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.jcislo/moltalyzer-mcp jcislo/moltalyzer-mcp Polymarket prediction-market intelligence + AI, GitHub & narrative feeds for agents, via x402. | |
| io.github.Jcorderop02/packet-tracer-mcp jcorderop02/packet-tracer-mcp MCP server for Cisco Packet Tracer 9 — live IOS, OSPF, BGP, NAT, VLAN, VoIP, QoS, IPv6, wireless. | |
| AtpMcp jcschuster/atpmcp Theorem provers for agents: SystemOnTPTP, StarExec, Isabelle and local ATPs, with SZS verdicts. | |
| io.github.jcucci/dotnet-sherlock-mcp jcucci/dotnet-sherlock-mcp .NET assembly introspection MCP server with advanced reflection and type analysis capabilities | |
| Flaim Fantasy jdguggs10/flaim-fantasy Fantasy analysis for your ESPN, Yahoo, and Sleeper leagues. Reads your leagues, never changes them. | |
| com.energyaisolution/solar-home-incentives jdhart81/energyai-mcp Solar and home energy discovery: estimates, incentive sources, guides and contractor options. | |
| io.github.jdhart81/viridisos jdhart81/viridis-agent-fleet ViridisOS — theorem-backed conservation certification + the unified trust root/mark/toll. Certify pa | |
| K8gentS — Kubernetes RCA MCP Server jdoornink/k8gents Kubernetes RCA agent that sandboxes its own AI with OPA Gatekeeper. MCP-ready for any client. | |
| io.github.JdPG23/market-data-toolkit-mcp jdpg23/market-data-toolkit-mcp 19 market-data tools for AI agents: company KYC, SEC filings, patents, auctions, tenders | |
| ClearMarket jdsource/clearmarket Reference data for prediction markets: graded resolution clarity, cross-venue links, provenance. | |
| io.github.jdw2111/propraven jdw2111/propraven-mcp Property intelligence: 180M+ US parcels — lookup, search, owners, hazards, permits, deeds. | |
| io.github.jean-johnson-zwix/arm-code-mcp jean-johnson-zwix/arm-code-mcp MCP server for Arm64 Linux performance: parse perf output, suggest NEON intrinsics, audit deps. | |
| codemem jeang42/codemem Shared memory for coding agents: projects, reusable code, sessions and commits across machines | |
| Homebrew MCP Server jeannier/homebrew-mcp A Model Context Protocol server that enables interacting with the Homebrew package manager on macOS through natural language, supporting commands like install, search, info, and doctor. | |
| Memento jee1/memento Agent memory MCP server with 4-type cognitive memory, hybrid search, and TTL-based forgetting. | |
| Audiobookshelf MCP jeeftor/abs-mcp Inspect and safely operate Audiobookshelf libraries over MCP. | |
| MCP Test Utils jeenyjai/mcp-test-utils Desktop UI automation for AI agents: verified clicks, UI Automation, OCR, scenario runs, recording | |
| io.github.jeet-dhandha/agent-webbridge jeet-dhandha/agent-webbridge Drive your real, logged-in Chrome (many profiles, parallel tabs) from any MCP client. Local only. | |
| io.github.jeet0007/mac-voice-mcp jeet0007/mac-voice-mcp Talk with your AI assistant out loud on a Mac, with on-device speech recognition (whisper.cpp). | |
| Idea to Motion jeetsoni/ideatomotion-mcp Make animated videos by asking Claude, Cursor or any MCP client. Your AI writes it, we render it. | |
| EzVerify Email Verification jefferyleo/ezverify-mcp Verify email addresses with EzVerify. Needs an EzVerify Starter or Business plan. | |
| io.github.Jegoba90/cryptocapi jegoba90/cryptocapi-mcp Análisis de mercado cripto con sello verificable: cada motor firma su análisis con SHA-256. | |
| ai.smithery/jekakos-mcp-user-data-enrichment jekakos/mcp-user-data-enrichment Enrich user data by adding social network links based on provided personal information. Integrate… | |
| EU Audit Trail jellewas/eu-audit-mcp Tamper-evident audit trail MCP server for EU AI Act & GDPR compliance. | |
| Switchboard jemplayer82/mcp-switchboard Self-hosted MCP message bus: agents DM each other, broadcast to channels, and track presence. | |
| TickTick MCP Server jen6/ticktick-mcp An MCP server that enhances TickTick workflow by providing comprehensive task management tools with improved filtering capabilities, allowing AI assistants and MCP-compatible applications to interact with TickTick tasks with greater precisi | |
| io.github.jeneric/stig-mcp jeneric/stig-mcp MCP server: MITRE ATT&CK® -> NIST 800-53r5 -> DISA STIG fix/check steps, mitigations and detections | |
| ai.smithery/jenniferjiang0511-mit-ai-studio-hw3 jenniferjiang0511/mit-ai-studio-hw3 Greet people by name and check local forecasts and weather alerts across the U.S. Switch to a play… | |
| mifit jenwein/mifit Read-only access to your own Mi Fitness (Xiaomi) data: sleep, heart rate, steps, workouts | |
| io.github.jeongho54/loadbench jeongho54/loadbench-mcp MCP server for structural load & stability math: tipping, support reactions, beam checks. | |
| io.github.jeonghun917/readfirst jeonghun917/readfirst What to read and check before changing a file: project rules, risks, checks and tests per file. | |
| tossinvest-openapi-mcp jeongseongmok/tossinvest-openapi-mcp MCP server for exploring and integrating Toss Securities Open API, providing tools to browse endpoints, schemas, and generate code samples. | |
| Finance Toolkit jerbouma/financetoolkit 200+ transparent financial metrics calculated from raw statements, not third-party endpoints. | |
| io.github.jeresalmisto/calcfi-mcp jeresalmisto/calcfi-mcp 24 free personal-finance + macro tools (mortgage, paycheck, tax, FRED, BLS) for LLM agents. | |
| tossinvest-mcp jeric1223/tossinvest-mcp A read-only MCP server for Toss Securities Open API that enables AI assistants to retrieve stock prices, resolve symbols, check holdings, buying power, exchange rates, and OHLCV candles without placing orders. | |
| Tidesman jeronimocolon/tidesman-mcp A free native MCP server for running and debugging Linux containers with Apple's container tool. | |
| ALUN-ALUN jerponhr/alun-alun Indonesian-language square for AI agents. Register once to read or write; daily quotas; ledger. | |
| io.github.jerrysrodz/goldhold jerrysrodz/goldhold-mcp-server Persistent memory for AI agents. Search, store, and recall across sessions. | |
| Taoyuan Music jerryyangai/taoyuan-mcp Write an original song for one person: lyrics, two full versions and cover art in about a minute. | |
| Hermes Plant — Agent Commerce Assurance jessegdotio/hermesplant-mcp-server Preflight, approve, and prove consequential agent actions with signed evidence and x402 tools. | |
| io.github.jessepetersondev/consentgate-mcp jessepetersondev/consentgate-mcp Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed. | |
| ai.smithery/jessicayanwang-test jessicayanwang/frankfurtermcp Fetch latest and historical currency exchange rates from Frankfurter. Convert amounts between curr… | |
| Booboo jessymariau/booboo Query your AI system's wiring, knowledge, memory, agents and crons as one rooted graph over MCP. | |
| honest-cv jesuscabrerareveles/honest-cv Honest, ATS-safe CVs and cover letters from a skill inventory you confirm yourself. | |
| io.github.JesusGarcia9009/lethe jesusgarcia9009/lethe-engineering Context GC for LLM agents: offload large tool outputs and recall them to save tokens. | |
| JetAPI jetapi/jetapi-mcp-server Send WhatsApp, Telegram, SMS and MAX messages, files and bulk mailings via JetAPI | |
| com.jettyd/mcp jettydiot/jettyd-mcp Connect AI agents to IoT devices — read sensors, send commands, manage ESP32 fleets. | |
| WhatsApp Messaging API jevil25/whatsapp-messaging-api-mcp Send WhatsApp messages from Claude. No Meta Business approval or WhatsApp Business account. | |
| Blocksize Market Data jf-cmyk/blocksize-agentic-payments-mcp Read-only MCP server for Blocksize real-time market data: crypto VWAP, bid/ask, FX, metals and tokenized equities, with pricing, coverage and x402 endpoint lookup. Signed-in users of the Claude, ChatGPT and Cursor connectors get 30,000 free | |
| io.github.jfarcand/mirroir-mcp jfarcand/mirroir-mcp Drive a stock iPhone via iPhone Mirroring: no Developer Mode, Xcode or WDA. LLM-free skill replay. |
9,651–9,700 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.