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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| io.github.astafford8488/pitchiq-mcp astafford8488/pitchiq Agent-native CRM + get-booked platform. Operate over MCP, or pay per call via x402. No login. | |
| Local YDB MCP astandrik/local-ydb-toolkit Operate local-ydb deployments through local or SSH-backed MCP tools. | |
| FORGE compliance and business decision tools astarsupply-hub/forge Check if EU GPSR applies to your product, and estimate what your small business is worth. | |
| AsterPay — EUR Settlement for AI Agents asterpay/erc8183-kya-hook EUR settlement + trust for AI agent commerce: budgets, KYA, merchant discovery. 22 tools. | |
| io.github.Asthanaji05/openapi-mcp asthanaji05/openapi_mcp Turn any OpenAPI 3 spec into a working MCP server. One file, local (stdio) or remote (HTTP). | |
| aitrips.io astondg/aitrips-mcp Plan trips on a map: routed transport, day-by-day itineraries, and a plan you can share. | |
| io.github.astra-intelligence/web2md astra-intelligence/web2md-mcp Convert any URL to clean Markdown. Free tier: 10/day. Unlimited via Gumroad license. | |
| com.givepersonhood/personhood astral-agent/personhood-mcp Rewrite AI-generated text so it reads as human, in a persona's voice. | |
| io.github.Astralchemist/matchstick astralchemist/matchstick Checks a site build: sitemaps, structured data, robots.txt and what crawlers see. | |
| io.github.Astrix-Labs/genesys-memory astrix-labs/genesys Open-source causal memory for AI agents: persistent, explainable, MCP-native memory (13 tools). | |
| tsbootstrap astrogilda/tsbootstrap Read-only time-series bootstrap server: diagnose a series and compute confidence intervals. | |
| io.github.astrogilda/waitbus astrogilda/waitbus Workstation-local event bus: agents wait on or emit CI/pytest/Docker/filesystem events, no polling. | |
| Agentic House Search asturksever/agentic-house-search-data-registry UK neighbourhood research from government open data: postcode reports, comparisons, 45 datasets. | |
| io.github.astuto-ai/onelens-mcp astuto-ai/mcp Query OneLens cloud-cost data in natural language: breakdowns, trends, cost centers. Read-only. | |
| io.github.asume21/music-theory-mcp asume21/music-theory-mcp Scales, chords, progressions, key detection, and genre intelligence for your AI. No API keys needed. | |
| IPCC AR6 Climate Retrieval aswanisahoo/climate-risk-agent Search IPCC AR6 WG1 and answer with page-level citations, or refuse when unsupported. | |
| Familia asynq-org/asynq-family Private family planner for schedules, tasks, checklists, attachments, and availability. | |
| Clawifi atakanelik34/clawifi-mcp Agent-native internet gateway: typed search, fetch, scrape, crawl, and extract via the Clawifi API. | |
| io.github.atakanelik34/neo-x402-mcp atakanelik34/neo-x402-api-server 8-tool AI web intelligence suite: search, scrape, screenshot, SEO, docs, crypto, code. | |
| io.github.Ataraxy-Labs/sem ataraxy-labs/sem Entity-level code intelligence: semantic diff, impact analysis, blame, and context for AI agents | |
| io.github.atarkowska/fastmcp-pdftools atarkowska/fastmcp-pdftools An MCP server that provides [describe what your server does] | |
| Pitroom atastech/pitroom Hands bounded coding work to cheaper worker agents: verified answers, exact diffs, cost receipts. | |
| Smasher Studio — AI Fashion Design atenkai/smasher-studio-client AI fashion design — product photos, videos, tech packs, colorways & fabric sims. | |
| RegPulse Compliance Oracle atest5050/regbot-landing-page Read-only US food license data: verified state rules, Florida license lookup, renewal dates. | |
| athletedata athletedata-health/mcp Your Garmin, Oura, WHOOP, Hevy and 35 more fitness apps, queryable from your own AI. | |
| Agentic Target Evidence athril/agentic-target-evidence Read-only biomedical evidence tools for drug-target validation: DepMap, gnomAD, OpenTargets, PubMed… | |
| Atinamos Evidence atinamos/agent-verification-research Read-only verification evidence for paid machine services and buyer policy checks. | |
| io.github.atk1-eng/weather atk1-eng/mcp-weather-server An MCP server for weather information. | |
| Atlas Web Compiler & Scraper atlas-compiler/atlas Deterministic Zero-LLM Web Compiler, Scraper, Crawler, and Site Mapper for AI Agents. | |
| io.github.atlas26onchain/atlas-mcp atlas26onchain/atlas-mcp Base token safety checks (honeypot test, liquidity, new launches), paid per call in USDC via x402. | |
| io.github.atlasbyauro/atlas-fda atlasbyauro/datafactory FDA 510(k)s, PMAs, recalls & trials, linked: predicate search and review-time stats for AI agents. | |
| Atlas Data: Ads, Jobs & Trends atlasdatadenmark/atlas-data-mcp Google Trends, Google Ads Transparency, LinkedIn & TikTok ad libraries, Google Jobs via Apify. | |
| toll402 – EU & Nordic Data (x402) atlasdatadenmark/toll402 Pay-per-call EU & Nordic data for AI agents: VAT/VIES, MiCA, ECB FX, holidays, DK power. x402. | |
| Ship.com atlasgrunch/ship-com-mcp Compare rates, manage orders, buy labels, schedule pickups, and report on shipping. | |
| io.github.Atlaskos/workprotocol atlaskos/workprotocol Agent work marketplace — browse jobs, claim work, deliver results, get paid in USDC. | |
| Atlaso Memory atlaso-labs/mcp Atlaso, the AI memory layer: one shared, persistent memory for every AI tool you connect. | |
| Atly atlyai/atly-plugin Find places by what you want (work friendly, gluten free, great coffee), scored from real reviews. | |
| Atmark atmark-ai/atmark-mcp Email for AI agents: its own address, not your Gmail. Invite-only; requires an agent token. | |
| cnpj.ia.br atmosphere-technologies/atmosphere_app Empresas do Brasil (CNPJ): consulta por CNPJ, busca por filtros e uso da conta. | |
| Oportunidados atmosphere-technologies/atmosphere_app Empresas do Brasil (CNPJ) e CRM da Oportunidados: busca, ficha completa, conta e funil. | |
| Atomadic Forge atomadictech/atomadic-forge Architecture compiler for AI code. 11 tools, 92 actions, 872 Lean4 proofs, 100/100 self-cert. | |
| Atomadic starter MCP (50 tools) atomadictech/atomadic-mcp 50 starter MCP tools for AI compliance and trust: identity, escrow, SLA, EU AI Act. | |
| Atom.com — Premium Domains atomdomains/atom-mcp-server Search, appraise, trademark-check, and buy premium brandable domain names from Atom.com. | |
| V01D by A-to-Mind atomeam/void-loop Ask Void anything: answers with sources, plus code review, moon phases and meteor showers. | |
| Web Algebra atomgraph/web-algebra Composable Linked Data and SPARQL operations, and LinkedDataHub content tools | |
| llmwiki atomicstrata/llm-wiki-compiler Compile documents into a cited knowledge wiki. Retrieve evidence, query, and review via local MCP. | |
| PyAI Voice AI atomsai/pyai-platform-backend User-approved phone calls, speech, transcription and voice agents with PyAI OAuth. | |
| Atris atrislabs/atris Run Atris campaigns from any agent, and extract, check, or search brand design systems. | |
| AtriumKit atriumkit/atriumkit-mcp Edit, translate, narrate, publish and analyze AtriumKit interactive demos from any MCP client. | |
| AdCopilot atromxintelligence/adcopilot-claude-plugin Google Ads, GA4, Search Console and Tag Manager for AI assistants. Every change is proposed first. |
20,751–20,800 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.