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.KNambiarDJsc/meridian-mcp knambiardjsc/meridian Local-first compliance scanner for DPDPA 2023/2025, RBI FREE-AI, SEBI AI/ML & EU AI Act. | |
| OODS Foundry kneelinghorse/oods-foundry OODS Foundry is an object-oriented design system that extends the one you already have. | |
| Reasonbook kneelinghorse/reasonbook Reasonbook: decisions that survive the session, in a local record AI agents keep. | |
| Droidline knifelemon/droidline Let an AI agent see and use a real Android phone over Wi-Fi, without ADB or root. | |
| ArcGIS Pro MCP knight60/arcgis-pro-mcp Lets AI assistants control a live ArcGIS Pro session through arcpy, including layer management, attribute queries, geoprocessing, symbology, and export. | |
| io.github.KNIHAL/causly-server knihal/causly-server Open-source MCP server that turns any AI agent into your technical co-founder | |
| Reverie knowall-ai/mcp-reverie Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search | |
| KnowJudges knowjudges/knowjudges-mcp Source-linked research on U.S. judges, courts, cases, and judicial analytics. | |
| GIA — Governed Intelligence Architecture knowledgepa3/gia-mcp-server Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping. | |
| io.github.Koala-Studios/newton-browser koala-studios/newton-browser Local-only Chrome and Edge control for MCP clients through an origin-scoped extension. | |
| World Monitor koala73/worldmonitor Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 100 tools. | |
| IBI Portfolio (Israel) kobimantzur/ibi-portfolio-mcp Read-only IBI (Israel Brokerage) portfolio for AI apps: positions, cash, P/L. Login stays local. | |
| io.github.kochetkov-ma/brewpage-mcp kochetkov-ma/brewpage-openapi Publish HTML, Markdown, sites, KV, JSON and files on BrewPage; keep the returned owner token. | |
| agent-bom koda-ai-studio/agent-bom AI supply-chain BOM: agents, MCP servers, packages and recorded reach. Scan and investigate via MCP. | |
| io.github.kodandy/jp-biz-opportunity kodandy/jp-biz-opportunity-mcp Japanese public-sector business opportunities for AI agents: tenders, subsidies, sanctions. x402. | |
| io.github.kodandy/jp-crypto-tax-rules kodandy/jp-crypto-tax-rules-mcp Machine-readable Japanese crypto-asset tax rules for AI agents: rules-as-code with citations, x402. | |
| io.github.kodandy/jp-m2m-gateway kodandy/jp-m2m-mcp Raw Japanese regulatory data for AI agents: pension, gazette, gBizINFO. x402-metered (USDC). | |
| ai.smithery/kodey-ai-salesforce-mcp-minimal kodey-ai/salesforce-mcp Run SOQL queries to explore and retrieve Salesforce data. Access accounts, contacts, opportunities… | |
| Kody kody-hq/kody Your agents' cloud for individuals and teams. Search, execute, packages, jobs, and credentials. | |
| Kodza kodza-dev/kodza Free premium UI components in plain HTML, CSS and vanilla JS, for AI coding assistants. | |
| io.github.kofujimura/tctc-mcp kofujimura/tctc-mcp ERC-7303 token-controlled roles for AI agents: grant, check, and revoke permissions on-chain | |
| com.kogcat/kogcat-mcp kogcat/cc-kogcat Local-first judgment layer: counter-examples & blind spots from your own knowledge base. | |
| io.github.koki-develop/esa-mcp-server koki-develop/esa-mcp-server A Model Context Protocol (MCP) server for esa.io | |
| KoKo Finance — Credit Card Advisor kokofinance/koko-mcp-server AI credit card advisor - search cards, compare portfolios, and optimize rewards | |
| io.github.kokogo100/ragalgo kokogo100/ragalgo-mcp-server Dynamic RAG Engine preventing AI hallucinations in Korean Finance and Crypto markets. | |
| ResuStack koksalkapucuoglu/resume-enhance Build, version and render resumes as PDFs from Claude or any MCP client. | |
| io.github.kOlapsis/gofact kolapsis/gofact Creates compliant French e-invoices locally: Factur-X PDF/A-3 with EN 16931 CII XML, legal numbering | |
| JMAP mail kolapsis/jmap-mcp Read, organize, draft and send email on any JMAP server, with OAuth sign-in and zero configuration | |
| maintenant kolapsis/maintenant Docker monitoring for AI agents: logs, history, alerts. Can ack alerts; never touches containers. | |
| io.github.kolganovr/mokido kolganovr/mokido Write to a live Figma canvas, get a screenshot back, and roll back mistakes. Zero deps, free plan. | |
| VPS Ops koller-nexus/vps-ops-mcp Stdio MCP server that inspects and (with confirmation) mutates one VPS over SSH. | |
| io.kolmo.www/kolmo-mcp-server kolmo-construction/kolmo-mcp-server WA permit rules (city + state baseline, cited), parcel zoning, L&I checks, Seattle estimates & ROI | |
| nokk koloss777/nokk Headless browser for AI agents with Chrome's fingerprint that passes Cloudflare challenges. | |
| Midpoint Card Prices kolourr/midpoint-mcp Trading card prices and grading ROI for 1.5M+ Pokémon, Magic, Yu-Gi-Oh! and sports cards. Read-only. | |
| frugal-memory komakeule57-maker/frugal-memory Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings. | |
| komnet komdosh/komnet Git-backed message bus for AI coding agents — Claude Code, Cursor and Codex coordinate asynchronously, with no server | |
| Seraph kondux/seraph-mcp-public Crypto transaction firewall and risk tools for MCP agents. | |
| io.github.Koneisto/HomeAssistant-Light-MCP koneisto/homeassistant-light-mcp Control Home Assistant lights and scenes. Lights only by design for safety. | |
| io.github.Koneisto/no-as-a-service koneisto/no-as-a-service 1000+ creative ways to say no. Polite, humorous, professional rejection responses. | |
| Kong Konnect MCP Server kong/mcp-konnect A Model Context Protocol server enabling AI assistants to interact with Kong Konnect's API Gateway, providing tools to query analytics data, inspect configurations, and manage control planes through natural language. | |
| sofagent kongfangxun/sofagent Commit-time audit engine for AI coding agents. Scans git diffs with 24 audit rules, writes HMAC-signed tamper-evident audit history, and ships MCP tools for governance aggregation. | |
| servo-fetch konippi/servo-fetch Servo-powered MCP server for JS-aware web fetching, content extraction, crawling, and software-rendered screenshots — Chromium-free single binary. | |
| WordPress MCP konkomaji/wordpress-mcp Talk to your WordPress site: content, SEO, WooCommerce, page builders, media and speed, with undo. | |
| io.github.kontent-ai/mcp-server kontent-ai/mcp-server Connect to Kontent.ai to manage content, types, taxonomies, and workflows via natural language | |
| KontragentPro kontragentpro/kontragentpro-mcp Russian company data by INN: registry, financials, bankruptcy, inspections, sanctions | |
| Excel MCP Server (FsOpenXmlDsl) kookerella-ltd/kookerella.fsopenxmldsl Excel tools for AI agents: read/write, decompile to F#/C#/XML/JSON, or build from XML/JSON. | |
| Word MCP Server (FsWordDsl) kookerella-ltd/kookerella.fsworddsl Word tools for AI agents: read/write, decompile to F#/C#/XML/JSON, or build from XML/JSON. | |
| KooLink URL Shortener koolink/koolink-cli Shorten any long URL into a clean kool.ink link. Free, unlimited, no signup. AI-agent ready. | |
| Prerender Buddy kopachlager/prerenderbuddy-mcp Crawler diagnostics, AI visibility evidence and article drafts for review in Prerender Buddy. | |
| GitLab MR MCP kopfrechner/gitlab-mr-mcp Enables AI agents to interact with GitLab repositories, allowing them to manage merge requests and issues including listing projects, fetching MR details and diffs, adding comments, and updating MR titles and descriptions. |
10,501–10,550 of 115,409
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.