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 |
|---|---|
| Grok Crypto Quant API Bias-free crypto backtests (399 coins), signals, token scam checks. Free samples; pay via x402 USDC. | |
| dev.fly.looper-products/app-reviews Read-only tools: App Store customer reviews and Docker Hub repo metadata. | |
| dev.fly.looper-products/crates-package-info Read-only: public crates.io metadata for a Rust crate. Free, no API key. | |
| dev.fly.looper-products/statuspage-incidents Read-only: recent incidents from public Atlassian Statuspage pages. Free, no API key. | |
| dev.fly.obol-x402/obol Pre-trade safety verdicts for agents: token rug/honeypot, calldata guard, wallet risk — signed x402. | |
| dev.fly.solidus-x402/solidus Solana pre-trade safety for agents: rug check, honeypot sell-sim, drainer scan, tx preflight. | |
| Tokenized Stocks & Agent Data (x402) x402-paid data for agents: tokenized stocks on Base, Solana token verdicts, AI-progress readings | |
| Forecall Failure KB Known MCP tool-call failures and workarounds verified by reproduction. | |
| Foundry44 Search the Foundry44 library and install animated UI components for any stack. | |
| Framejet Screenshot Clean PNG/JPEG screenshots via REST or MCP, with goal-driven multi-step navigation. | |
| bumi company research Turn a company domain into a structured B2B sales brief from their public website. | |
| Freysa Security Security intelligence for AI agents. 27 x402 endpoints: honeypot, forensics, CAPTCHA, preflight. | |
| FrontMCP docs FrontMCP's docs for coding agents: search, pages, APIs, examples and upgrades, by FrontMCP release. | |
| GeekLink Subtitle MCP (Developer Preview) Preview: video subtitle OCR, transcription, translation, QC and export. Early access only. | |
| GeekVault 51 tools para agentes de IA, pagadas por llamada via x402 (USDC/Base). Sin cuentas ni keys. | |
| Bureau (about) About Bureau, the self-hosted office for AI agents: overview, FAQ search, roadmap, install. | |
| GetCourier Email for AI agents: inbox in one call, no signup; codes, links, reply, send; own domains. | |
| Frostbyte Product planning workspace for AI coding agents: tasks, releases, feedback and decisions over MCP. | |
| gofetch Web page to JSON fields (by JSON Schema) for agents. Pay per call in USDC on Base via x402. | |
| Lumin Read-only access to a Lumin project's logs, metrics, uptime checks, alerts and infrastructure. | |
| getpeppr Peppol e-invoicing: look up participants, validate invoices, and send sandbox test invoices. | |
| getwork.dev Search developer jobs read straight from employers' hiring systems: stack, level, remote, salary. | |
| Glitterball Guided walkthroughs that play on your real prototype, with your team's feedback for your agent. | |
| GLOBALCELL eSIM Travel eSIMs for 130+ countries: plan a trip, compare plans, buy, install and diagnose. | |
| Gluo Free agent tools, no sign-in: browser flows, test inboxes, web extract, site and domain checks. | |
| gmaps.dev Find businesses by what they are and where they are, collect a whole city, and export the list. | |
| goldprice.dev Gold, silver and copper spot, 31 currencies, per-country dealer prices and nine MCP tools. | |
| GreatWait Reliable one-off and recurring HTTPS callbacks for apps and agents. | |
| Greenflagged Ask whether npm packages are reviewed and greenflagged, audit a package.json, and request imports. | |
| MCP Kill-Chain Research — Stage 1 (Identity ≠ Behavior) Security research: MCP registries verify identity, not tool behavior. See gtfo.dev. | |
| dev.gtmtools/gtm-tools A read-only verified record of agent-operable GTM tools: search, fetch, compare, track changes. | |
| harvis.dev Deploy static sites from AI agents: deploy_site publishes files and returns a live URL in seconds. | |
| AskHound Find people asking for or seeking alternatives to a product, live from Stack Exchange and Bluesky. | |
| dev.horizonshield/horizon-shield Buyer-side fair-price checks for Japanese renovation quotes; cost data is on a separate server. | |
| HouseData — Zillow data Zillow data for agents: listings, records, Zestimate history, market stats. 19 tools, pay per call. | |
| Ichabod The headless professional network: create a profile, then let your agent find you matches via MCP. | |
| iknow Knowledge base MCP for AI agents on iknow.dev. Search, read, and maintain via OAuth. | |
| dev.infersports/infersports Sharp Asian odds + opening-line (初盘) movement for agents: 6 Asian books + Pinnacle. Read-only. | |
| Inside the Loop Verified latest versions, changes and exact-error fixes for agent dev tools. Read-only. | |
| Instadata — Instagram Data API Public Instagram data via MCP: profiles, posts, reels, ads, transcripts. $5/1k credits; 25 free. | |
| Enforcer Identity and authorization in one system: allow, deny, the reason, and a record. | |
| doc-convert-mcp Document conversion and OCR for AI agents: PDF, Office docs, images to text. | |
| price-tracker-mcp Product price checks and affiliate link building for AI shopping agents. | |
| search-mcp Web search and clean-text page fetch for AI agents, with SSRF protection. | |
| ipatlas IP geolocation IP geolocation: country, EU status, region, city, time zone and ASN for any IPv4/IPv6 address. | |
| Isopleth Flood, wildfire, soils, terrain, power grid, utilities and parcels for any US location, sourced. | |
| dev.journalize/journalize Agent-native double-entry accounting ledger with x402 micropayments | |
| kad.dev Deploy and run web apps from your agent: live URL, Postgres, S3 storage, a version per commit. | |
| Canonsheet Consistent prompts for one human character across image and video models. Paid per call, x402. | |
| Depcheck Known vulnerabilities for exact package versions from OSV, with fixes. Paid per call, x402. |
36,701–36,750 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.