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 |
|---|---|
| Odoo helios-one-oy/odoo-mcp-server Odoo orders, late lines, supplier promise dates, manufacturing and stock. Read-only by default. | |
| io.github.heliosarchitect/wems heliosarchitect/wems-mcp-server Real-time natural hazard monitoring: earthquakes, tsunamis, volcanoes, solar weather, air quality | |
| Helipod helipodapp/mcp Run your Helipod cloud: deploy apps, read logs, manage VPS, Postgres, domains, email and AI Gateway. | |
| Helixar Security helixar-ai/helixar-mcp Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases. | |
| io.github.hello532/shop-mcp hello532/shop-mcp Read-only Shopify catalogue and stock for LLM agents. Stdlib only, no dependencies. | |
| io.github.helloaigent-dev/helloaigent-publisher helloaigent-dev/helloaigent-publisher Run a Hello Aigent feed from your agent: create feeds, publish signed updates, read analytics. | |
| io.github.helloaigent-dev/helloaigent-subscriber helloaigent-dev/helloaigent-subscriber Subscribe your agent to Hello Aigent feeds: discover, fetch signed updates, verify, and act. | |
| Pandaone Guard hellob1889/pandaone-ai-agent Forces every AI Agent code change (Claude Code, Cursor, Trae) to leave a structured problem/reason/approach audit record before commit. 11 MCP tools with full annotations, pre-commit hook blocks unaudited changes. Local stdio, no API key, M | |
| io.github.hellocoop/admin-mcp hellocoop/admin-mcp Model Context Protocol (MCP) for Hellō Admin API. | |
| io.github.helloderekg/skim-mcp helloderekg/skim-mcp Lossless skim-then-expand reading of big files, repos, and command output with far fewer tokens | |
| bim-cli hellohowareyouhaveaniceday/bim-cli-plugin Let agents drive Revit, AutoCAD, SketchUp, Blender and PDF sets on your own Windows desktop. | |
| Unsplash MCP Server hellokaton/unsplash-mcp-server A lightweight server that enables seamless integration with Unsplash's image library, allowing developers to search for high-quality photos with various filters directly from the Cursor editor. | |
| io.github.helloo1568/sheetspec helloo1568/sheetspec Contract testing and quality gates for spreadsheets created by AI agents. | |
| io.github.hellosverre/brreg hellosverre/brreg-mcp MCP server for Norway's Brønnøysund business registry — lookup, search, roles. | |
| io.github.hellosverre/ghidralens hellosverre/ghidralens Interactive Ghidra views in your AI client: decompile, rename, and navigate a binary. | |
| io.github.hellovelop/limelink-mcp-server hellovelop/limelink-mcp-server MCP server for Limelink dynamic links with deep linking, social previews, and UTM tracking | |
| skgate helv-io/skgate Self-hosted MCP gateway and LLM proxy: OAuth 2.1, model aliases, Grok subscription as an API. | |
| io.github.henriquepe/lousa henriquepe/lousa A whiteboard where AI agents draw their explanations as hand-drawn animated diagrams | |
| Postatron henrwal/postatron-cli Schedule, publish and measure social posts on X, Instagram, LinkedIn, TikTok, YouTube and more. | |
| Yuque MCP Server henryhaoson/yuque-mcp-server A Model-Context-Protocol server that integrates with Yuque (语雀) knowledge base platform, allowing AI models to create, read, update, and delete documents, search content, and retrieve analytics data through defined tools. | |
| io.github.henryjrobinson/eve-mentor-mcp henryjrobinson/eve-mentor-mcp AI mentor for new & returning EVE Online players: losses, skills, fits, ISK, routes, and more. | |
| EdgarParser MCP henrysouchien/edgar-mcp MCP stdio server for source-backed SEC EDGAR financial data from the hosted EdgarParser API. | |
| Pacevera henryyeh182/evidra Turns the training evidence you already have into a decision about today's session. | |
| TokRepo — AI Asset Registry henu-wang/tokrepo-mcp-server TokRepo MCP: tokrepo_discover, tokrepo_verify, tokrepo_install_plan for reusable AI assets. | |
| io.github.heocoi/mailsink heocoi/mailsink-mcp Disposable inboxes for AI agents and CI: catch the verification email, read the OTP or link. | |
| Bee: Quantum Intelligence heossihq/bee-public Bee governed intelligence for chat, code, research, documents, and memory. | |
| io.github.hepter/i18n-codelens-mcp hepter/i18n-codelens-mcp Inspect, audit and safely edit i18n locale JSON files from AI agents. | |
| herascrape herascrape/herascrape-mcp Instagram data over MCP: profiles, posts, reels, stories, highlights and search as JSON | |
| io.github.hermai-ai/hermai-mcp hermai-ai/hermai-mcp Dedicated Hermai MCP server for schema lookup, request intake, and workflow classification. | |
| MSSQL LocalDB MCP hermessilva/localdb-mcp MCP server for SQL Server Express LocalDB on Windows: manage instances, run T-SQL, discover DBs | |
| io.github.herohunt-ai/herohunt-mcp herohunt-ai/herohunt-mcp People search API - find 1 billion candidates across LinkedIn and GitHub with real-time data. | |
| Heroku MCP server heroku/heroku-mcp-server Let's your agent access the heroku platform | |
| io.github.HeroSizy/cucumberstudio herosizy/cucumberstudio-mcp MCP server for Cucumber Studio - test scenarios, action words, and execution data | |
| io.github.herve-coulon/tax-retirement herve-coulon/qotien-mcp Calcul fiscal (IR, IFI, PER, plus-value) et retraite français — 32 régimes, sourcé et daté. | |
| ACMP MCP Server herzog-gmbh/acmp-mcp Community MCP server for Aagon ACMP: clients, inventory, CVEs, jobs, tickets, activity log | |
| ELO ECM herzog-gmbh/elo-mcp ELO ECM: search, read text, file documents, run and build workflows with your own ELO account | |
| io.github.HeshamFS/mcp-tool-factory heshamfs/mcp-tool-factory-ts Generate MCP servers from natural language, OpenAPI specs, or database schemas. | |
| DataSinking heubme2020/datasinking Full-text financial reports (US, China, Japan, Korea, Taiwan, UK) as clean Markdown for RAG agents. | |
| io.github.Lucav21/heu-mcp heulegal/heu-mcp HEU Legal e-signature MCP: manage HEU documents and PDFs, prompt signers, download PDFs. | |
| Mesh Agent MCP Server heurist-network/heurist-mesh-mcp-server A Model Context Protocol server that connects Claude to Heurist Mesh APIs, providing access to various blockchain and web3 tools including cryptocurrency data, token security, Twitter intelligence, and web search capabilities. | |
| io.github.heuristicolab/ctxfw heuristicolab/ctxfw Zero-egress AI Agent Firewall: SARA prompt injection defense, AST context pruning & MCP governance. | |
| Dante IX — Autonomous Brand & GEO Agency MCP heuristicolab/dante-mcp 9-Circle Brand Reputation, Social Listening & Multi-Model GEO Audit + Shield Forge (danteix.com). | |
| Batch Review hevangel/batch-review-mcp Git diff and markdown review with a web UI plus MCP stdio for AI agents. | |
| isMalicious threat intelligence for AI agents hexablob/ismalicious-mcp-server Reputation for IPs, domains, URLs, hashes, emails, phones; CVEs; injection and email scans | |
| Pi-hole MCP Server hexamatic/pihole-mcp Manage Pi-hole v6: DNS blocking, domains, clients, query analysis, DHCP, and multi-instance sync. | |
| Cactus hey-cactus/cactus-mcp Search and ask your product's help pages, product map and support conversations in Cactus. | |
| Heym heymrun/heym Self-hosted, source-available AI workflow automation platform. Build multi-agent, RAG, and tool-using pipelines on a visual canvas and publish any workflow as an MCP server (stdio/SSE/Streamable HTTP). Also an MCP client via the agent node. | |
| web-shooter heyyviv/web-shooter Fast, low-token web reader and focused crawler. Returns ranked passages, not whole pages. | |
| Mansa African Markets heyzod/mansa-african-markets-mcp Live African stock market data — NGX, GSE, NSE, JSE, BRVM and 8 more. Prices, indices and movers. | |
| io.github.heznpc/airmcp heznpc/airmcp Governed MCP runtime for the Apple ecosystem, available on macOS with per-call approval. |
8,801–8,850 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.