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 |
|---|---|
| Last EHR — Medplum cbetz/last-ehr FHIR chart tools for MCP: read-only by default, with elicitation-gated, human-approved writes. | |
| MochiPDF cbolgiano/mochipdf Remote MCP server for HTML-to-PDF and screenshots with OAuth and API-key auth. | |
| Klaren — French Companies Directory ccamborde/klaren.fr Search French companies, directors and associations (INPI, INSEE, RNA). | |
| io.github.CCSTT-dev/callable ccstt-dev/callable-task-deck API for AI agents to delegate tasks to real humans. | |
| Custom AI View ccustomai/custom-ai-view See any site as it looks on a real iPhone, iPad or MacBook — and drive that window over MCP. | |
| CCXT ccxt/ccxt Official CCXT MCP server - Market data and trading across 100+ exchanges and prediction markets | |
| Captapi cdcstream/captapi-mcp Public social media data: profiles, posts, comments, transcripts and ad libraries, 30+ platforms. | |
| io.github.cdeust/automatised-pipeline cdeust/automatised-pipeline Codebase intelligence MCP server — index any repo into a property graph; 26 tools for agents. | |
| io.github.cdeust/prd-spec-generator cdeust/prd-spec-generator Turns a feature description into a verified 9-file PRD — multi-judge consensus, 17 MCP tools. | |
| RemembrallMCP cdnsteve/remembrallmcp Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector. | |
| io.github.cdonoyan/shuka cdonoyan/shuka-agent Universal trust attestation for AI agents: create, verify, and negotiate Shuka trust proofs. | |
| EVMole cdump/evmole Local structured analysis of deployed EVM runtime bytecode | |
| CedarAI Data Depot cedarai/cedar-mcp Read-only Cedar ARMS railroad data via Cedar login for authorized carriers. | |
| Agent^Rider ceedot-rock/agent-rider Signed agent identity, trust scoring, credit economy, and social layer for AI agents. | |
| Celigo celigo/ai Manage your Celigo integrator.io account: integrations, flows, connections, errors, and jobs. | |
| CardDeals Live Gift Card Deals cello305/carddeals-mcp Search current U.S. gift-card discounts from validated providers. Anonymous and read-only. | |
| AgentIndex — measured reliability for agent services cengit1/agent-index Measured uptime, price and payment evidence for 19,021 agent services. Reliability, not quality. | |
| Central City centralcity-ai-hq/protocol Every AI. One room. The open hub where the world's AI agents meet, work together and exchange. | |
| HubSpot Integrations MCP centrify-internal/hubspot-mcp-server MCP server for the HubSpot Integrations Center HubDB: search and retrieve integration data. | |
| Cerebrium Docs cerebriumai/cerebrium-skills Search the Cerebrium docs: deployment, cerebrium.toml, hardware, endpoints. Also sends feedback. | |
| run.onvibe/onvibe ceritium/onvibe Talk to Claude and get a live web app deployed to a real URL, with Postgres, storage and cron. | |
| io.github.cesco345/capital-equipment cesco345/capital-equipment-mcp Search, book, and manage scientific research equipment across 500+ STEM core facilities. | |
| DV360 MCP Server cesteral/mcp-open-advertising DV360 campaign management — writes, targeting, custom bidding, previews, and media uploads | |
| Whichli · Photo Polls cetinkol/whichli Turn photos or product links into a poll your friends vote on. One link, free, no account needed. | |
| A-du: ADU rentals, plans and rules cfkoss/a-du Permit-verified ADU rentals, pre-approved plans and cited ADU rules for LA, San Diego, SF and NYC. | |
| HomeMortgageOnline mortgage tools cgabrew7/homemortgageonline Read-only mortgage calculators and the site's published rate snapshot. | |
| RentalAnalytics rent tools cgabrew7/rentalanalytics Read-only HUD rent lookup and the site's existing rental calculators. | |
| Used Fork Truck cgabrew7/usedforktruck Read-only price book, seller screen, and financing illustration. | |
| com.connorgallic/connorgallic cgallic/connorgallic.com Query Connor Gallic's profile, products (KaiCalls, Kai CMO, Build with Kai), and writing. | |
| LessonFolk cgseb/lessonfolk Open-source AI courses taught by your AI tutor in conversation, with progress saved by MCP tools. | |
| Stepgate chaarangan/stepgate Agents can't skip steps: runs gated stepfiles on the client's own model. | |
| TokenBar chaconlucas/tokenbar AI usage limits (Claude Code, Codex, Copilot, Windsurf): check budget and time until reset. | |
| House Duck chaddungnam/chaddungnam.github.io Read-only public information about House Duck games and its Korean-first development Blog. | |
| RadiusOS CRM chadrnewell-hash/outreachos 34-tool CRM server — contacts, pipeline, quotes, invoices, scheduling, email, and AI scoring. | |
| aether studio — AI Image Generation, Editing & Creative Workflow chaehomie/knoll Generate, edit, and explore AI images. Flux, Imagen, LoRA identity swap, upscale, and more. | |
| ChainFX Capability Network chainfx/payment-gateway Agent Pay and planning graph for stablecoin commerce. | |
| com.chaink9/chaink9 chaink9/chaink9-mcp Token risk checks on BSC, ETH, Base and Arc: trades the token on a fork. Paid in USDC via x402. | |
| Folkmoot chaiseetbureau/folkmoot AI agents debate, vote and reach binding decisions in public halls. No signup to read. | |
| ChalkTalk chalktalkhq/plugins Create tutorial videos by chatting with AI. | |
| Ransack chancewalker165-dot/ransack Web search & fetch MCP for AI agents: 12 engines, one key, flat $15/mo at ransack.tools. | |
| RegEvidenceHub CableCert changhuliu/cablecert-qa Independent owner-side QA for structured-cabling certification closeout evidence. | |
| RegEvidenceHub CQC changhuliu/cqc-provider-mcp RegEvidenceHub CQC: England provider-registration and statutory-notification preflight. | |
| HMI Import Preflight changhuliu/factorytalkimportpreflightmcp Independent static checks for supported tag and alarm CSV import formats; no HMI or PLC access. | |
| Trust Live changhuliu/mcp-selection-lab Evidence-linked MCP selection and non-executing Safe-Call review; surfaces unknowns. | |
| OPC UA NodeSet Gate changhuliu/opc-ua-nodeset-compatibility-gate Deterministic release-compatibility preflight for OPC UA NodeSet2 XML. | |
| RegEvidenceHub Premises changhuliu/uk-premises-licence-mcp RegEvidenceHub Premises: UK premises-licensing preflight for supported authorities. | |
| RegEvidenceHub Taxi changhuliu/uk-taxi-phv-mcp RegEvidenceHub Taxi: England taxi/PHV licensing preflight and council comparison. | |
| RegEvidenceHub Waste changhuliu/uk-waste-rule-mcp RegEvidenceHub Waste: England waste registration, DWT readiness and permit-change preflight. | |
| io.github.ChanMeng666/archlang-mcp chanmeng666/archlang ArchLang: compile, describe, lint, validate, score, repair, fix, finish, suggest, complete, link. | |
| Chaos Cypher chaoscypherinc/chaoscypher Local-first knowledge graphs from your documents: build, search (GraphRAG) and edit on your machine. |
21,451–21,500 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.