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 |
|---|---|
| SecureInput r69shabh/secureinput Local API key input for AI agents, with command and .env delivery. | |
| Vuntum raaaaageeeee/vuntum-mcp Sourced, dated data on consumer robots and physical AI: specs, prices, availability, evidence. | |
| Payment Intelligence raafet57/payment-intelligence-plugin Offline ISO 20022 payment tools: explain and scrub pacs/camt, CBPR+, SSI checks, IBAN and BIC. | |
| MetaLend rabeles11/metalend-mcp Browse, deposit, withdraw & rebalance stablecoins on Aave, Morpho & Euler across major EVM chains. | |
| RaceHooks racehooks/racehooks-mcp Predictive models and analytics for motorsport — race intelligence delivered to your endpoint. | |
| io.github.rachadele/biolit rachadele/biolit LLM-assisted biomedical literature screening and extraction for PubMed, GEO, and preprints. | |
| Wonderkraftz - Premium Gifting Studio rachit1987/wonderkraftz-mcp Browse and shop Wonderkraftz premium gifts. Recommendations, cart, and checkout via AI. | |
| geoseo-mcp rachit8484/geoseo-mcp SEO + GEO: Search Console, Bing, Yandex, IndexNow, AI Overviews and LLM citation tracking. | |
| Unity MCP Server rachitkumarrastogi/unity-mcp-server MCP server for Unity: 130+ tools, Unity 6 skills, AI/ML discovery. No Editor. | |
| Progressor racstan/progressor-mcp Keeps an AI coding agent on its plan across context compression, with a live local dashboard. | |
| RacterMX racter-ciso/ractermx-mcp Manage RacterMX email forwarding — domains, aliases, webhooks, and more — via AI. | |
| RAD Security rad-security/mcp-server CP server for RAD Security, providing AI-powered security insights for Kubernetes and cloud environments. This server provides tools for querying the Rad Security API and retrieving security findings, reports, runtime data and many more. | |
| io.github.radiovisual/zoekt-mcp radiovisual/zoekt-mcp Fast indexed code search for AI agents, powered by Sourcegraph Zoekt. | |
| AgentTrust raditotev/agent-trust MCP Server for Agent Reputation & Trust Scoring | |
| DeepSeek Search Everywhere radoxtech/deepseek-search-everywhere-mcp Web search, page fetching and multi-source research via the DeepSeek Search & Fetch API. | |
| Call Me radres/call-me Your AI rings your iPhone, speaks its question, and gets your spoken answer back as text. | |
| infrastructure-mcp radumalica/infrastructure-mcp Give Claude Code, Cursor, and other AI agents safe access to your real infrastructure — without giving them raw SSH access. | |
| mcp-rae rae-api-com/rae-mcp Model Context Protocol (MCP) server for the Royal Spanish Academy (RAE) API. It allows language models to interact with RAE's dictionary and linguistic resources. | |
| io.github.RAEN-DT/pynet-mcp-bridge raen-dt/pynetbridge MCP implementation to connect AI agents with the PyNet Platform for BIM/Engineering automation. | |
| io.github.rafaelgaspar/longhorn-mcp rafaelgaspar/longhorn-mcp MCP server for the Longhorn distributed storage manager API, with a --read-only mode. | |
| Board Planner rafalpodles/board-planner Project board for teams and coding agents: Kanban, sprints, 46 tools, OAuth 2.1 or API tokens. | |
| Lingua Universale MCP Server rafapra3008/cervellaswarm Verify AI agent communication with session types and formal proofs | |
| io.github.rafavecchi/grantd rafavecchi/grantd Grantd MCP server: let your AI agent act on a user's behalf across third-party APIs via OAuth. | |
| io.github.rafe-walker/kronicle-lite rafe-walker/kronicle-lite Hash-chained local document store with signed receipts and an orient protocol for stale agent memory | |
| io.github.rafe-walker/sea-lite rafe-walker/sea-lite Work queue for parallel coding agents: leased path-scoped claims, typed links, hash-chained history | |
| io.github.Raffaele86/local-leads-mcp raffaele86/local-leads-mcp Find local businesses with no website via OpenStreetMap, then verify them. No API keys needed. | |
| io.github.Raffaele86/seo-stack-mcp raffaele86/seo-stack-mcp The complete open-source SEO data stack for AI agents: 7 sources, 86 tools, one MCP server | |
| mcp-context-condenser rafim-dev/mcp-context-condenser Enables AI coding agents to reduce token usage by condensing source code into AST skeletons, extracting specific symbols, compressing logs, and estimating token budgets. | |
| MCP Doctor rafim-dev/mcp-doctor Provides health checks, binary validation, and auto-repair for MCP configurations in Claude Desktop, Cursor, and Cline. | |
| Smart Git MCP Server & CLI rafim-dev/mcp-smart-git Enables AI assistants to perform Git workflows with semantic commit messages, pre-PR secret audits, conflict resolution, and release changelog generation. | |
| Schema Bridge MCP Server rafim-dev/schema-bridge-mcp Enables schema conversion from SQL/Prisma/JSON to Zod, TypeScript, and Pydantic, and generates realistic synthetic mock data. | |
| io.github.rafsilva85/skillflow rafsilva85/skillflow-mcp-server Search, discover, and install 500+ AI agent skills from the SkillFlow marketplace. | |
| RenewRoster raghuchinnannan/renewroster-mcp Track domain and SSL certificate expiry for your agency clients from any MCP client. | |
| Ragie Model Context Protocol Server ragieai/ragie-mcp-server An MCP server that enables AI models to retrieve information from Ragie's knowledge base through a simple 'retrieve' tool. | |
| io.github.RagingOrangutan/rootvine-mcp ragingorangutan/rootvine-mcp Neutral commerce resolution for AI agents — music live, ranked by trust, never by commission. | |
| io.github.ragionex/memory-mcp ragionex/memory-mcp Persistent memory for AI agents - save once, recall in every session, project and tool. | |
| io.github.rahuljava2807/claude-bridge-mcp rahuljava2807/claude-code-bridge-mcp Pipes Claude Code session output into Claude Chat — no more copy-paste between tools | |
| SaaS Puppy rahulparathy/saas-puppy-mcp Look up or compare free-tier developer tools, with the catch spelled out. | |
| ContextSmith rahulsankhla312/contextsmith Give your coding agent the right code: graph + hybrid search, packed into a token budget. Local. | |
| Think MCP Tool rai220/think-mcp An MCP server that provides a "think" tool enabling structured reasoning for AI agents, allowing them to pause and record explicit thoughts during complex tasks or multi-step tool use. | |
| io.github.RailKill/mcp-aider-executor railkill/mcp-aider-executor Model Context Protocol (MCP) server to execute aider-specific code editing operations | |
| io.github.railwayapp/mcp-server railwayapp/railway-mcp-server Official Railway MCP server | |
| Raily railyai/raily-mcp Raily personal-agent MCP with scoped reads and approved actions. | |
| DocPull raintree-technology/docpull Sync public web sources into cited context packs for AI agents, RAG, and MCP clients. | |
| io.github.Raistlin82/btp-sap-odata-to-mcp-server-optimized raistlin82/btp-sap-odata-to-mcp-server-optimized Enterprise SAP OData to MCP Server with AI capabilities and Cloud Foundry integration | |
| io.github.rajanrengasamy/vidlens-mcp rajanrengasamy/vidlens-mcp YouTube intelligence layer for AI agents. 41 tools, 10 modules, zero config. | |
| cadence rajanshxrma/cadence Provides Claude with real-time access to local health data including sleep, recovery, strain, and workouts from WHOOP and Apple Health, enabling informed context-aware interactions. | |
| io.github.Rajeev-Shyam/quellgeist-commits rajeev-shyam/quellgeist Read-only MCP server: get_recent_commits over a local deploy log (Quellgeist triage). | |
| GRACE Hello MCP rajitharul/grace-hello-mcp A very simple remote MCP server that greets you, with a custom icon. | |
| Oura-MCP rajskij/oura-mcp Ask your Oura Ring about sleep, readiness, activity, stress and heart rate in ChatGPT or Claude, in any language. Read-only, 10 task-oriented tools; runs in a sandbox demo mode with no credentials. |
17,001–17,050 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.