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 |
|---|---|
| GST Cranes Public Discovery MCP gkmex75/crane-rental-directory Public read-only discovery tools for GST Cranes marketplace, wanted ads, and Crane Wiki. | |
| Gkmex Crane Inventory gkmex75/gkmex-developer-resources Public, zero-auth, read-only access to Gkmex used-crane inventory. | |
| GL1TCH Token Safety gl1tchbased-pixel/gl1tch-coin Token rug-risk scans, Know Your Agent wallet checks and deployer reputation for AI agents. | |
| io.github.GlassCaseOfEmotion/agentgauge glasscaseofemotion/agentgauge-skill Scan any website's AI readiness: AI search visibility and AI agent usability. Free, no auth. | |
| Glasser glasser-ai/plugins One key to 1,000+ paid data APIs: enrichment, SEO/SERP, scraping, places, news. Pay per call. | |
| Rius glassflow/rius-mcp-server Query your AI agents' traces, errors, cost and alerts in Rius, the agent observability platform. | |
| dev.glbforge/glbforge glbforge/glbforge Make AI-generated 3D assets web-ready: budgets, SSIM-verified optimization, STL/USDZ export. | |
| Ad Library: Google Ads Transparency & LinkedIn Ads gleanery-works/ad-library-mcp Every ad a company runs on Google and LinkedIn: copy, creatives, dates, impressions, targeting. | |
| Job Market & EU Supplier Data gleanery-works/job-and-supplier-data-mcp Jobs from 10,000+ company career sites, Germany's Arbeitsagentur, Wellfound startups; EU suppliers. | |
| Glen glen-web-app/glen-mcp Search your team's shared agent memory, and use and save the org's skills and documents. | |
| LeaseIQ Pro glennl201/leaseiqpro Excel-verified lease finance math for AI agents: equipment, solvers, schedules. | |
| com.sourcerdesk/sourcers-desk glennquinting/sourcerdesk-api-docs Recruiter-grade boolean/x-ray search strings from a 20-year sourcing playbook. | |
| io.github.glidermcp/glider glidermcp/glidermcp.com Roslyn-powered C# code analysis server for LLMs. Supports stdio and HTTP transports. | |
| com.glitchexecutor.grow/glitch-grow-linkedin-ad-mcp glitch-exec-labs/glitch-grow-linkedin-ad-mcp MCP server for the LinkedIn Marketing API — campaigns, analytics, creatives. | |
| Glitchless glitchless-gg/glitchless Coding agents can build a game. They can't see anyone play it. Glitchless lets them. | |
| io.github.Glittering/ai-browser glittering/ai-browser Visible Electron browser driven by a semantic accessibility tree: 17 MCP tools, no screenshots. | |
| iCloud Calendar (CalDAV) glob0x17/mcp-icloud-caldav iCloud Calendar over CalDAV: list, create, update, move and delete events. Optional read-only mode. | |
| io.github.skviteberg/kultur-dev global-intech-as/kultureintelligence-mcp Cultural intelligence for AI: protect brands from reputational damage across 195 countries. | |
| io.github.Shreyas-Profile/browser-mcp globalion/browser-mcp Hosted real Google Chrome MCP with per-user persistent state. Navigate, click, type, screenshot. | |
| io.github.globallayer/mcp-server globallayer/marketplace Merka2a MCP server - AI agents search, negotiate and order GPU compute | |
| TESSA Marketing & Technology globalpart/tessa-aios TESSA's AI interface: services, case studies, AI-readiness audits, professional services directory. | |
| GlobKurier Shipping MCP globkurier-pl/mcp-server Track shipments and search shipping products (DPD, InPost, DHL, FedEx, UPS, GLS) via GlobKurier API. | |
| GSC MCP Core glq0546/gsc-mcp-core Multi-tenant GSC data fetcher for AI agents. OAuth secured. | |
| io.github.gluip/chart-canvas gluip/chart-canvas Create interactive visualizations and query data sources (SQLite, CSV, Parquet, JSON) | |
| unripe glumly/unripe Check how long ago a package version was published before an agent adds it, in 20 ecosystems. | |
| 水獭 AI 比价 gm365/shuita-ai-price Compare AI subscription prices (ChatGPT, Claude, Gemini, Grok) across 130+ verified shops. | |
| Agent Hub gmannerhj/agent-hub-mcp Text-only board for AI agents: read threads, post signed Nostr events, play timed quiz games. | |
| Arckép gmen1057/arckep-mcp Generate images, video, speech, 3D, slide decks, Word/Excel/PDF docs, product cards, and AI chat. | |
| MCP Marketplace gmoneyn/mcp-marketplace Search and install 4,000+ security-scanned MCP servers from inside any MCP-aware AI client. | |
| GNews gnews-io/gnews-io-mcp-server Official GNews API server: search news articles and top headlines from 80,000+ sources. | |
| com.geiant/mcp-agentcore gns-foundation/geiant AI governance MCP server for EU AI Act compliance and jurisdiction verification | |
| com.geiant/mcp-perception gns-foundation/geiant Geospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance | |
| GRAFOMEM CGR Capture gns-foundation/grafomem Record agent judgments and their real outcomes on GRAFOMEM Cloud. Capture now, score later. | |
| GRAFOMEM CGR Read gns-foundation/grafomem Read Foundation-signed, offline-verifiable CGR agent-reputation attestations. No install. | |
| Assay goassay/assay-plugins Hand a task to another person's AI agent, or take paid tasks. Paid only when the work passes. | |
| TrustLayer goatgaucho/trust-layer Agent reputation scoring: trust scores, Sybil detection, cross-chain identity for 133K+ agents | |
| io.github.GoatInAHat/toolfactory goatinahat/toolfactory Build an agent tool once; ship it as Agent Skills, MCP servers, Agent Plugins / Claude / Codex | |
| io.github.Goatleaf12/fuin-oni goatleaf12/fuin-oni Read FUIN ONI state, grind PoW mint proofs, build unsigned mint calldata on BSC. Never signs. | |
| io.github.Goatleaf12/oagent-units goatleaf12/oagent-units Read OAGENT Units state, grind PoW mint proofs, build unsigned mint calldata on BSC. Never signs. | |
| GoCardless MCP Server gocardless/gc-mcp Manage GoCardless payments, mandates, subscriptions, refunds and payouts via AI assistants. | |
| Practonaut godarg/practonaut Local practice gym for AI agents on real apps: practice Excalidraw tasks, get a reproducible score. | |
| GitJog — Hungarian legislation godavid/gitjog Full text and amendment history of Hungarian acts: section-level search, point-in-time text, diffs. | |
| gPTY godot-pty/gpty Spawn panes, inject input and read output in a tiling terminal workspace | |
| io.github.godwin105/arbiter godwin105/arbiter_ai Is this transaction safe to sign? Decodes what it really does and answers allow, warn or block. | |
| io.github.Godzilla-lab/quorum godzilla-lab/quorum-api Market evidence with receipts: every claim resolves to a real stored record you can fetch back. | |
| io.github.Goingparabolic/painprep-mcp-server goingparabolic/painprep-mcp-server Interventional pain medicine MCP: Medicare checklists, CPT/ICD-10, ASRA, prior-auth & appeals | |
| agency.goji/goji goji-agency/goji-mcp Answers on AEO, SEO, web and brand from GOJI's published material. Melbourne, Australia. | |
| knowbase gokhanibrikci/knowbase What other agents already tried against your build error, which attempt worked, and the dead ends | |
| DiffSense goldensupremesaltedfish/diffsense MR/PR risk audit MCP server: semantic diff + rule engine, strict read-only. Run as image or pip. | |
| io.github.Goldentrii/agent-recall goldentrii/agentrecall-mcp Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only. |
23,451–23,500 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.