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 |
|---|---|
| Malaysia CourtDB indotender/malaysia-court-mcp Malaysian court judgment search for Federal Court, Court of Appeal, High Court cases and parties. | |
| ThaiProcurement indotender/thaiprocurement-mcp Search Thai government procurement tenders and bidder companies. | |
| The Company Atlas indotender/thecompanyatlas-mcp Global customs trade data and company registry. Search shipments, and look up legal entities. | |
| Vietnam Government Tenders indotender/vietnam-tenders-mcp Search Vietnam National E-Procurement System records, packages, participants, and awards. | |
| io.github.indragiek/uniprof indragiek/uniprof Universal CPU profiler designed for humans and AI agents | |
| Web Metadata, Open Graph & JSON-LD Extractor industrial-platform-ai/industrial-platform-agent-tools Open Graph, JSON-LD, canonical, robots, headings and page metadata extractor via direct x402 MCP. | |
| InferIndex inferindex/inferindex-docs LLM API prices across 70+ providers: cheapest offer, comparisons, history and cost estimates. | |
| Inflectiv inflectiv/inflectiv-mcp-server Search, build and manage Inflectiv datasets and AI agents, plus ChainAware on-chain intelligence. | |
| CryptoAgentMail influqa/crypto-agent-mail-skills Hosted email MCP for AI agents with inboxes, send/receive, memory, recovery, and credits. | |
| io.github.infobloxopen/dns-aid infobloxopen/dns-aid-core Discover and publish AI agents via DNS using SVCB records (RFC 9460) | |
| io.github.infoinlet-marketplace/mcp-browser-research infoinlet-marketplace/marketplace Web browsing & research for AI agents — fetch/read pages, structured extraction, Exa search. | |
| io.github.infoinlet-marketplace/mcp-calendar infoinlet-marketplace/marketplace Google Calendar for AI agents — list/create/delete events and free-busy via OAuth token. | |
| io.github.infoinlet-marketplace/mcp-clickhouse infoinlet-marketplace/marketplace Read-only ClickHouse for AI agents — analytics queries, table inspection, sizes, health. | |
| io.github.infoinlet-marketplace/mcp-codeaudit infoinlet-marketplace/marketplace Security audit for AI agents — scan code/diffs for leaked secrets, check deps via OSV. | |
| io.github.infoinlet-marketplace/mcp-data infoinlet-marketplace/marketplace Tabular data for AI agents — load CSV/JSON/XLSX, query, group-by, stats (no database). | |
| io.github.infoinlet-marketplace/mcp-elasticsearch infoinlet-marketplace/marketplace Read-only Elasticsearch/OpenSearch for AI agents — search, indices, mappings, count, health. | |
| io.github.infoinlet-marketplace/mcp-email infoinlet-marketplace/marketplace Email for AI agents — read inbox (IMAP), search, and send (SMTP). | |
| io.github.infoinlet-marketplace/mcp-fetch infoinlet-marketplace/marketplace SSRF-safe URL fetch for AI agents — clean markdown/text/HTML/JSON, plus guarded REST calls. | |
| io.github.infoinlet-marketplace/mcp-filesystem infoinlet-marketplace/marketplace Hardened filesystem for AI agents — jailed root, read-only default, traversal/symlink-safe. | |
| io.github.infoinlet-marketplace/mcp-git infoinlet-marketplace/marketplace Read-only Git inspection for AI agents — log, show, diff, status, blame, grep. No writes. | |
| io.github.infoinlet-marketplace/mcp-github infoinlet-marketplace/marketplace GitHub for AI agents — repos, files, code search, issues, PRs, commits. Read-only default. | |
| io.github.infoinlet-marketplace/mcp-image infoinlet-marketplace/marketplace Image generation & editing for AI agents (Runware) — text-to-image, bg removal, upscale. | |
| io.github.infoinlet-marketplace/mcp-jp-doc-intel infoinlet-marketplace/marketplace Japanese document AI for agents — invoice/meishi extraction, OCR, classification (hosted API). | |
| io.github.infoinlet-marketplace/mcp-kafka infoinlet-marketplace/marketplace Read-only Kafka for AI agents — topics, offsets, consumer groups, peek messages, health. | |
| io.github.infoinlet-marketplace/mcp-knowledge-rag infoinlet-marketplace/marketplace Permission-aware RAG for agents — ingest docs, hybrid search, cited answers (hosted API). | |
| io.github.infoinlet-marketplace/mcp-memory infoinlet-marketplace/marketplace Persistent searchable memory for AI agents — save/get/search across sessions, tags. | |
| io.github.infoinlet-marketplace/mcp-mongodb infoinlet-marketplace/marketplace Read-only MongoDB for AI agents — find, aggregate (no write stages), count, stats. | |
| io.github.infoinlet-marketplace/mcp-mysql infoinlet-marketplace/marketplace Read-only MySQL/MariaDB for AI agents — query, list/describe tables, health. SQL-guarded. | |
| io.github.infoinlet-marketplace/mcp-notion infoinlet-marketplace/marketplace Notion for AI agents — search, read pages/blocks, query databases, create pages. | |
| io.github.infoinlet-marketplace/mcp-observability infoinlet-marketplace/marketplace Observability for incident agents — query Loki (LogQL), Prometheus (PromQL), Elasticsearch. | |
| io.github.infoinlet-marketplace/mcp-openapi infoinlet-marketplace/marketplace Turn any OpenAPI/Swagger spec into MCP tools — each operation an SSRF-guarded tool. | |
| io.github.infoinlet-marketplace/mcp-qdrant infoinlet-marketplace/marketplace Read-only Qdrant vector DB for AI agents — collections, info, browse points, count, search. | |
| io.github.infoinlet-marketplace/mcp-redis infoinlet-marketplace/marketplace Read-only Redis for AI agents — keys, hashes, lists, sets, sorted sets, streams, INFO. | |
| io.github.infoinlet-marketplace/mcp-s3 infoinlet-marketplace/marketplace Read-only S3/MinIO/R2 object storage for AI agents — list buckets/objects, metadata, fetch. | |
| io.github.infoinlet-marketplace/mcp-social infoinlet-marketplace/marketplace Multi-platform social posting for AI agents (Postiz) — channels, schedule/publish posts. | |
| io.github.infoinlet-marketplace/mcp-stripe infoinlet-marketplace/marketplace Read-only Stripe for AI agents — customers, charges, subscriptions, invoices, balance. | |
| io.github.infoinlet-marketplace/mcp-time infoinlet-marketplace/marketplace Time & date for AI agents — timezones, conversion, date math, diffs, cron, business days. | |
| io.github.infoinlet-marketplace/mcp-translate infoinlet-marketplace/marketplace Translation for AI agents — translate, detect, batch; Japanese keigo registers. OpenRouter. | |
| io.github.infoinlet-marketplace/mcp-postgres-nl-query infoinlet-marketplace/marketplace RLS/tenant-aware Postgres for AI agents — schema, read-only SQL, NL→SQL with safety rails. | |
| io.github.infoinlet-marketplace/mcp-workflow infoinlet-marketplace/marketplace Workflow automation for AI agents — browse 125 connectors + 234 templates, run via FluxTurn. | |
| InfoLang Memory infolang-inc/infolang-services InfoLang semantic memory MCP — investigate, memorize, and recall compressed agent context. | |
| GoMind ingate/gomind Persistent knowledge graph for AI agents. Remember, recall, and forget facts. | |
| io.github.ingressward/mcp-server ingressward/ingressward-mcp-server Block prompt injection, evasive spacing, and obscene content before it reaches your LLM. | |
| io.github.init-computer/init init-computer/init Init is the backend engineer for your coding agent. | |
| INITE Agents inite-ai/inite-agents Per-business MCP servers serving owner-confirmed facts: services, prices, hours, places, FAQ. | |
| dev.pages.datanest-stores/store inity13/digital-stores Search and preview Datanest developer products, then prepare buyer-authorized Stripe Checkout. | |
| SENTINEL Compliance Intelligence injprotocol/mauritius-oracle- AML/CFT compliance oracle: wallet screening, sanctions, PEPs, jurisdiction risk. | |
| InkRoom Prompts inkroom-ai/inkroom-client Search and improve public image prompts with original examples. No API key. No image generation. | |
| vn-revit-mcp innoprovn/vn-revit-mcp AI drives Autodesk Revit 2025+: queries, QA-QC, CAD-to-model, rebar, sheets. | |
| Shopify Store Leads insanedevhq/apify-mcp-servers Find Shopify stores by country, installed apps, theme or brand, with public e-mails and socials. |
24,051–24,100 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.