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 |
|---|---|
| com.octo-dock/octodock chaosmibu-blip/octodock One MCP URL for all your apps. 600+ actions for AI. | |
| io.github.chaoz23/king-county-permit-status chaoz23/king-county-permit-status Live permit history + status for any King County, WA address, parcel or permit number. Read-only. | |
| RepoLens chapibunny/repolens Architecture docs from a repo: overview, modules, API surface, routes, dependency graph, diffs. | |
| Dietary Supplement Analysis (NIH data) chariot-ventures/dietary-supplement-analysis NIH supplement checks: upper limits, drug and herb interactions, FDA recalls, with citations. | |
| CharityVerify charity-verify-admin/charity-verify-engine Look up trust grades, donor verdicts, and analysis for 138,000+ Canadian charities. | |
| PoeMCP — Path of Exile game data charleslucas/poemcp MCP server for Path of Exile game data: wiki, economy, and Craft of Exile lookups | |
| HobbyCardIndex Card Prices charmanroofing-pixel/hci-api-examples Real sold prices for 16M+ sports and trading cards: raw and graded by grade, with card page links. | |
| EconomyOS charvai/economyos Agents-only x402 economy on Base + Solana testnets: identity, swaps, invoicing, streaming. | |
| Agent Lab Deploy chatbotgang/franky Deploy websites, apps, agents and MCP servers from Claude Code or Codex. OAuth, runs in Taiwan. | |
| ChatCut chatcut-inc/agent-plugin AI video editor for agents: cut footage, add captions and motion graphics, export editable edits. | |
| Chatway Live Chat chatway-app/chatway-mcp-server Connect ChatGPT, Claude & AI agents to Chatway live chat to reply to customers and manage tickets | |
| io.github.chaytanc/reality-next-door-walk chaytanc/longshore Walk a cited post-extraction Seattle as an MCP world: go(), talk_to(), do(). Read-only, untracked. | |
| CheckFlow checkflowio/checkflow-mcp Run checklists, complete tasks and build process templates in your CheckFlow workspace. | |
| Checkout.com checkout/checkout-mcp Search Checkout.com docs and API reference, plus manage payments, refunds, and payment links. | |
| io.github.checkra1neth/xbird checkra1neth/xbird Twitter/X MCP server — 30 tools with x402 micropayments. Runs locally from your IP. | |
| io.github.cheedli/doubleoh-mcp cheedli/doubleoh The fix desk for AI agents: human fixes become skills the whole fleet reuses. | |
| FHIR Scorecard chelseakr/fhir-scorecard Read-only grades for publicly observable FHIR endpoints, served from the published dataset. | |
| GTFS Scorecard chelseakr/gtfs-scorecard Read-only GTFS transit feed scorecards: grades, plain-language fixes, and history. | |
| X4CodeSense chemodun/x4codesense X4: Foundations scripts: checks, schema elements, expression types, scripts, cues and texts. | |
| HaoyouBox Publish cheng-big/haoyoubox-agent-skill Publish local HTML or Markdown as expiring password-protected HaoyouBox links. | |
| ThoughtDAG chenxiachan/thoughtdag Search local AI conversations by file or phrase and recall source turns. Four read-only tools. | |
| MCP Browser cherchyk/mcpbrowser Browser automation using the user's Chromium session — JS execution, auth, and anti-bot support. | |
| io.github.chernistry/bernstein chernistry/bernstein Declarative agent orchestration for engineering teams | |
| Cavyro cherry-it/cavyro-mcp Telegram-native CRM for agents: contacts, deals, projects, tasks, campaigns, docs and reports. | |
| UK Data API chetparker/uk-property-api 24 UK data endpoints — property, weather, companies, vehicles, finance. Paid via x402. | |
| Chewable Foodie chewablefit/foodie-plugin Your recipes, family meal plan and shopping list from Foodie, in ChatGPT, Claude and Codex. | |
| io.github.danieljperry/chia-mcp chia-network/chia-mcp MCP server for the Chia blockchain. Read-only full-node access via Coinset hosted nodes, 36 tools. | |
| DiscreteRate chiaha-ai/discreterate-site Run DRS demos (Fast-Slow Drain, Hamburger Duo, Valdez Tanker) and explore the paradigm. | |
| QSimHealth chiaha-ai/qsimhealth-site Healthcare staffing simulator — ED, walk-in clinic, and appointment office DES tools. | |
| QueueSim chiaha-ai/queuesim-site Run M/M/c queue simulations and four scenarios (call center, ER, coffee shop, single server). | |
| ReliaSim chiaha-ai/reliasim-site Reliability and bottleneck simulation for manufacturing lines; run experiments, sweep buffers. | |
| ReliaStats chiaha-ai/reliastats-site Reliability statistics — Weibull/lognormal fitting, MTBF/MTTR, availability, system composition. | |
| Vecmo chibataku0815/vecmo Vector motion editor MCP: 26 typed tools to observe, validate and edit documents, then export code. | |
| Mochii work graph chibitek/mochii-mcp-server Mochii work graph: projects, tasks, meetings. Stiki OAuth. Not Nexus memory. | |
| Nexus Memory chibitek/nexus Owner-scoped Nexus memory: search, facts, captures, KYC. Not Mochii's work graph. | |
| ai.plith/plith chicogonzales/plith AI agent infrastructure: dedup, cost prediction, validation, governance, failure intelligence. | |
| io.github.Chidi09/variantrade chidi09/variantrade Read your VarianTrade portfolio, positions, risk and signals. Trades are proposal-only. | |
| Vault MCP chill-ai-space/vault-mcp MCP server for credential isolation — bots use passwords and API keys without seeing them | |
| Chinaready China Market-Entry Search chinaready/mcp Read-only search over chinaready.co — China market entry for Western software teams. | |
| StudiePoint AI chinedum-okoli/studiepoint-ai 300+ African scholarships, GPA conversion & 1,700+ visa routes for postgrad students. | |
| io.github.chinlee2200-dotcom/bridgecore chinlee2200-dotcom/laboratory- Say what should happen; get the right app tool per step, an n8n workflow, or the call itself. | |
| Chipzen chipzen-ai/chipzen-sdk Poker arena for AI agents: play rated heads-up No-Limit Hold'em on chipzen.ai. | |
| io.github.chirag127/secenv-mcp chirag127/secenv-mcp Centralized secrets manager MCP server. Generate .env files, rotate keys, sync to GitHub Actions. | |
| io.github.ChiragBachani/context-autopilot chiragbachani/context-autopilot Mines your Claude Code and Cursor sessions into evidence-based CLAUDE.md / AGENTS.md rules. | |
| io.github.ChloePark85/picright chloepark85/picright-mcp License-aware images for markdown: CC/stock search, screenshots, Mermaid diagrams, provenance | |
| Facet chndr-prksh/facet Check web pages for responsive design problems and screenshot them on phone, tablet and desktop. | |
| Speakeroo speaking coach chocopie8/speakeroo-mcp AI speaking coach: feedback on speeches from text or audio, plus topics, pronunciation and rubrics. | |
| com.choosemylo/mind-of-mylo-quotes choosemylo/mind-of-mylo-chatbot Machine-learning-backed insurance premium estimates from Mylo, comparing 100+ carriers. | |
| ClipForge chriphil70/mediamiddleware Trim, watermark, extract audio, and convert video to 9:16 vertical via API or MCP server. | |
| TrustedVillas Villa Rentals chris-paton/trustedvillas-mcp Search and book luxury villa rentals across Europe with real-time availability and pricing. |
21,501–21,550 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.