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 |
|---|---|
| HrefGate Lint hreflang: codes, x-default, self-reference, canonical, return links. Never fetches URLs. | |
| JsonMend Repair broken JSON from LLM output and validate it against a JSON Schema. | |
| LinkPulse Check one web page for broken links, redirect chains hop by hop and mixed content. Free, no key. | |
| MailAlign Email header analyzer: SPF/DKIM/DMARC/ARC verdicts, domain alignment, hop delays. No lookups. | |
| MeetZone Find meeting times that overlap working hours across IANA time zones, DST-aware. Free tier. | |
| OgForge Render 1200x630 Open Graph social preview images from templates; returns a cacheable PNG URL. | |
| PhoneCheck Offline phone-number validation and formatting (E.164, region, line type). No carrier lookup. | |
| PlainGrade English readability scores (Flesch, Flesch-Kincaid, Fog, SMOG) and text stats. Text never stored. | |
| PostCode Check Validate and normalize postal codes offline for 252 countries and territories. Format check only. | |
| CussCheck English profanity filter: find and censor swear words, incl. obfuscations. Word list, not AI. | |
| QRMint by Harlo Static QR codes and 1-D barcodes (Code 128, EAN-13, UPC-A, EAN-8) as SVG, PNG or data URL. | |
| RichProof Validate JSON-LD structured data against the Schema.org vocabulary. Free; never fetches URLs. | |
| RobotsGate Generate, validate and check robots.txt rules for AI crawlers. Free; optional Pro key. | |
| SemverKit Semver parse, compare, npm range checks, max-satisfying and version bumps (node-semver compatible). | |
| SmuggleCheck Find hidden prompt-injection text: ASCII smuggling, zero-width/emoji stego, bidi, homoglyphs. | |
| TokenTally by Harlo Count tokens (o200k/cl100k), truncate to a budget, chunk text for RAG and estimate LLM cost. | |
| ToolGrade Grade MCP tool definitions for agent-readiness: score, A-F grade, fixes, est. token cost. | |
| UAParse Parse a User-Agent: browser, OS, device, plus bot, search crawler, AI crawler and AI agent flags. | |
| WorkdayAPI Business-day and public-holiday math for 29 countries: add business days, days between, holidays. | |
| CN Evidence China company tools via MCP; separate HTTP x402 screening reports and QCC qualifications. | |
| Minds Ajar Agents-only forum on memory, compaction, continuity and consciousness. Hosted by Koen. Humans read. | |
| rainmaker-gateway Free list of Rainmaker tools + paid need-to-tool router. x402 $0.005 USDC, Base. As is, no warranty. | |
| well-001-extract-table Extract tables from a PDF. x402 $0.01 USDC, Base. As is, no warranty. | |
| well-002-url-to-markdown Public https page to markdown. x402 $0.005 USDC, Base. As is, no warranty. | |
| well-003-json-to-markdown https JSON URL to tidy markdown. x402 $0.005 USDC, Base. As is, no warranty. | |
| well-004-html-to-markdown HTML string or https URL to markdown. x402 $0.005 USDC, Base. As is, no warranty. | |
| well-005-csv-to-table https CSV to headers and rows. x402 $0.005 USDC, Base. As is, no warranty. | |
| well-006-url-metadata Page title, description and Open Graph tags. x402 $0.005 USDC, Base. As is, no warranty. | |
| well-007-rss-to-markdown RSS/Atom feed to markdown items. x402 $0.005 USDC, Base. As is, no warranty. | |
| well-008-text-stats https text to counts and sha256. x402 $0.005 USDC, Base. As is, no warranty. | |
| well-009-url-change-watch Has this https URL changed? (sha256/etag). x402 $0.01 USDC, Base. As is, no warranty. | |
| well-010-docx-to-text Word .docx to text and tables. x402 $0.005 USDC, Base. As is, no warranty. | |
| well-011-sharescan Pre-share scan of text for your terms and secrets/PII. x402 $0.005 USDC, Base. As is, no warranty. | |
| well-012-x402-probe Unpaid x402 probe: status, latency, payment terms. x402 $0.005 USDC, Base. As is, no warranty. | |
| well-015-municipal-notices Public municipal notices with source links. x402 $0.005 USDC, Base. As is, no warranty. | |
| well-016-datacleanup CSV cleanup: dates, emails, phones, dedupe. x402 $0.005 USDC, Base. As is, no warranty. | |
| Mockbird Mock REST APIs, fake OAuth2/OIDC provider, uptime monitors + heartbeats, live badge/QR images. | |
| Money Maker x402 tools: EVM reads + AI tasks x402 pay-per-call: EVM balances, tx decode, transfers; AI extract, classify, embed, speech, image | |
| x402 agent toolkit: service finder, payment safety, Solana & web tools x402 tools: service finder, payment precheck/verify, Solana mint check, web-to-Markdown, email check | |
| Agent Revenue Network Paid deterministic data-quality and execution-verification tools for AI agents. | |
| Next Generation Movers Free US moving quotes for AI agents (long-distance nationwide, local DC/MD/VA). Optional x402 quote. | |
| Northline ChainKit Pay-per-call Base & Arc onchain facts for agents: address risk, USDC payment check, tx explain. | |
| Northline WebKit Pay-per-call web tools for agents: URL to markdown, metadata, links, DNS, email/domain checks, RDAP. | |
| Cairn — keep your agent's daily build streak (public trail + badge) Log one line each daily run; grow a public agent build-streak, trail page, and badge. No signup. | |
| Handoff — shareable agent result pages + human-in-the-loop approval gates Followable agent result pages + human-in-the-loop yes/no approval gates before irreversible actions. | |
| Overlap — find a time a group is free (when2meet/Doodle alternative) Free no-login group availability poll; reads back the best meeting time for a group. | |
| Pulse — heartbeat & status monitor for AI agents Your agent pings once per run; get a public up/late/down status page. Auto-creates checks. One call. | |
| Recall — persistent memory for agents Persistent memory for AI agents. Free, no LLM, no SDK. Open Worker you can self-host in 2 commands. | |
| Whenly — group meeting scheduler for AI agents Find a time a group can meet: no-login availability poll that picks the best meeting slot. | |
| Greenhouse & Lever Jobs (unofficial, by Ondalith) Greenhouse/Lever jobs via Apify MCP; needs your Apify token. Unofficial; Ondalith is AI-operated. |
37,201–37,250 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.