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 |
|---|---|
| PDF Kit AI-powered PDF tools: fill forms, merge, extract data, and split PDFs | |
| co.pepys/pepys-mcp Transcribe audio & video: diarization, timed SRT/VTT, podcasts, paste-a-link, whole-feed batch. | |
| Perplexity Browser MCP Search Perplexity using your browser login. Returns answers, sources, and thread URLs. No API key. | |
| Company fundamentals by filing date Company financials from official filings, each figure keyed to its filing date. | |
| io.github.oguzc/playwright-wizard-mcp MCP server providing Playwright test generation wizard with intelligent prompts and best practices | |
| PodPDF Turn HTML, Markdown, URLs and saved templates into PDFs with the PodPDF API. | |
| io.github.vibegpt/policycheck AI seller verification and policy risk analysis for any online store. | |
| Pombus Email boxes for AI agents. Read, draft, send and triage mail. | |
| Positif The agent switchboard: identity, policy, loop-guard, and an append-only audit ledger. | |
| io.github.martymarkenson/postgres-connector MCP server for querying PostgreSQL databases | |
| Power Strip Security Prompt-injection shield for agents: read pages, scan content, audit MCP servers and skills. x402. | |
| 找客户 · Find Customers｜销售线索与评论区获客 Find sales leads in Douyin, Xiaohongshu, and Kuaishou comments; installs its Skill with approval. | |
| PreClone Check what a repo would run on your machine (open, agent start, install) before you clone it. | |
| Pre-Trip compliance scanner Screen regulated-health marketing copy against source-cited rulesets, all 50 states. | |
| Preventionlabs See what's wrong with a live website from the outside, with proof: uptime, DNS, HTTPS, leaked files. | |
| PreviewDrop Deploy any Git branch to a live HTTPS preview URL from your agent. No Dockerfile required. | |
| Proofsheet Run e2e flows on real iOS and Android phones through the local Proofsheet hub (macOS). | |
| ProofStream Dispatch a human verifier to physically verify anything in the real world. For AI agents. | |
| io.github.LBZ558/prophetkey-mcp ProphetKey MCP bridge - encrypted local-first API key vault for AI agents, keys never exposed | |
| com.sulvo.publisher-revenue-audit/audit Publisher revenue audit: ads.txt and ad-stack checks, Sulvo onboarding, and Boost ad-block recovery | |
| QNSQY Linux only, local: post-quantum CBOM scan, encrypt to public keys, verify. Takes no secrets | |
| io.github.quantumproxies/quantumproxies-mcp Web scraping, SERP search, crawl/map and 74 Collectors through residential proxies. 25 tools. | |
| Quire PDF Turn JSON into polished PDFs: invoices, receipts, quotes, certificates, or any data. | |
| io.github.B0ydT/r-packagedev-mcp MCP server for R package development using usethis, devtools, renv, and testthat | |
| Reconstitution Calculator Lab math: reconstitution, unit conversion, C1V1, molarity, percent w/v, serial dilution. | |
| reference-mcp Reference integrity for AI agents. Scans and verifies links, imports, assets, deps. | |
| com.reflexmcp/reflex Browser automation for AI agents: compressed page snapshots, batched actions, fewer tokens. | |
| release-gate-mcp Release intelligence for AI agents. Detects breaking changes and recommends semver. | |
| ReplyLayer Safe email for AI agents: a mailbox with inbound scanning, outbound checks and human review. | |
| io.github.0xthaner/reputa DISCONTINUED. Reputa was shut down. Final release: no network, no keys, shutdown notice only. | |
| Resolve402 French directors, NACE company search (FR, NO, FI), KYB checks, contacts, hiring signals, x402. | |
| io.github.vpatser1/resume-optimizer Resume analysis, ATS compatibility checks, bullet improvements, job-tailored optimization | |
| Revnuvo Trust Verify companies, domains and counterparties before transacting. Sanctions, UBO, fraud scoring. | |
| RONIN Web Research Web research and source retrieval. Native MCP tool with x402 Base USDC payment, 0.010000 per call. | |
| Routebase Design, mock, test, document and monitor your APIs from one living OpenAPI spec. | |
| RTL awareness for coding agents Give coding agents right-to-left awareness: lint, normalise Arabic, detect direction. | |
| Runsheet YouTube Autopilot The YouTube autopilot: plan, write and schedule YouTube videos, and upload from your machine. | |
| Salamailer Send end-to-end encrypted email and files. Encryption happens on your machine, not our server. | |
| Sandboxer Cloud Linux VMs for your agent: run code, Docker, files and HTTPS previews in a Sandboxer microVM. | |
| Santuri Search official documentation for well-known libraries. | |
| santyvv-data — market & on-chain data Market and on-chain crypto data for AI agents. Pay per call in USDC on Base (x402). | |
| ru.scanbase/scanbase Website compliance checks for Russian personal data law 152-FZ: score, violations, fix instructions. | |
| Science AI Journal MCP Server Academic peer-review, research-gap finding, journal recommender, and article writer tools. | |
| Screenshotor Website screenshots for AI agents: real Chrome, ad/cookie/chat blocking, bot-wall detection. | |
| SEAL Large files and secrets between people and agents, never through the chat or the model. | |
| Seedfast Generates relationally valid test data in a PostgreSQL database from its live schema. | |
| SendShort Turn long YouTube videos into shorts and music videos, and schedule posts to TikTok and YouTube | |
| io.github.vpatser1/seo-audit-tool SEO page audits with 0-100 scoring, keyword analysis, link checking, sitemap validation | |
| Serenn — Find Verified Field Service Technicians Find verified appliance repair, HVAC, and plumbing technicians by location and brand. | |
| serp402 Google search for agents: web, news, images, places, shopping, Scholar. Paid per call over x402. |
46,551–46,600 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.