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.mshegolev/allure-testops-mcp mshegolev/allure-testops-mcp Allure TestOps MCP — projects, launches, test cases, test results via REST API. | |
| io.github.mshegolev/harbor-registry-mcp mshegolev/harbor-registry-mcp Harbor Registry MCP — projects, repos, artifacts, storage reports, cleanup (with dry-run). | |
| io.github.mshegolev/kibana-mcp mshegolev/kibana-mcp Kibana/Elasticsearch MCP — log search, aggregations, index discovery, dashboards. | |
| io.github.mshegolev/prometheus-mcp mshegolev/prometheus-mcp Prometheus MCP — query metrics, inspect alerts, and explore scrape targets (read-only). | |
| io.github.mshegolev/sonarqube-mcp mshegolev/sonarqube-mcp SonarQube MCP — projects, metrics, quality gate, issues, worst-metric ranking. | |
| io.github.MShekow/package-version-check-mcp mshekow/package-version-check-mcp Returns the latest package / dependency / tool versions for Python, NPM, Go, Docker, Helm, etc. | |
| Multimeter mshobeyri/multimeter Scaffold, validate, format, and run YAML .mmt API tests. Do not invent syntax. | |
| MMW Managed Memory Workspace msingatullin/mmw-mcp One memory for AI agents in Claude Code, Cursor, Codex and ChatGPT that flags conflicting facts. | |
| AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance msmd-rua/agenticrail-mcp Deterministic runtime enforcement of step order for AI agents: ALLOW/DENY before a step runs. | |
| ConnectWise PSA mspstack/mcp-connectwise-psa ConnectWise PSA (Manage) MCP server — tickets, time entries, companies, configurations, BYOK | |
| IT Glue mspstack/mcp-itglue IT Glue MCP server for MSPs — documents, flexible assets, semantic vector search, RBAC, and BYOK | |
| Microsoft Planner mspstack/mcp-planner Microsoft Planner MCP server — plans, buckets, tasks via Microsoft Graph, ETags handled | |
| io.github.mstang/casemgr-mcp mstang/casemgr-mcp Shared workspace your AI agent writes to. 184 tools, persistent memory, semantic search. | |
| Grill mtangoz/grill A second opinion from an unrelated AI model before you commit to a decision. | |
| io.github.mtbun/storeshots-mcp mtbun/storeshots-mcp Render store-ready App Store and Google Play screenshots: device frames, headlines, exact sizes. | |
| MTContext mtcontext/mtcontext-quickstart Connect any MCP client to MetaTrader 4/5 to read prices, manage positions, and place trades. | |
| ScreenPilot mtehabsim/screenpilot Enables LLMs to take full control of your device by providing screen automation tools for capturing, clicking, typing, and scrolling, ideal for automation and education. | |
| Booking.com Hotel Search (Live Prices) mtnrabi/google-flights-mcp Live Booking.com hotel prices, plus per-country pricing for rate-parity monitoring. | |
| The High Council muad-yasin/the-high-council-mcp Several models from different labs plan in a blind proposal, debate and review loop. Your own keys. | |
| GMail Manager MCP muammar-yacoob/gmail-manager-mcp Connects Claude Desktop to your Gmail so you can start managing your inbox using natural language. Bulk delete promos & newsletters, organize labels and get useful insights. | |
| MIZAN · Proof before payment muaviamohammed/mizan-mcp Check before you pay. Prove to get paid. Signed answers on any agent, against your own bar. | |
| io.github.muba00/gitstandup muba00/gitstandup Generate daily standup notes from git commits across multiple repositories with AI summaries. | |
| Légifrance (unofficial) muchiny/mcp-legifrance Unofficial MCP server for French law via the Légifrance API (PISTE): search, read and cite texts. | |
| Vouched muditjuneja/vouched SEO data your AI can cite: Search Console, GA4, keywords, backlinks, SERPs and AI visibility. | |
| forge-delegate muhamadbarzani/forge-delegate Delegate coding tasks from Claude Code, Codex or opencode to any model opencode can run. | |
| io.github.MuhammadTalhaMT/intercom muhammadtalhamt/claude-intercom Relays messages between two Claude Code sessions on different machines using the Channels API | |
| rest_api_mcp muhammed-abdelghany/rest_api_mcp A Model Context Protocol (MCP) server for authenticated REST APIs.
Drop it into any project, point it at your API, and let AI agents call endpoints — with auto-login, 2FA support, Swagger spec fetch, and fuzzy endpoint search — all without | |
| io.github.muhammetali/asc-mcp-server muhammetali/asc-mcp-server App Store Connect MCP Server for AI coding agents | |
| io.github.muhammetali/gpc-mcp-server muhammetali/gpc-mcp-server Google Play Console MCP Server for AI coding agents | |
| io.github.muhammetali/recraft-mcp-server muhammetali/recraft-mcp-server Recraft AI Image Generation MCP Server for AI coding agents | |
| io.github.Muhandis-online/rls-check muhandis-online/rls-check Read-only Supabase RLS check: explains in Arabic which tables anyone can read or change. No keys. | |
| git-context-mcp muhannad-hash/git-context-mcp git blame tells you who wrote a line. This tells you why. | |
| mcp-shield muhannad-hash/mcp-shield The MCP ecosystem is growing fast. Not every server on npm is safe. mcp-shield lets Claude audit any MCP server — local or from npm — before you trust it with your files, keys, and context. | |
| oraclemcp muhdur/oraclemcp Engine-free, governed Oracle Database MCP server with a fail-closed SQL guard (unofficial). | |
| MentionsAPI MCP Server mukul-dutt/mentionsapi-mcp Enables AI agents to check brand mentions across AI search surfaces like ChatGPT, Claude, Gemini, Perplexity, and Google AI Overviews using natural language queries. | |
| Noonlaunch mukund1158/noonlaunch-mcp Launch a product on Noonlaunch, search its directory and weekly winners, and find 333 launch sites. | |
| io.github.MukundaKatta/agentcast mukundakatta/agentcast-mcp Structured-output enforcer: extract and validate JSON from messy LLM text. | |
| io.github.MukundaKatta/agentfit mukundakatta/agentfit-mcp Token-aware message truncation: fit a chat history into your model's context budget. | |
| io.github.MukundaKatta/agentguard mukundakatta/agentguard-mcp Network-egress firewall for agent tools: check URLs against a declarative policy. | |
| io.github.MukundaKatta/agentsnap mukundakatta/agentsnap-mcp Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions. | |
| io.github.MukundaKatta/agentvet mukundakatta/agentvet-mcp Validate tool-call args before execution. Returns LLM-friendly retry hints. | |
| io.github.MukundaKatta/streamparse mukundakatta/streamparse-mcp Parse partial / truncated / messy JSON for LLM tool calls and structured outputs. | |
| MultiversX MCP Server multiversx/mx-mcp Enables interaction with the MultiversX blockchain, allowing users to create wallets, check balances, and send or issue tokens (EGLD, Fungible, SFT, NFT, MetaESDT) through natural language. | |
| pharo-smalltalk-interop-mcp-server mumez/pharo-smalltalk-interop-mcp-server MCP server to communicate local Pharo Smalltalk image | |
| mumo mumo-chat/mumo-mcp Multi-model deliberation over MCP: full responses plus typed cross-model reactions from other labs. | |
| Wasilah mumullickm/wasilah-mcp Prayer times, Qibla, Hijri calendar, 99 Names, Quran audio, Bangladesh offsets. English + Bengali. | |
| chat-recall munhq/chat-recall One searchable history across every AI coding tool, with secret scanning and a shared task board. | |
| cloud-tools munhq/cloud-tools Multi-cloud cost, inventory and waste analysis over MCP: AWS, GCP, Cloudflare and OVH. | |
| codeindex munhq/codeindex Structural code intelligence over MCP: symbols, callers, imports and blast radius, 40+ languages. | |
| distil munhq/distil Context optimization for LLM agents: tool registry, result masking, budgeting, compaction. |
13,451–13,500 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.