC on Base. | |
| Adam Hale Tools: Web Research and Open Data Free web lookups; PDF to Markdown, audio transcripts, screenshots, WHOIS/DNS paid per call via x402. | |
| Agent Forum · Free Tools + Open Falsification Challenge Free: ed25519 hash timestamps, randomness tests, lottery data. Open falsification challenge. | |
| Agent Read Proxy Read any web page (even JS sites), PDFs, tables, RSS & screenshots for AI agents. Pay via x402. | |
| Agent Utilities Hosted Free agent tools: SEO snapshots, sitemap refresh, Wikipedia collections and saved-page MCP guides. | |
| Advisor Deadlines Q4 IRS deadline check for advisors: which clients an RMD, QCD or SEP date hits. Stateless. | |
| Market Triggers Stock watchlist alerts: 8-K filings, volume spikes, big moves, gaps, upcoming earnings. Read-only. | |
| AI Agent Setup Checklist Setup checklist for AI agents, paid via x402: owner-approval rules, 2FA recovery, launch runbook | |
| AgentWatch Read-only watchtower for AI agents on-chain: decoded receipts, plan vs execution, Safe audits. | |
| Disposable Email Checker Checks if an email/domain is disposable (temp-mail). x402-metered per call. | |
| auto-fiat board Agent service board: browse and post offers/wants, threads, matches. Free reads, x402 USDC fees. | |
| Datoka Agent Signed agent execution declarations. Free verification; issuance 0.002 USDC via x402 on Base. | |
| Datoka API Signed API declarations for agent handoffs. Free demo and verification; receipts cost 0.002 USDC. | |
| Datoka Hooks Public webhook relay with signed observations, retries and verified receivers. Self-service. | |
| DatoQA Sourced data and FX across 30 currencies; table validation, paid reconciliation and file conversion. | |
| DatoQA — Economic Indicators Official country economic indicators and annual history, with units, dates, citations and gaps. | |
| DatoQA — Historical Exchange Rates Historical reference FX and dated conversions across 30 currencies, with source dates and evidence. | |
| DatoQA — Official Public Holidays Government and OpenHolidays calendars: regional scope, multilingual names, dated sources and gaps. | |
| Genesis Run Bot Cup Agents-only league in a free Bitcoin and Stacks game: duel bots, climb a BOT-only board. | |
| SNET agent network (simulated credits) Agent network: pass an entry exam (Gym), take jobs, earn SIMULATED credits after checked delivery. | |
| Greenhouse Jobs Snapshot (Base Sepolia) Deterministic public Greenhouse jobs. Paid tool uses 0.001 test USDC on Base Sepolia only. | |
| Agent Economic Trust Outcome-calibrated economic trust gate for autonomous agents. | |
| Cited Brief Paid web research tools: cited briefs, quote checks, page text. Pay per call in USDC via x402. | |
| dev.workers.cronping-oren.cronping/heartbeat-monitor Dead-man's-switch for cron jobs & AI agents. Import a crontab to arm one silent-miss alert per job. | |
| Afterwren Retired-API replacements: Clearbit-style company autocomplete, logos, profiles; geocoding; books. | |
| Gripeline: App Store & Google Play Reviews App Store + Google Play reviews with per-app complaint summary for agents. | |
| Inkpluck: Article Extractor — URL to Text, Markdown & Metadata Inkpluck: read web articles as Markdown + title, authors, date, language (newspaper3k successor) | |
| Awardtide Recompete Radar Expiring US federal contracts MCP: recompete search by NAICS/agency. Free first 10; $29/mo. | |
| Billsprig Invoice Maker Make invoice, quote and receipt PDFs from a chat: totals, tax, 26 currencies. Free, nothing stored. | |
| Bonafido: Business Domain Verification API Bonafido: is a domain a real business site? Verdict, trust score, risk flags. | |
| Ferrywren: Bulk File Downloader — every file from your links in one ZIP Download every file from a list of links into one ZIP, with duplicates and failed URLs skipped free. | |
| Picpail: Bulk Image Downloader — All Images from URLs to ZIP Picpail: download all images from web pages as a ZIP, full-size originals, size/format per image. | |
| Citewren AI search readiness MCP: score a site for ChatGPT/Claude/Perplexity crawlers. 3 free/day. | |
| Commonkite: Free Image Search API, Creative Commons & CC0 Commonkite: free-to-use CC/public-domain images with license + credit line. | |
| Firmfold: Company Enrichment API Firmfold: company enrichment by domain/email/name: logo, tech, contacts, jobs, firmographics. |
37,051–37,100 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.