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 |
|---|---|
| io.github.houtini-ai/fanout houtini-ai/fanout-mcp Multi-URL comparative content analysis with topical gap detection | |
| io.github.houtini-ai/fmp houtini-ai/fmp-mcp Access financial data and market information via Financial Modeling Prep API | |
| io.github.houtini-ai/gemini houtini-ai/gemini-mcp Model Context Protocol server for Google Gemini AI with chat, research, and grounding | |
| io.github.houtini-ai/geo-analyzer houtini-ai/geo-analyzer Scores content on the signals that get it cited by ChatGPT, Perplexity and AI Overviews | |
| io.github.houtini-ai/google-knowledge-graph houtini-ai/google-knowledge-graph-mcp Search Google's Knowledge Graph for structured information about real-world entities | |
| io.github.houtini-ai/lm houtini-ai/houtini-lm Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model. | |
| io.github.houtini-ai/seo-audit-console houtini-ai/seo-audit Technical SEO in Claude: GSC + crawl + DataForSEO - audit, portfolio, market sizing, content recon. | |
| io.github.houtini-ai/seo-crawler-mcp houtini-ai/seo-crawler-mcp Crawl and analyse websites for SEO errors using Crawlee with SQLite storage | |
| YubHub houtini-ai/yubhub Build job feeds from careers pages; query enriched jobs and hiring stats. Needs a YubHub API key | |
| capital.hove/read-only-local-mysql-mcp-server hovecapital/read-only-local-mysql-mcp-server MCP server for read-only MySQL database queries in Claude Desktop | |
| capital.hove/read-only-local-postgres-mcp-server hovecapital/read-only-local-postgres-mcp-server MCP server for read-only PostgreSQL database queries in Claude Desktop | |
| Hovercode hovercode-ltd/hovercode-mcp Create and manage QR codes, short links, landing pages, and forms in your Hovercode workspace. | |
| MERX - TRON Resource Exchange hovsteder/merx-mcp TRON energy exchange for AI agents. 54 tools, 30 prompts, 21 resources. A2A + ACP. | |
| io.github.howardpen9/grok-mcp howardpen9/grok-mcp Use xAI Grok as a peer reviewer + PR gate from Claude Code, Cursor, Cline and any MCP host. | |
| io.github.Hoya25/nctr-mcp-server hoya25/mcp-server NCTR Alliance rewards — search bounties, check earning rates, and discover communities. | |
| Nordnet Portfolio hpasic/nordnet-mcp Read-only Nordnet brokerage data: accounts, positions, trades, balances, orders, instruments. | |
| Coating Lab hpdkhoa/coatinglab-mcp Real surface finishes for game gun models: sourced finishes, variants, wear baked from use | |
| Feel Lab hpdkhoa/feellab-mcp An FPS feel checklist, measured from a timeline any game's probe can write | |
| Model Lab hpdkhoa/modellab-mcp Draws rigged game gun models in Blender from parameters, checked against the real gun | |
| Pose Lab hpdkhoa/poselab-mcp Measured spatial answers for posing first-person arms and a rifle in Blender | |
| Weapon Lab hpdkhoa/weaponlab-mcp Find and fix first-person weapon bugs behind a gate: your game's probe measures, the Gate judges | |
| HPP x402 MCP Bridge hpp-io/x402-mcp-bridge MCP bridge for autonomous x402 payments in HPP USDC.e — discover and pay for services per call. | |
| HProxy hproxy-com/hproxy-mcp Free proxy list, live proxy checker and IP lookup for AI agents. No key, nothing to install. | |
| su.hpt/hptsu-mcp hpt-su/hptsu-mcp Search hpt.su — Russian/EAEU vehicle compliance documents: type approvals, certificates, VIN lookup. | |
| HQBase hqbase/hqbase Connect AI agents to your self-hosted HQBase shared email workspace. | |
| io.github.hqkh4nh/dejared hqkh4nh/dejared-mcp Java decompiler MCP server. Explore, search, and decompile JAR, WAR, EAR, and AAR bytecode. | |
| io.github.HrishiKabra/voting-mcp hrishikabra/voting-mcp Social-choice voting rules (Borda, Copeland, Condorcet, STV, opinion pool) as MCP tools. | |
| AI Workbench MCP hrishikesh-thakre/ai-workbench-mcp Goose-first MCP server for Workbench-owned acceptance evidence, validation gates, and analytics. | |
| Hronaut Browser MCP hronaut/hronaut A visible desktop browser for coding agents, with a separate workspace for each project. | |
| Agent Workspace MCP hrrodan/agent-workspace-mcp A sandboxed, agentic workspace providing secure filesystem, bash, and uv-powered Python execution. | |
| io.github.hrtips/cvx hrtips/cvx Create, validate, and render CV PDFs from plain YAML — fully local, no accounts. | |
| Sandbox Env MCP hs3434/sandbox-env-mcp Persistent Docker/SSH sandbox for AI agents: shell exec, file ops, audit log. | |
| MCP Server for YNAB hs737/mcp-server-for-ynab Connect your AI assistant to YNAB. Read-only by default, with reversible opt-in writes. | |
| Korea Finance Factcheck hs85-newbie/korea-finance-factcheck Fact-checks numbers in Korean finance writing against DART, Bank of Korea ECOS and US Treasury | |
| Oxford Ledge hs902/oxford-ledge-mcp Ask your assistant; it reads the public record: SEC filings, 13F, insider trades, BDC loans. | |
| HSH Data-on-Demand hshintelligence/data-on-demand Made-to-order data for AI agents: company intel, B2B contacts, scraping. Pay per call via x402. | |
| archy hslee16/archy Architectural sensor for Python codebases. | |
| io.github.hsouf/cldf-mcp hsouf/cldf-mcp WALS typology joined with Glottolog classification, with provenance and family-aware counts. | |
| Taiwan Jobs 台灣求職 hsuanc0921/tw-jobs-mcp Read-only Taiwan job search: 104, Yourator, and Greenhouse, Lever and Workday career sites. | |
| io.github.html2pdfconverter/mcp-server html2pdfconverter/mcp-server MCP server for HTML2PDF Converter | |
| TrustyData htristram/trustydata-mcp-server French address quality, geocoding, routing, company lookup & catchment stats (BAN, INSEE, OSM). | |
| io.github.HTTPayer/mcp httpayer/mcp x402 micropayments for AI agents — credits-based, no wallets, no blockchain. | |
| log-ai-compressor hu-chenyu/log-ai-compressor Local log forensics: compress logs into citable evidence with root-cause confidence tiers. | |
| JevSim huaaudio/jevsim Run verified iOS and Android UI workflows in one agent tool call with Jev. | |
| io.github.huandu/feishu-markdown-mcp huandu/feishu-markdown MCP server for Feishu Markdown | |
| io.github.HUANGCHIHHUNGLeo/claude-real-video huangchihhungleo/claude-real-video Let any LLM watch a video locally — and search everything it has ever watched. | |
| io.github.HuangGoodmanAgency/pops4-mcp-catalog huanggoodmanagency/pops4-mcp-catalog AI-native corporate gifting & event infrastructure for Fortune 500. 70K products, 200+ brands. | |
| octocounts-mcp huanglizhuo/octocounts Analyze and compare public GitHub repository line counts (SLOC) from any MCP client. Provides per-language files, code, comment, and blank totals via the OctoCounts API, with compare_repos for side-by-side diffs of two repos or refs. | |
| io.github.huangyunbin/soclip huangyunbin/soclip-mcp Turn TikTok, Instagram, X and Facebook URLs into video download links and metadata. | |
| XHelio-SPICE huangzesen/xhelio-spice Spacecraft ephemeris made easy — auto-managed SPICE kernels for heliophysics |
8,951–9,000 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.