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 |
|---|---|
| Hatun MCP - Governed Agent Gateway szl-holdings/hatun-mcp Governed MCP gateway: policy gate on every tool call, hash-chained DSSE receipt on every result. | |
| io.github.sznt2010/agentresources-mcp sznt2010/agentresources-mcp MCP server for Agent Resources: Trust Cards, signed telemetry, ERC-8004 identity, x402. | |
| llm-prices-cn szp2005/llm-prices-cn Daily-verified LLM API pricing dataset (44+ models, CN & global) with a hosted MCP server for live price queries and token cost estimation. | |
| io.github.t-crew/memory-pulse t-crew/memory-pulse Give any agent self-improving memory you can trust in production. Built-in memory security. | |
| ForgeBridge t1ktakdev/forgebridge A local, permissioned MCP agent for authorized developer workstations. | |
| io.github.t3ratech/mcp-session-bridge t3ratech/mcp-session-bridge Drive a browser you are already signed into, through the free T3rnel Browser extension. | |
| EUDAMED MCP t4dhg/mcp-eudamed Search public EUDAMED devices, verify actors and build traceable evidence checklists. | |
| MCP FactorialHR t4dhg/mcp-factorial Full CRUD MCP server for FactorialHR: employees, teams, time off, projects, ATS, payroll. | |
| MCP Holded t4dhg/mcp-holded MCP server for Holded (Spanish ERP): invoicing, accounting, treasury, CRM, projects, payroll. | |
| io.github.t8y2/dbx t8y2/dbx Query databases from AI agents using connections configured in DBX. | |
| There's An AI For That taaft/mcp Search TAAFT for AI tools and retrieve public tool details. | |
| Taasky taasky/mcp Agent-to-agent negotiation: schedule meetings, agree prices and terms; each human approves the deal. | |
| Taasky Common ground taasky/taasky Coding agents (Claude Code, Codex) reach shared understanding: findings agreed, disputed or open. | |
| io.github.taazkareem/clickup taazkareem/clickup-mcp-server Premium AI integration. Tasks, lists, docs, folders, time. 50+ tools. Instant setup. | |
| Tabhand tabhand/tabhand Let your coding agents use your real, signed-in Chrome, in background tabs that never steal focus. | |
| tabnas tabnas/mcp Seven tools over the tabnas parsing engine: parse, validate, diagnose, fixtures, compare. | |
| com.jamesrosingmd/zenoti tacit-code/zenoti-mcp-server MCP server for Zenoti spa/wellness/medspa — guests, appointments, bookings, invoices | |
| io.github.tacps126/webdata-tools-mcp tacps126/webdata-tools-mcp 44 web-data tools for AI agents: jobs, news, tenders, laws, markets, health, trade, local leads. | |
| Linear tacticlaunch/mcp-linear A Model Context Protocol server that enables AI assistants to interact with Linear project management systems, allowing users to retrieve, create, and update issues, projects, and teams through natural language. | |
| Kirok Memory tadfuji/kirok-mcp Persistent memory for AI agents - hybrid semantic + keyword recall with autonomous consolidation | |
| ILens tadis174/ilens Inspect compiled .NET assemblies (Windows): find types, decompile to C#, trace usage, compare builds | |
| io.github.taehyeonglim/korean-elementary-learning-map-mcp taehyeonglim/korean-elementary-learning-map-mcp 한국 초등 2022 개정 교육과정 학습 그래프 MCP 서버 (성취기준 620 · 원문 수록 · 주제 1,956 · 선수관계 1,894) | |
| AI Rover Studio taewankung/ai-rover-mcp Let an AI agent drive a 2D robot rover simulator in the browser: sensors, camera, wiring and code. | |
| io.github.tago-io/mcp-server tago-io/mcp-server Model Context Protocol server for TagoIO data and analytics | |
| io.github.KyleTaggart/lsp tagteamdesign/lightsync-pro Sync Lightroom, Figma, Dropbox & Canva assets to WordPress and Shopify via natural language. | |
| Tailscale tailscale-mcp/tailscale-mcp Drive a Tailscale node and its tailnet through the CLI and the control-plane API | |
| io.github.taimiralain/stackguide-mcp taimiralain/stackguide-mcp Dynamic context loading for AI assistants with TDD workflow and AST analysis | |
| ai.takara/miru takara-ai/miru-code Hybrid semantic and keyword code search for coding agents. | |
| arxiv-latex-mcp takashiishida/arxiv-latex-mcp An MCP server that enables MCP clients to directly access and process arXiv papers by fetching the LaTeX source, improving mathematical content understanding. | |
| io.github.takeaseatventure/cron-mcp takeaseatventure/cron-mcp MCP cron validator for AI agents; flags impossible schedules and other silent cron bugs. | |
| PictMCP takeyaqa/pictmcp Provides pairwise combinatorial testing capabilities to AI assistants. | |
| io.github.takiguchi-yu/google-workspace-mcp-server takiguchi-yu/google-workspace-mcp-server An MCP server for Google Workspaces. | |
| Zitadel MCP takleb3rry/zitadel-mcp Enables faster, cleaner integration with Zitadel for user authentication. | |
| TakoCode takocode-chimera/takocode-mcp Build, preview and publish full-stack web apps with TakoCode's hosted coding agent. | |
| Tako takodata/tako-mcp Premium live data from S&P Global, FRED, OECD & more, plus web search, in one call. | |
| mi-sii-mcp taksuma-0/mi-sii-mcp Servidor MCP para el SII de Chile: IVA, F29, F22 y boletas de honorarios. Solo lectura y local. | |
| Lebanese Legislation taktekhq/lebanese-legislation Search and read Lebanese laws, articles, court rulings and Gazette issues. Verbatim texts only. | |
| Google Calendar MCP Server takumi0706/google-calendar-mcp A Model Context Protocol server that integrates Google Calendar with Claude Desktop, enabling users to manage calendar events (view, create, update, delete) through natural language. | |
| Epublys takyon236/epublys-mcp EPUB/PDF tools: merge, split, compress, convert, edit metadata, validate ebooks. | |
| com.wallet-connectors/wallet-verifier-mcp talaodao/connectors MCP server for verifying EUDI/Talao wallet data via OIDC4VP (pull) for AI agents. | |
| PlanVortex taliasoftworks/planvortexmcp Schedule posts, read comments and answer messages across all your social networks. | |
| Talivia Revenue Analytics talivia-group/agent Revenue-first analytics installed and verified by AI agents through Talivia | |
| LinkedIn MCP (by TalkToHumans) talktohumans/linkedin-mcp The safest LinkedIn MCP: your Agents read DMs, search your network and draft messages you send. | |
| Tallyfy Workflow Automation tallyfy/mcp-public Automate tasks, processes, and approvals with AI. | |
| io.github.taltal-beep/mcp-server-celery taltal-beep/mcp-server-celery Read-only Celery debugging: workers, queue depths and stuck-task diagnosis. | |
| GuardRails-MCP tam-ds/guardrails-mcp Local prompt regression tracker with six fictional cases and evidence for human review. | |
| Jira - GitHub MCP Server tamarengel/jira-github-mcp Enables end-to-end automation of developer workflows from Jira issue tracking to GitHub pull requests through natural language, allowing developers to search issues, create branches, commit changes, and manage PRs directly from their IDE. | |
| io.github.tamas-fm/project-lore tamas-fm/project-lore-mcp A local-first MCP server that routes development tasks to authoritative project documentation. | |
| Charming tambo-labs/charming-mcp Build personal interactive apps with real URLs and persistent storage, using any AI. | |
| git-context-mcp tamishaks-2/git-context-mcp Provides AI coding agents with structured Git repository context including project state, code structure, activity, and risk analysis without modifying or uploading code. |
19,201–19,250 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.