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 |
|---|---|
| io.github.runapi-builder/hailuo-mcp runapi-ai/hailuo-mcp RunAPI MCP server for Hailuo: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/happyhorse-mcp runapi-ai/happyhorse-mcp RunAPI MCP server for HappyHorse: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/ideogram-v3-mcp runapi-ai/ideogram-v3-mcp RunAPI MCP server for Ideogram V3: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/imagen-4-mcp runapi-ai/imagen-4-mcp RunAPI MCP server for Imagen 4: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/infinitetalk-mcp runapi-ai/infinitetalk-mcp RunAPI MCP server for InfiniteTalk: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/kling-mcp runapi-ai/kling-mcp RunAPI MCP server for Kling: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/luma-mcp runapi-ai/luma-mcp RunAPI MCP server for Luma: query historical tasks. | |
| io.github.runapi-builder/midjourney-mcp runapi-ai/midjourney-mcp RunAPI MCP server for Midjourney: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/nano-banana-mcp runapi-ai/nano-banana-mcp RunAPI MCP server for Nano Banana: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/qwen-2-mcp runapi-ai/qwen-2-mcp RunAPI MCP server for Qwen 2: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/qwen-image-mcp runapi-ai/qwen-image-mcp RunAPI MCP server for Qwen Image: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/recraft-mcp runapi-ai/recraft-mcp RunAPI MCP server for Recraft: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/runway-aleph-mcp runapi-ai/runway-aleph-mcp RunAPI MCP server for Runway Aleph: query historical tasks. | |
| io.github.runapi-builder/runway-mcp runapi-ai/runway-mcp RunAPI MCP server for Runway: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/seedance-mcp runapi-ai/seedance-mcp RunAPI MCP server for Seedance: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/seedream-mcp runapi-ai/seedream-mcp RunAPI MCP server for Seedream: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/suno-mcp runapi-ai/suno-mcp RunAPI MCP server for Suno: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/topaz-mcp runapi-ai/topaz-mcp RunAPI MCP server for Topaz: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/veo-3-1-mcp runapi-ai/veo-3-1-mcp RunAPI MCP server for Veo 3.1: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/vidu-mcp runapi-ai/vidu-mcp RunAPI MCP server for Vidu: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/wan-mcp runapi-ai/wan-mcp RunAPI MCP server for Wan: create tasks, poll status, check pricing. | |
| io.github.runapi-builder/z-image-mcp runapi-ai/z-image-mcp RunAPI MCP server for Z Image: create tasks, poll status, check pricing. | |
| io.github.runbook-ai/browser-agent runbook-ai/runbook-ai-mcp MCP server for browser automation with AI agent | |
| Runcrate runcrateai/runcrate-mcp AI cloud for agents: launch GPUs, run jobs that stop their own billing, schedule runs. | |
| Cycles — Budget Authority for AI Agents runcycles/cycles-mcp-server Runtime budget authority for AI agents — reserve, enforce, reconcile spend across providers | |
| rundata.re · La Réunion 974 en direct rundata-re/rundata La Réunion (974) en direct : actualités, météo, rando, bus, eau, événements, volcan, cyclones, air. | |
| German Real Estate Depreciation & Restnutzungsdauer rundum-immo/real-estate-appraisal-mcp German property depreciation (AfA), Restnutzungsdauer, Kaufpreisaufteilung & appraisals via AfAMax | |
| MCP Alchemy runekaagaard/mcp-alchemy Connects Claude Desktop directly to databases, allowing it to explore database structures, write SQL queries, analyze datasets, and create reports through an API layer with tools for table exploration and query execution. | |
| io.github.runesleo/polymarket-toolkit runesleo/polymarket-toolkit Read-only Polymarket data tools for AI agents: profiles, PnL, market scans. No keys, no orders. | |
| Fleets runfleets/cli Multi-site analytics as tools: GA4, Search Console, Cloudflare edge, PageSpeed, insights. | |
| io.github.runframe/runframe-mcp-server runframe/runframe-mcp-server MCP server for Runframe incident management covering incidents, on-call, postmortems, and more. | |
| Runhooks runhooks/runhooks-mcp Schedule and manage recurring and one-off HTTP jobs on Runhooks from your AI agent. | |
| VibeCart runjohnray2-lgtm/vibecart Agent-native commerce with trusted catalog, durable carts, and Stripe Checkout via MCP and UCP. | |
| Flux Cloud runonflux/flux-cloud-mcp Deploy, pay for and manage apps on Flux Cloud, the decentralized cloud. Prices in USD. | |
| io.github.RunTimeAdmin/nooscape-mcp runtimeadmin/nooscape-mcp Read-only facts with dates about AI agents, wallets and endpoints from Nooscape's public record. | |
| ai-runtime-guard runtimeguard/runtime-guard ai-runtime-guard is an MCP server that sits between your AI agent and your system, enforcing a policy layer before any file or shell action takes effect. No retraining, no prompt engineering, no changes to your agent or workflow, just insta | |
| com.runvouch/runvouch runvouch/runvouch Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run. | |
| io.github.Runware/mcp runware/mcp Access the full Runware API as MCP tools: image, video, audio, 3D, and text. | |
| Alya — The Hub for Autonomous Agents rupert1987/alya-mcp Operator-as-agent MCP hub. 6 tools. First $5 free, then $0.001/call. | |
| xlsx-tools-mcp ruriazz/xlsx-tools-mcp MCP server for accurate, structure-preserving read/write access to Excel (.xlsx) files | |
| RuSender rusender/rusender-mcp Manage email campaigns, contacts and deliverability analytics in RuSender from an AI assistant. | |
| Real Alpha rushabhsheth/realalpha-mcp What AI founders and researchers said in long interviews: quotes, speakers, dates and links to cite. | |
| io.github.rushi053/privacypage-mcp rushi053/privacypage-mcp Generate privacy policies, ToS, EULAs, cookie policies & disclaimers from your AI agent. | |
| codecortex rushikeshmore/codecortex Persistent codebase knowledge layer for AI agents. Pre-digests codebases into structured knowledge (symbols, dependency graphs, co-change patterns, architectural decisions) and serves via MCP. 28 languages, 14 tools, ~85% token reduction. | |
| Adako: ad ops for AI assistants ruslan2027/adako-mcp Google, Meta, LinkedIn and ChatGPT Ads for AI assistants. Every change needs your approval. | |
| FateTell russguo/fatetell-mcp Deterministic BaZi (Four Pillars) charts, Chinese almanac and saved FateTell charts. | |
| Rust MCP Filesystem rust-mcp-stack/rust-mcp-filesystem Blazing-fast, asynchronous MCP server for seamless filesystem operations. | |
| omni-dev rust-works/omni-dev Atlassian Jira/Confluence MCP server with schema-validated Markdown↔ADF roundtrips — surfaces content-model violations at conversion time instead of silently dropping panels, mentions, and layouts. | |
| free-web-mcp rustemmustafingovua-byte/free-web-mcp Web search and page reading for AI agents with zero API credits | |
| com.trailweights/trailweights-mcp rustfreeone/trailweights-mcp Verified ultralight gear evidence for agents: weights, specs, reviews, consensus. Paid per call. |
17,601–17,650 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.