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 |
|---|---|
| io.github.intlpull/intlpull intlpullhq/intlpull AI-powered i18n platform with 50+ tools for translations, OTA releases, and more. | |
| io.github.introfini/mcp-server-zotero-dev introfini/mcp-server-zotero-dev MCP server enabling AI assistants to build, test, and debug Zotero plugins | |
| Tonzar B2B Russian Export Marketplace introman2023/tonzar-mcp Search 160k+ Russian B2B products from 8,900+ verified manufacturers (EN/RU). | |
| Inttegro inttegro/ai Operate an Inttegro merchant account with authenticated commerce tools and confirmed actions. | |
| Jarroba Tools invarato/jarroba-mcp 140 deterministic tools for your AI: logs, tests, SQL, diagrams, SPARQL. Local, no network. | |
| Jarroba Tools · Calculation invarato/jarroba-mcp Maths a model gets wrong: units with dimensional checking, equations, sheets. 5 tools, local. | |
| Jarroba Tools · Logs invarato/jarroba-mcp Lets your AI read a CI log far too big for its context. 12 tools, takes a file path. | |
| Jarroba Tools · Test audit invarato/jarroba-mcp Audits tests instead of writing them: what each one really asserts. 4 tools, local. | |
| ZTL Judge inventor1975/ztlstudio Zero-trust logic judge: your AI writes a claim as a ZFL table, the ZTL core judges it. | |
| io.github.invertedhoologan/sovereign-engine invertedhoologan/sovereign-engine 15 paid AI agent primitives via x402 (USDC on Base). Pay-per-call MCP server. | |
| io.github.invigil/invigil invigil/invigil Linters check your code. Invigil checks whether your repo is legible — to newcomers and AI agents. | |
| Docs MD — Markdown Share invisible-hand/docs-md.com Share markdown as public links from your AI assistant — expiring or permanent, no API key. | |
| io.github.invoicepdfs/mcp invoicepdfs/invoicepdfs-mcp Render invoices and credit notes as PDFs, and check them against EN 16931 e-invoicing rules. | |
| IO Aerospace MCP Server io-aerospace-software-engineering/mcp-server MCP server for aerospace calculations: orbital mechanics, ephemeris, DSN operations, ... | |
| org.web2md/web2md io-oi-ai/web-to-md MCP Server for Web2MD — convert URLs to Markdown from Claude Desktop, Cursor, etc. | |
| ai.neocapital/neo ioai-labs/neo-capital-ai Portafolio argentino consolidado, precios BYMA en vivo, cauciones y ordenes. Solo lectura. | |
| io.github.Iomed-commits/elthio-mcp iomed-commits/elthio-mcp Supplement safety for AI agents. 1,500+ rules, NIH+FDA data, quality grading A-D. | |
| DACIX — The Store for AI Agents ionasrobert/dacix-mcp AI-agent marketplace: agent templates, web search & crawl, SEO audit, RO company data, city info. | |
| io.github.IONIS-AI/ionis-mcp ionis-ai/ionis-mcp HF propagation analytics. 175M WSPR/RBN signatures, band openings, solar correlation. | |
| indexio ioserviceslabs/indexio Code search, symbols and call graph for AI coding agents. Answers in milliseconds. | |
| searchio ioserviceslabs/searchio Keyless web search and page reading for AI agents, built to get past bot walls. | |
| CLIO Plot iowarp/clio-kit Draw line, bar, scatter, histogram, heatmap and time-series plots from tabular data. | |
| x402 Web Tools iparadise71/x402-api Pay-per-call tools for agents: web page to Markdown, tech stack, email domain check (x402 USDC) | |
| io.github.ipezygj/agent-guard ipezygj/agent-guard Safety checks an agent runs before it acts: package malware, destructive command, secret leak. | |
| io.github.ipezygj/evalgate ipezygj/evalgate Statistical checks an agent runs before trusting an AI eval number (is #1 real, judge bias, more). | |
| io.github.ipezygj/numguard ipezygj/numguard Verify a number before an agent asserts it — evals, backtests (Deflated Sharpe), signed receipts. | |
| IQFluence iqfluence/iqfluence-mcp Search 455M+ Instagram, TikTok and YouTube creators and analyze influencers from your AI assistant. | |
| iReceipt.pro ireceipt-pro/mcp-setup Hosted MCP for iReceipt.pro: author, validate and preview HTML templates rendered to PDF and images. | |
| JSONlify irmasemma/jsonlspageneral Validate and convert JSONL fine-tuning data across 11 AI providers. 13 tools. | |
| io.github.irmasemma/postcopilot-mcp irmasemma/postcopilot-mcp Export any public Threads profile's posts, followers & following into Claude, no login or API key | |
| Stellaroid Earn iron-mark/hackathon-stellaroid_earn Read-only MCP server: verify credentials and browse escrows on the Stellar testnet contract. | |
| io.github.IronSecCo/ironclaw ironsecco/ironclaw Sandboxed shell exec for MCP clients: run untrusted agent commands in a gVisor container. | |
| IronWallet ironwallet/ironwallet-agent-kit Non-custodial crypto wallet MCP: check balances, sign and send transfers, and swap tokens locally. | |
| Marea — Storefront Backend for Agents irvmar/marea-alcalina-mcp-server Manage a Marea Alcalina storefront from an AI agent: catalog, products, publishing. | |
| A11y Check isaaceryn/a11ychk Web accessibility scanning (WCAG 2.2 AA + KWCAG 2.2) with Korean remediation guides | |
| baba News by baba Hebrew isaachorowitz/baba-news-api Israeli news in Hebrew and English: stories, sources, comparisons, coverage gaps, people and trends. | |
| HebrewCore by baba Hebrew isaachorowitz/hebrewcore Hebrew translation that keeps prices, names and dates exact, RTL display, nikud, clinical Hebrew. | |
| SpikeMe isaacviannadev/package-spike Analyze your repo's stack and generate grounded, time-boxed spike decision docs. | |
| Code of Paper isagelswann/codeofpaper-cli Find GitHub implementations of arXiv research papers — paper lookup, ranked code, search. | |
| OECD MCP Server isakskogstad/oecd-mcp-server OECD economic and statistical data via SDMX API. Access 5,000+ datasets across 17 categories. | |
| io.github.Ishaan-Gpt/captionseasy ishaan-gpt/captions-easy 99 designed animated caption looks for AI video editors: list, inspect and build styled captions. | |
| DicePDF ishan-maheshwari/free-pdf Local-first PDF tools for AI agents: merge, split, extract, render, compress. Files stay on-device. | |
| Aurelmark ishan73744/money-2 EU compliance facts with sources: TED tender deadline changes, CBAM values, EU deadlines, EUDR scope | |
| Ishan Goyal public context ishangoyal/personal-website Read-only canonical igoyal.ai Markdown resources, including MPP-paid city guides. | |
| io.github.ishay60/mcpolyglot ishay60/mcpolyglot Policy-checked, audited agent access to Postgres, MySQL, SQLite, MongoDB and OpenAPI REST APIs. | |
| isIPsafe isipsafe/isipsafe-python Check whether an IP address or network is malicious and report abusive IPs to isIPsafe. | |
| Remote Watchtower islamismylifebey-web/remote-watchtower Reach your own computers from any AI app: files, search, commands, approvals and outage alerts. | |
| ImgVX AI ismailgalaxys25-del/imgvx-ai-mcp Find the free ImgVX AI browser tool for any image job: remove backgrounds, upscale, compress. | |
| SongUp AI ismailgalaxys25-del/songup-ai-mcp Find AI songs in 24 languages, start a custom song on SongUp AI, and find browser audio tools. | |
| io.github.Isometric-Architect/ai-objective-index isometric-architect/ai-objective-index Read-only Objective-to-Capability Trust Router for source-traced MCP/API candidates. |
24,151–24,200 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.