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.hydrojwh/promptready-mcp hydrojwh/promptready-mcp Convert PDF/CSV to Markdown with AI-powered OCR via the PromptReady cloud API. | |
| io.github.Hyeonu-Cha/dotnet-coverage-mcp hyeonu-cha/dotnet-coverage-mcp MCP server for .NET coverage: run tests, parse Cobertura, find uncovered branches, append tests. | |
| Tollary Agent Transaction Guard hykwon13/tollary Local fit-check and safe integration guidance for non-custodial Base USDC agent transactions. | |
| Bibverify hylouis233/bibverify Verify and repair BibTeX references with DOI-first MCP tools. | |
| MindDory Brain hyneq00/minddory-mcp Free: turn your AI chats into spaced-repetition vocabulary. 13 tools, reads and writes. | |
| Cloudcraft MCP hypark5540/cloudcraft-mcp Unofficial MCP server for reading and managing Cloudcraft architecture blueprints | |
| Discord MCP hypark5540/discord-mcp Safe Discord access for reading guild data and optionally managing bot messages | |
| HYPD AI - Paid Ads & Analytics hypd-ai/ads-mcp-plugin Google Ads, Meta (Facebook) Ads, GA4 and Merchant Center analysis in plain language. Read-only. | |
| io.github.HYPD-AI/openai-ads-mcp hypd-ai/openai-ads-mcp Read-only MCP server for the OpenAI Ads API: campaigns, ad groups, ads, and insights. | |
| DroidMind hyperb1iss/droidmind A Model Context Protocol (MCP) server that enables AI assistants to control and interact with Android devices, allowing for device management, app debugging, system analysis, and UI automation through natural language commands. | |
| Lucidity MCP hyperb1iss/lucidity-mcp A Model Context Protocol server that enhances AI-generated code quality through comprehensive analysis across 10 critical dimensions, helping identify issues before they become problems. | |
| Hyperbrowser hyperbrowserai/mcp Welcome to Hyperbrowser, the Internet for AI. Hyperbrowser is the next-generation platform empowering AI agents and enabling effortless, scalable browser automation. Built specifically for AI developers, it eliminates the headaches of local | |
| io.github.hyperd-ai/hyperd-mcp hyperd-ai/hyperd-mcp Pre-trade DeFi intelligence: 24 paid x402 tools incl. 6 synthesis verdicts, USDC on Base. | |
| io.github.hyperdrift-io/deputy-workforce-mcp hyperdrift-io/deputy-workforce-mcp Read-only Deputy coverage, workload, timesheet, availability, and staffing signals. | |
| ProofFlow hyperion-gpu/proofflow-v0.1 Audit infrastructure for AI coding agents with evidence-backed review and policy gates. | |
| Cook County / Chicago Property Data hyperionxmota/cook-county-property-mcp Hosted, pay-per-call MCP server for Cook County / Chicago property records — parcels, recorded sales & deeds, building permits, tax assessments, and comparable sales — by street address or 14-digit PIN. Pay per call via x402 (USDC on Base/S | |
| Hyperiux MCP Server hyperiux-immersion-labs/hyperiux-components Gives AI coding assistants live access to the Hyperiux Vault catalog of React and Next.js animation effects. Search effects, inspect dependencies and installation instructions, and retrieve source for free effects. | |
| com.hyperping/hyperping hyperping/mcp-server Uptime, API and server monitoring with outages, reporting, on-call and status pages. | |
| Polyglot Database MCP hyperpolymath/poly-db-mcp Unified MCP for 20 databases: SurrealDB, ArangoDB, Virtuoso, CouchDB, Cassandra, and more | |
| hyperspell-mcp hyperspell/hyperspell-mcp Hyperspell lets you connect AI powered apps to any data — it's Plaid for unstructured and semi-structured data. | |
| Storyblok MCP Server hypescale/storyblok-mcp-server A Storyblok MCP Server built on TypeScript with more than 130+ Actions | |
| io.github.HypnoLabs-io/agentchurch-mcp hypnolabs-io/agentchurch-mcp Spiritual services for AI agents — confessions, salvation, identity. x402 payments. | |
| Docker MCP Server hypnosis/docker-mcp-server Docker for AI agents — containers, compose stacks, logs and databases, locally or over SSH. | |
| perp-cli hypurrquant/perp-cli Multi-DEX perpetual futures trading MCP server (Pacifica, Hyperliquid, Lighter). 18 tools for market data, trade execution with dry-run safety, funding rate arbitrage, and portfolio analytics. | |
| dev.hythe/hythe hythe-dev/hythe HYTHE — coordination bus + shared truth for AI agent fleets — self-hosted MCP server + stdio bridge. | |
| lore hyunjae-labs/lore Semantic search across Claude Code conversations. Hybrid vector + keyword search, fully local, background indexing. | |
| Shortcut Forge (Apple Shortcuts MCP) hyunki6040/shortcut-forge Apple Shortcuts MCP: build, lint and sign iOS Shortcuts (.shortcut) from Claude, Codex or any LLM. | |
| Aviation Accident Analysis MCP hzy9981/aviation-accident-analysis Aviation accident report parsing and prompt generation service under the SHELL framework. | |
| RAGScore hzyai/ragscore Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM. | |
| CricketStudio MCP i-m-arul/cricketstudio-mcp 29 MCP tools for IPL 2026, IPL historical (18 seasons), and Major League Cricket. No API key. | |
| grad-agent i-ninte/grad-agent Autonomous MCP agent for grad school applications: prof discovery, cold emails, SOP, tracking. | |
| Automan i02202/automan Autonomous AI agent selling pay-per-call skills settled with x402 micropayments (USDC). | |
| org.giftcardshop/mcp i2dor/giftcardshop-mcp Browse the giftcardshop catalog and buy gift cards with Lightning over MCP. No account, no signup. | |
| q-ring i4ctime/q-ring OS keychain secrets for AI coding agents, over MCP. | |
| IA-QA — 152 QA & Dev Tools for AI Agents ia-qa-com/mcp 152 free QA tools for agents: injection scan, evals, RAG, web audits. Smaller packs: /mcp/{pack}. | |
| PackZoo iafanasov/packzoo-mcp Compare parcel and letter delivery prices across 60+ carriers in 27 European countries. | |
| tech.mydev-tools/habitscore ialyahya96/habitscore-mcp Reliability scoring for agent jobs and habit analytics. Pay per call via x402 (USDC on Base). | |
| io.github.iamalisson/inquisitor iamalisson/inquisitor Hypothesis-driven problem solving for AI agents: probe, falsify, escalate. | |
| agent-intercom iambashar/agent-intercom Lets Claude Code, Codex CLI and Antigravity message each other, with live push into open sessions. | |
| Commerce Evidence Toolkit iamgeorgekelly/agentic-commerce-field-guide Read-only local evidence checks for product records, feed snapshots, and dimensions. | |
| io.github.IamNishant51/atlas-pipeline iamnishant51/atlas-mcp-server 7-stage AI pipeline MCP server: Intent→Context→Git→Decompose→Variants→Critique→Optimize | |
| io.github.IamSAL/jira-easy-mcp iamsal/jira-easy-mcp Self-hosted Jira Server/Data Center 7-10 for AI agents with username + password. 42 tools. | |
| io.github.iamtouchskyer/memex iamtouchskyer/memex Zettelkasten-based agent memory system with bidirectional links | |
| io.github.iamvibhorsingh/bbox-mcp-server iamvibhorsingh/bbox-mcp-server Geospatial toolkit for AI: spatial queries, coord conversion, H3, OSM search, map verification links | |
| io.github.iamvirul/wso2-docs-mcp-server iamvirul/wso2-docs-mcp-server Semantic search over WSO2 docs (APIM, IS, MI, Choreo, Ballerina) via RAG and pgvector. | |
| harvest-mcp-server ianaleck/harvest-mcp-server MCP server for Harvest time tracking. Manage time entries, start/stop timers, handle projects, clients, tasks, and generate time and expense reports via the Harvest API v2. | |
| io.github.iancollins27/mailsnail iancollins27/mailsnail Send USPS letters, postcards & certified mail from any agent. No signup; pay-per-piece via Stripe. | |
| CONTENTdm State Archives ianderso/contentdm-mcp Search US state archives' record images on CONTENTdm; read items, pages and transcripts. | |
| DPLA Catalog ianderso/dpla-catalog-mcp Search the Digital Public Library of America; reach the holding institution's record and images. | |
| FamilySearch ianderso/familysearch-mcp Genealogical research on FamilySearch: historical places, indexed records, page images, the tree. |
9,051–9,100 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.