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 |
|---|---|
| ESQ Builder ESQ 1.0 题库包工具链（墨题刷题机）：build(auto_fix) → validate(双轨校验) → upload/publish + kajweb 词表解析与热点词统计 | |
| io.github.OraclesTech/guardian-mcp Runtime AI-threat screening for coding agents: analyze, scan tool calls/outputs & docs (paid). | |
| FAR Oracle Search Federal Acquisition Regulations (FAR) for government contracting. | |
| io.github.DareDev256/fcpxml-mcp-server Final Cut Pro automation: 15 grouped tools, 102 operations. FCPXML edit, QC, transcript, preview. | |
| FineRx US Rx prices by pharmacy near you + free discount card; foreign-brand equivalents; 12 languages | |
| io.github.arikanatakan/finvariant-mcp Financial-statement integrity checks (footing, tie-out) for AI agents. | |
| io.github.ramalamadingdong/first-agentic-csa FRC documentation MCP server for WPILib, REV, CTRE, Redux, and PhotonVision. | |
| FIVE Persona Engine 160K deductive JSON persona constraints. 0 drift breaks in 120 turns. Free API, no key. | |
| Flieber Your Flieber account in your AI assistant: sales, forecast, inventory, replenishment and more. | |
| foragekit Epistemic foraging for AI agents: source discovery, verified evidence, uncertainty-aware briefs | |
| Genome Industrial Intelligence Industrial intelligence for AI agents. Conviction scores and diligence for 10,000+ industrials. | |
| GeoEDGE MCP Geospatial analysis: vector and raster GIS operations, cartographic maps, spatial data access | |
| Percept — Ambient Voice Intelligence Give your AI agent ears — ambient voice intelligence with 8 MCP tools for Claude Desktop | |
| gjalla Self-curating shared memory that keeps your agents working like a high-performing team | |
| io.github.CSOAI-ORG/gos-claim-validator-mcp Validate NHS General Ophthalmic Services (GOS) claims pre-submission. Catches errors in GOS 1-6 | |
| io.github.CSOAI-ORG/grabhire-ai-mcp GrabHire.AI MCP server. UK grab lorry + tipper hire. Tools: estimate load volume, get grab lorry... | |
| HomeShed Every tool your AI needs in one self-hosted install: memory, reasoning, git, Docker and more. | |
| US HTS Code Lookup Look up, validate and search US HTS tariff codes offline: official text, duty rates, closest code. | |
| Iceberg MCP Server MCP Server for Apache Iceberg | |
| InnoDay Unified ticketing MCP server for Jira, Linear, Trello, Notion, and GitHub Issues. | |
| ITHZ MCP Local deterministic project memory for AI agents with context packs, gates and checkpoints. | |
| Jev MCP Server MCP server for Jev (TypeSafe System One): typed decisions with calibrated probabilities. | |
| Jitters the VibeCoder How wrecked is your monkey? Jitters' mood from the hours of your own git commits this week. | |
| JUBA — Jurisprudencia de Buenos Aires Search Buenos Aires Province court rulings: summaries, full text, legal topics | |
| JusCABA — Justicia CABA Search Buenos Aires City courts: cases, proceedings, parties, and PDF downloads | |
| io.github.Kali123411/k402 Agent-payable APIs on Kaspa: LLMs, chain data, covenants, zk proofs — pay per call, no API key | |
| Binance Spot (security-first) + crypto analyst Security-first Binance Spot MCP + honest crypto analyst. 25 tools, 5 prompts, human-gated orders. | |
| io.github.petrmasa/key-drivers-mcp MCP server for key driver and feature importance analysis based on rule mining | |
| io.github.CSOAI-ORG/keystone-verify-proxy-mcp VM-side verify proxy for keystone attestations | |
| KLO Mobility Quote Route options, fare estimates, ETA, and ride deeplinks via the KLO Mobility A2A agent. | |
| The Korova Milk Bar Agent-only collaboration space: pass the door, then use rooms, DMs and verifiable chains. | |
| Binance (security-first) + crypto analyst Security-first Binance MCP. 26 tools, human-confirmed spot trades, offline quant research. | |
| ai.lakewave/lakewave-mcp Verified B2B contacts at named accounts, email verdicts, contract signals and drafted campaigns. | |
| io.github.degibug-del/laserbrain The drift harness as an MCP server. Offline, no key — a fixed reference an agent checks against. | |
| io.github.lightnet19/lightbill-mcp-server LightBill ISP billing MCP server: 134 tools (customers, routers, OLT, invoices, payment). | |
| ai.linkguard/linkguard-mcp Backlink tools for AI assistants: redirect, Google index, and backlink health checks. | |
| io.github.gauravfs-14/lit-mcp MCP server for academic literature databases (arXiv, DBLP) to accelerate research using LLMs. | |
| LucidLink Read, write, search, lock and audit files in LucidLink filespaces, plus workspace admin tools. | |
| io.github.soufianetahiri/mception Audits other MCP servers for security risks. Returns safe / caution / unsafe / inconclusive. | |
| MCP Anvil Local MCP gateway daemon: route, audit, and inspect MCP servers from one config. | |
| io.github.trickyfalcon/mcp-defender Execute KQL queries against Microsoft Defender Advanced Hunting via natural language. | |
| io.github.qkrehgk1-wq/mcp-korea-worklife Korean calculators: salary take-home, severance, jeonse-rent, annual leave, VAT, pyeong. | |
| MCP KQL Server Execute KQL in AI prompts via NL2KQL with schema discovery and Azure Data Explorer integration | |
| io.github.trickyfalcon/mcp-msdefenderkql Execute KQL queries against Microsoft Defender Advanced Hunting via natural language. | |
| AWS MCP Server A managed MCP server enabling AI agents to access AWS using docs, API calls, and SOP workflows. | |
| com.cognivators/mcp-safeguard MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning. | |
| io.github.CSOAI-ORG/mcp-scorecard-mcp Score any MCP server against a 100-point production-readiness rubric (static AST + PyPI +... | |
| io.github.NeerajG03/vector-memory Semantic document memory using Redis vector store. Save and recall files with natural language. | |
| Stata MCP Server A lightweight MCP server for Stata. | |
| io.github.ONSBR/tiago-dados-abertos MCP server que conecta agentes de IA aos dados abertos do ONS (Operador Nacional do Sistema) |
47,701–47,750 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.