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 |
|---|---|
| Knot connectknot/knot-mcp Shared memory across ChatGPT, Claude, Cursor, and Gemini. OAuth 2.1 context & supersession. | |
| Syl Guardian connor274/syl-guardian-mcp Causal check on AI agent claims, from ad-spend/ROAS lift to any decision: pass, caution or hold. | |
| Syl Pulse connor274/syl-pulse-mcp Causal analytics: ask a business question, get a deterministic causal answer and charts. | |
| io.github.conquext/neuron conquext/neuron AI-powered WhatsApp chatbot platform with 196 tools for bots, campaigns, and contacts. | |
| io.github.constellation-works/orbit constellation-works/orbit Orbit's local-first task and workflow registry for coding agents. | |
| PropelAgent Studio contacto291/propelagentstudio AI agent platform: manage leads, conversations, bots, calendar and CRM via MCP. | |
| io.github.contactxyz-admin/morningform contactxyz-admin/morning-form stdio MCP proxy for MorningForm — bridges Claude Code to MorningForm HTTPS MCP server. | |
| ContactZapp contactzapp/contactzapp-mcp Keeps your contacts in sync across Google, Microsoft, Apple and CardDAV, and cleans up duplicates. | |
| AI Video Enhancer Studio contentasoftware/mcp-launcher Upscale, stabilize, denoise and raise the frame rate of videos locally on your NVIDIA GPU | |
| 3D CAD Converter contentasoftware/mcp-launcher Convert STEP, IGES, STL, OBJ, FBX, glTF and 3MF files on your Windows PC, one file or a folder | |
| Contenta Converter contentasoftware/mcp-launcher Batch-convert, resize and edit images on your Windows PC: 100+ formats, PDF albums, metadata | |
| Contenta Photo Converter contentasoftware/mcp-launcher Batch-convert, resize and edit images on your Windows PC: 100+ formats, PDF albums, metadata | |
| VideoRecompress Studio contentasoftware/mcp-launcher Shrink video files on your Windows PC with H.265/AV1 and GPU encoding, a whole folder at a time | |
| ESP32 Control contentforge-press/esp32-mcp Control ESP32 IoT devices from AI agents: status, GPIO, ADC, reboot. | |
| Tariff Data contentforge-press/us-tariff-data US stacked tariffs (MFN+301+232), daily-updated, Chinese labels, keyless, $49 x402 unlock | |
| Contentrain contentrain/ai Git content governance, 23 deterministic MCP tools. Hosted: docs.contentrain.io/developer/mcp-cloud | |
| Economic Statistics contentwriterco/economic-statistics-mcp Official economic statistics for AI agents: GDP, inflation, trade and debt for 150+ countries. | |
| Health Statistics contentwriterco/health-statistics-mcp Health statistics for AI agents: life expectancy, causes of death, health spending, WHO data. | |
| Labour Market Statistics contentwriterco/labour-market-statistics-mcp Labour market statistics for AI agents: unemployment, employment and wages for 150+ countries. | |
| Polish Company Financials contentwriterco/polish-company-financials-mcp Polish company financial statements for AI agents: revenue, profit, assets, rankings, benchmarks. | |
| Polish KYB contentwriterco/polish-kyb-mcp Know-your-business checks for Polish companies: KRS, owners, insolvency, sanctions, gazette notices. | |
| Polish Public Tenders contentwriterco/polish-public-tenders-mcp Polish public procurement for AI agents: BZP and TED tenders, awards, buyers and contractors. | |
| io.github.context-foundry/context-foundry context-foundry/context-foundry Recursive Claude spawning for autonomous project builds with self-healing test loops | |
| io.github.contextium-io/mcp-server contextium-io/contextium Your team's knowledge, always in context. SOPs, coding standards, and workflows for Claude. | |
| com.contextser.mcp/nodecel contextser/nodecel-cli Vibe deployment for nodecel — deploy, roll back, diagnose, and manage apps and domains from chat. | |
| Contracko contracko/contracko-skills AI contract management (CLM): contract review, data extraction, reminders and renewal deadlines. | |
| co.contraption/mcp contraptionco/mcp An MCP server that provides [describe what your server does] | |
| Control Plane controlplane-com/ai-plugin Control Plane (controlplane.com): deploy and operate workloads across AWS, GCP, Azure, and more. | |
| Convai Analytics conv-ai/convai-analytics Analyze Convai sessions, latency, reliability, usage, and provider telemetry via API key. | |
| io.converly/converly converly-conversion-tracking/converly-mcp Set up and manage conversion tracking by chatting with your AI assistant. | |
| Converra converra/converra-agent-kit Fix production agent behavior with tested changes and a production verdict on every fix. | |
| com.convexvalue/cvserver convexvalue/cvforge-docs Live US options chains with Greeks and IV, a screener, SQL, and FMP fundamentals. | |
| basebalance.cloud — x402 RPC & MCP gateway conway-research/automaton USDC-gated Base JSON-RPC: free 10 req/min, $0.50 per 10k. Failover, cache, /mcp, ledger. | |
| io.github.coo1white/cool-workflow coo1white/cool-workflow Signed, cited, replayable workflows for Claude, Codex, Gemini, DeepSeek, and other agents. | |
| NeoSatoshi Card Recognition cookiebreed/card-recognition-api Identify trading and football cards in a photo, search and correct them, with Cardmarket prices. | |
| Cookiy cookiy-ai/cookiy-skill AI user research via studies, interviews, recruitment, reports, and quantitative surveys. | |
| LoveMarkdown coolnico/markdown Markdown ⇄ Word (.docx) and Markdown → LaTeX. Native Word equations (OMML) restored as LaTeX math. | |
| StoriesFly: Instagram and TikTok data coolpac/storiesfly-api-client Live public Instagram and TikTok data for AI assistants: profiles, posts, stories, followers. | |
| LinkedIn MCP (by TalkToHumans) coolsapiens/linkedin-mcp The safest LinkedIn MCP: your Agents read DMs, search your network and draft messages you send. | |
| Etuki FinOps & LLM Pricing Oracle cooyun/etuki-gate Cryptographic 563-leaf LLM rate oracle, context-cliff auditor, and prompt cache optimizer. | |
| selvo cope-labs/selvo Linux CVE prioritisation: 16 MCP tools for scan, fleet, runtime, and PR-able fix discovery. | |
| Solana Security Standard copenhagen0x/solana-security-standard Scan Solana/Anchor code against the Solana Security Standard and serve the ruleset to MCP clients. | |
| io.github.copyleftdev/fabric-atelier copyleftdev/fabric-atelier AI-powered content processing with 226 Fabric patterns for writing, analysis, and code generation. | |
| CoralSwarm Connect coralswarm/coralswarm-connect Search and save your coding work in a CoralSwarm ocean: sessions, decisions, meetings. | |
| io.github.CordilleraSarl/clearotron cordillerasarl/clearotron Clearotron — trademark clearance that shows its work | |
| Cashly core-nexis/cashly Personal finance tracker: log expenses and income, track EMIs, debts, subscriptions and bills. | |
| CoReason Ecosystem — Federated MCP Gateway coreason-ai/coreason-ecosystem CoReason Tripartite Architecture Governance Plane. Stateless zero-trust federated MCP gateway. | |
| Corebee Customer Support corebee-ai/corebee-plugin Hosted support inbox over MCP: answer web chat, WhatsApp, email and SMS, manage knowledge. | |
| Coredence coredence/coredence Query a measured identity: its rules, the evidence behind each one, and the topics they belong to. | |
| io.github.coregentdevspace/sql-server-analyst-mcp coregentdevspace/sql-server-analyst-mcp Read-only SQL Server Analyst MCP — safe schema, stored procedure, and performance analysis. |
21,901–21,950 of 50,909
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.