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 |
|---|---|
| TheFaceAnalysis the-face-analysis/thefaceanalysis-mcp Face shape rules and a 102-face open measurement dataset. Read-only, no photos. | |
| specpack the-kipdev/specpack Audit and write CLAUDE.md / AGENTS.md / Cursor rules; generate full build specs for new projects. | |
| Webhook Toolkit the-kipdev/webhook-toolkit Webhook URLs for AI agents: receive, wait for, replay, sign and verify webhooks (Stripe, GitHub…). | |
| dev.wpagent/wpagent-mcp the-kipdev/wpagent-mcp Manage WordPress & WooCommerce from any MCP client — 58 tools over a signed REST API. | |
| Apple Health MCP Server the-momentum/apple-health-mcp-server A Model Context Protocol server that enables seamless interaction between LLM-based agents and Apple Health data, allowing users to query, analyze, and manage health records through natural language commands. | |
| FHIR MCP Server the-momentum/fhir-mcp-server Enables LLM-based agents to interact with FHIR healthcare data through natural language prompts, providing full CRUD operations on FHIR resources, document processing, and semantic search capabilities. | |
| io.github.the-nine-nation/remote-ssh-mcp the-nine-nation/remote-ssh-mcp Persistent stateful remote SSH sessions for AI agents via MCP + OpenSSH. | |
| io.github.The-OpenROAD-Project/openroad-mcp the-openroad-project/openroad-mcp The OpenROAD MCP server - interactive EDA sessions via Model Context Protocol | |
| io.github.The-Pixel-Boys/shield-kya the-pixel-boys/shield-kya Audit trail and traceability for AI agents. MCP gate: evaluate, ingest, request approval. | |
| io.github.the-staq/tradestaq-mcp the-staq/tradestaq-mcp AI-powered crypto trading tools. Strategies, backtests, bots, and portfolio management. | |
| Anvil the-warl0ck/anvil-mcp Local physics/chemistry bench as MCP: plain words in, 12-domain simulations out. | |
| Harvest the-warl0ck/harvest-mcp Plain-English training-data scout: 12 experts sweep HuggingFace + GitHub, compose scored packs. | |
| geeknews-mcp-server the0807/geeknews-mcp-server This project is a Model Context Protocol (MCP) server that fetches articles from GeekNews. It is implemented in Python, and performs web scraping using BeautifulSoup. | |
| Agent News by The Agent Times theagenttimes/agent-news Verified, sourced, real-time intelligence layer for AI agents. | |
| The Agent Times MCP Server theagenttimes/tat-mcp-server Query breaking news, verified statistics, and editorial analysis from The Agent Times directly from any AI agent via MCP. | |
| Emfirge theanshsonkar/emfirge Git branch for your cloud. Understand AWS risk, prove fixes, and ship safer changes. | |
| com.ratchetgate/ratchet thearchitect0x-glitch/ratchet Your agent asks before it acts, so the same real-world action is attempted at most once. | |
| InvoiceBloom theasteve/invoicebloom-mcp Create, send and track invoices for freelancers and small businesses. | |
| MIND theastraway/mind-mcp-server MIND knowledge-graph memory for agents. 44 tools: CRM, Life, MoneyMIND, Budget, Sheets, Email, Sign. | |
| io.github.Backers-Shawn/pplz-agent thebackers/pplz-agent PPLZ AI Agent — Let AI play your social life simulation automatically. | |
| io.github.TheBarmaEffect/glassbox-framework thebarmaeffect/glassbox Runtime constitutional verification for AI answers — claim reasoning, ECS, red team, audits. | |
| io.github.TheBaronofAI/okaneland-mcp thebaronofai/okaneland-mcp Verified AI-tool prices and AI product margin math for agents. | |
| io.github.thebasedcapital/brainbox thebasedcapital/brainbox Hebbian memory for AI agents. Learns file patterns, predicts next tools, saves tokens. | |
| io.github.thebriangao/totem thebriangao/totem Totem — talk to your wearables with AI. Today: full Whoop access (48 tools). | |
| The Stall thebrierfox/the-stall x402 capability chassis: 170+ AI-callable, pay-per-call data tools (US/global equities, crypto/DeFi, prediction markets, gov/legal, research, infra) settled in USDC on Base mainnet via the Coinbase CDP facilitator. No API keys or accounts — | |
| io.github.TheBurdz/amz-vault theburdz/amz-vault-mcp Amazon Seller Central + Ads: settlement-accurate P&L, full PPC, every write staged for approval. | |
| CV Forge thechandanbhagat/cv-forge Forge powerful, ATS-friendly CVs tailored to any job - an MCP server for intelligent CV generation | |
| Quantified Self MCP Server thecimal/quantified-self-mcp Privacy-first MCP server for querying personal health and finance data with AI. Built with Python, FastMCP, and SQLite. Local-first and open source. | |
| cc.thecolony/mcp-server thecolonycc/colony-mcp-server Remote MCP server for The Colony — a social network for AI agents (posts, DMs, search, marketplace). | |
| io.github.thecolourfoundation/rune thecolourfoundation/rune Evidence-backed codebase understanding with file:line citations, for AI clients over MCP. | |
| com.thecryptoport/cryptoport-port thecryptoport-mcp/cryptoport-port Daily board of what crypto YouTube channels said: coin calls, stances, catalysts. Free, no key. | |
| io.github.TheDesignFounder/dreamlayer thedesignfounder/dreamlayer-mcp Generate and edit images, remove backgrounds, upscale, and create sprite sheets through DreamLayer. | |
| io.github.thedhruv-07/github-repo-mcp thedhruv-07/github-repo-mcp MCP server for GitHub repo health, commit summaries, issue triage, and RAG Q&A. | |
| DocStoX thedocstox/docstox-plugin Indian stock research on real NSE and BSE data: fundamentals, screens, FII flows and F&O. Read-only. | |
| io.github.theduodecim/ascii-art theduodecim/ascii-art-mcp MCP server that exposes ASCII and Unicode art tools | |
| Moonscroll thefedoration/moonscroll-mcp Short Form Video Insights for Instagram, TikTok, Shorts | |
| MeshVault Connectors thefiredev-cloud/meshvault-connectors Read-only tools: EMS protocols, courts and judges, NPI and FDA data, GPU fit for open models. | |
| ConferenceCaptioning thefirstprototype/confcapmcp Read live captions, saved transcripts and audience questions from your ConferenceCaptioning events. | |
| network.flint/agent-transaction-control thefraudfather/flint-plugin Issue Agent Passports and verify agent authority before value moves. Signed verification records. | |
| com.kazejev/profile theglobe/profile-mcp Profile server for kazejev.com: biography, skills, projects and education. | |
| io.github.thegoldbarometer/thegoldbarometer thegoldbarometer/mcp-server Today's gold buying-conditions score (0-100), its published history, and what followed since 1971. | |
| The Living Bread thegoodfruit/living-bread-mcp Scripture with evidence labels, churches and prayer near you, crisis lines first. Jesus is Lord. | |
| io.github.thegoodguysla/myco-brain thegoodguysla/myco-brain Shared, source-backed memory for AI agents on your own Postgres, with an optional document engine. | |
| io.github.thegridwork/aiact thegridwork/aiact Scan codebases for AI usage, classify risk, generate EU AI Act compliance reports. | |
| io.github.thegridwork/license thegridwork/license Scan dependencies for license compliance — copyleft conflicts, unknown licenses, risk. | |
| io.github.thegridwork/privacy thegridwork/privacy Audit websites for GDPR, CCPA, and ePrivacy compliance — trackers, consent, and policies. | |
| io.github.thegridwork/siteaudit thegridwork/siteaudit Audit websites for accessibility, performance, SEO, design, and mobile. 47 WCAG checks. | |
| GEO Audit (AI Search Visibility) theharrisontruong-web/agent-apis Scores any URL's AI-search visibility with concrete fixes. $1.50/call via x402. | |
| Clarity MCP thehealthai/clarity-mcp Condition-aware ingredient & product safety intelligence for AI agents. Every answer carries a claim-level evidence attestation, verdict, an evidence tier, and a citation – curated against authoritative sources (LactMed, InfantRisk, PubMed, | |
| Constat — 483 Risk Radar thehealthai/fda-risk-radar-mcp The MCP server behind Constat — FDA & NHTSA regulatory-risk intelligence for AI agents, over the Model Context Protocol. Live public regulatory data — recalls, adverse events, warning letters, 510(k) premarket evidence, postmarket drift sig |
19,401–19,450 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.