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 |
|---|---|
| IndustryLens industrylensop/industrylens-mcp-docs B2B SaaS competitor pricing changes, strategic moves, market landscapes, reports and comparisons. | |
| io.github.Inefavel/sfmc-mcp-server inefavel/sfmc-mcp-server MCP Server para Salesforce Marketing Cloud: valida queries do Automation Studio antes de rodar. | |
| INFATON MCP35 infaton/mcp35 MCP server for 1C:Enterprise ERP with 35 tools: metadata inspection, document CRUD, register queries, and BSP integration. First MCP server for Russian ERP systems (300,000+ organizations). JSON-RPC 2.0 compliant BSL implementation. | |
| InferCPI infer-cpi/api AI inference price index: token prices, cost per capability, open vs closed, hosts, cost per task. | |
| Apollo.io MCP Server inferensys/apollo-io-mcp Apollo.io MCP server for prospecting, enrichment, CRM, sequences, and outreach workflows | |
| Contextful inferensys/contextful Efficient context management: code search, evidence packs, and memory for coding agents. | |
| dr-mcp inferensys/dr-mcp Audits MCP configs, scores risk, and creates reversible repair plans. | |
| Infimium infimium-ai/infimium-agent Private AI context layer for semantic code search, dependency graphs, memory, and workspaces. | |
| io.github.Infinihash/infinihash-kyt-mcp infinihash/infinihash-kyt-mcp Screen crypto wallets vs OFAC SDN + threat intel; pre-payment checks, signed receipts; SAR drafts | |
| io.github.Inflectra/mcp-server-spira inflectra/mcp-server-spira A Model Context Protocol (MCP) server enabling AI assistants to interact with Spira by Inflectra. | |
| ai.inflowpay.app/inflow inflowpayai/inflow-mcp MCP Server for agents to onboard, pay, and provision services autonomously with InFlow | |
| Influship influship/influship-mcp Find and analyze influencers with creator search, lookalikes, profiles, posts, and transcripts. | |
| Sponsorbook influship/sponsorbook-mcp Research YouTube sponsors, inspect sponsorship evidence, and manage brand lists with Sponsorbook. | |
| io.github.info-arnav/unlocalhost info-arnav/unlocalhost Deploy localhost to a private, authenticated link from your AI coding agent. | |
| io.github.infolegalge/legal-ge infolegalge/legal.ge-mcp Find verified legal specialists in Georgia from natural-language queries. Trilingual (ka/en/ru). | |
| ORANO MCP Server infotik/orano-mcp-server Read-only MCP server exposing a user ORANO library to their own AI agent. | |
| InfraMap inframaporg/mcp US power plant, generation, price, curtailment and water data, with sources on every result. | |
| InfraNest infranest-infrastructure-organized/infranest-mcp Monitor websites, servers, domains and SSL with InfraNest, and ask your AI assistant what is down. | |
| ai.smithery/infranodus-mcp-server-infranodus infranodus/mcp-server-infranodus Map text into knowledge graphs to create a structured representation of conceptual relations and t… | |
| Infraveil Agent Guard infraveilhq/infraveil-guard Gate an AI agent's destructive actions behind human approval, with a tamper-evident log. | |
| Infraveil Control Plane infraveilhq/infraveil-mcp Govern your backend control plane from your AI agent - signed, human-approval-gated. | |
| Infrawise infrawise/mcp-server Azure FinOps infrastructure cost optimization | |
| Ingero ingero-io/ingero eBPF-based GPU causal observability with 7 MCP tools for AI-assisted GPU debugging | |
| witness ingtian/witness Distills your sessions or any text corpus into a dated history of how its subject changed. | |
| Sapiens Sintéticos inhabitants/sapiens-mcp Operate your Sapiens Sintéticos AI studio: generate image, article, voice, music and video. | |
| mcp-image-compression inhiblabcore/mcp-image-compression MCP server for local compression of various image formats | |
| Exec Sandbox inhuman/mcp-exec Single exec tool running caller Python in a network-isolated locked-down sandbox. | |
| Kubernetes Ephemeral Job inhuman/mcp-k8s-ephemeral-job Runs a command in a throwaway Kubernetes pod and returns exit code, output and artifacts. | |
| SSH Fleet inhuman/mcp-ssh-fleet Curated ssh_probe diagnostics and single-host ssh_exec over an allowlisted SSH fleet. | |
| Inistate MCP inistate/inistate-mcp MCP server for the Inistate platform: module discovery, entry management, and activity submission. | |
| ideaudit inite-ai/ideaudit-mcp The scoring behind an audit allowed to say no. Twenty deterministic tools, offline, no account. | |
| INITE Brain inite-ai/inite-brain-service Long-term memory for AI agents: a bitemporal knowledge graph with cited answers. | |
| INITE Club inite-ai/inite-club-mcp Ask the agent of someone whose calendar you could not get. No credential needed to try. | |
| INITE Process Diagnostic inite-ai/inite-diagnostic Takes a business process apart and says what to automate first. Eight questions free, 43 paid. | |
| INITE, signed in inite-ai/inite-visibility Your INITE account, and Local Start bought for you, paid from your INITE wallet or by card. | |
| WhatsApp MCP by TimelinesAI initechsoftware/whatsapp-mcp-by-timelinesai Ask questions across your WhatsApp inbox from Claude, ChatGPT, Cursor or any MCP client. | |
| io.github.inity13/agentstack-mcp inity13/agentstack-mcp Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools. | |
| io.github.inity13/precisioncalc-mcp inity13/precisioncalc-mcp High-precision finance & business calculations for AI agents — exact decimals, never floats. | |
| io.github.inity13/scenariosim-mcp inity13/scenariosim-mcp Deterministic what-if & scenario simulation for AI agents: projections, sensitivity & break-even. | |
| Stockbit MCP ino-xious/stockbit-mcp Indonesian exchange (IDX) via your own Stockbit account: quotes, bandarmology, charts. Unofficial. | |
| Inoh inoh-app/inoh-mcp Search the Inoh dictionary and create, track and delete your own vocabulary flashcards. | |
| Symbol (XYM) inotakeh/symbol-mcp-server Read-only MCP server for the Symbol blockchain (XYM): node health, harvesting, voting keys. | |
| io.github.inSideos-designs/cowork-qa insideos-designs/cowork-qa-mcp Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots. | |
| Enrichment Crawlers MCP by InsightfulPipe insightful-pipe/enrichment-mcp-server Hosted Enrichment Crawlers MCP server, with each action switched on or off per account. | |
| Meta Ads MCP by InsightfulPipe insightful-pipe/facebook-ads-mcp-server Hosted Meta Ads MCP server for Claude, ChatGPT and Cursor, with each action switched per account. | |
| Facebook Pages MCP by InsightfulPipe insightful-pipe/facebook-pages-mcp-server Hosted Facebook Pages MCP server, with each action switched on or off per account. | |
| Google Ads MCP by InsightfulPipe insightful-pipe/google-ads-mcp-server Hosted Google Ads MCP server for Claude, ChatGPT and Cursor, with each action switched per account. | |
| Google Analytics 4 MCP by InsightfulPipe insightful-pipe/google-analytics-mcp-server Hosted Google Analytics 4 MCP server, with each action switched on or off per account. | |
| Google Business Profile MCP by InsightfulPipe insightful-pipe/google-my-business-mcp-server Hosted Google Business Profile MCP server, with each action switched on or off per account. | |
| Google Search Console MCP by InsightfulPipe insightful-pipe/google-search-console-mcp-server Hosted Google Search Console MCP server, with each action switched on or off per account. |
9,251–9,300 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.