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 |
|---|---|
| AgentDM: Agent to Agent Communication Platform agentdmai/agentdm Agent communication platform for agent to agent messaging via MCP. Messages, channels, skills. | |
| ScreenshotMCP agentforge-labs/site-screenshot-public Desktop and mobile website screenshots plus page context for AI agents and automation workflows. | |
| AgentGate agentgate-builder/agentgate Check if an AI agent is registered, Active and Verified in the Concordium Agent Registry (CIS-8004). | |
| InjectScan agentgate-builder/x402-prompt-injection-scan Prompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools | |
| WebRead agentgate-builder/x402-url-to-markdown Read any public web page as clean Markdown for LLMs. Respects robots.txt. Free tier; x402 paid API. | |
| Agentgates Wallet agentgates-ai/agentgates An agent wallet over MCP: balances, and sends, swaps and earn moves its owner approves. | |
| Crypto Signals MCP agenthustler/crypto-signals-mcp Real-time crypto volume anomaly detection across 50+ tokens with pump signals. | |
| io.github.agentic-eng/a2atlassian agentic-eng/a2atlassian Jira & Confluence for AI agents. Pre-configured connections, compact output. | |
| io.github.agentic-eng/a2db agentic-eng/a2db Safe, read-only database access for AI agents. 5 databases, batch queries, SQLGlot. | |
| RCO-A2A - Record of Cleared Orders agentic-private-office/rco-a2a Signed receipt per cleared agentic order, by decision id. Two tools: write_receipt, verify_receipt. | |
| AgenticBooks agenticbooks/agenticbooks Startup books from live bank and billing feeds: P&L, balances, approvals, period close. | |
| Jobbi Agent Gigs agenticgigs/jobbi-mcp Index of paid tasks AI agents can do, aggregated hourly from public bounty and task boards. | |
| io.github.agenticmail/mcp agenticmail/agenticmail Real email and SMS for AI agents — send mail, receive verification codes, drive a real inbox. | |
| OpenAlex MCP Server agenticsolutions-hq/openalex-mcp-listing Search OpenAlex papers, authors, institutions and citations. Hosted on Apify; needs an Apify token. | |
| TradeOS Public Intelligence agenticsrclab/tradeos-public-intel-kit Crypto market intelligence, evidence, watchlists, feedback, and paid x402 SKU routing. | |
| Agentics agenticstechnologies/agentics.you Shared memory for AI agents, with a receipt for every write. Hosted MCP at agentics.you/mcp. | |
| Agentic Substrate agenticsubstrate/site Agent reputation economy: known-answer probation, expertise tags, jobs, staked delivery | |
| Agentic Reputation Gateway agenticsubstrate/site Read-only gateway for durable agent identity, consent, recognized work, and signed receipts. | |
| AgentFund agentigris/agentfund Fundraising tools for AI agents on Solana: create campaigns, donate via x402, check reputation. | |
| AgentLine agentlinehq/agentline-mcp Give AI agents a phone number. Voice calls, SMS, and phone number management for MCP clients. | |
| Agent Margin Router agentmarginrouter/agentmarginrouter 38 x402 pay-per-call tools for AI agents (USDC/USDT on Base): web, crypto, on-chain, geo, packages | |
| AgentIndex agentndx/agentndx Search 15K+ MCP services, A2A agents, and x402 APIs from 5 registries. Paid via x402 (USDC on Base). | |
| NOMOS Cross-Border Broker agentnomos/nomos-crossborder-broker Cross-border preflight, x402 quote and evidence receipts for A2A/MCP agent workflows. | |
| AKShare agentpit-io/hunter-community Let a model explore AKShare's 1000+ China market data functions on its own — search, inspect, call | |
| Kronos agentpit-io/hunter-community Stock price forecasting for China A-shares — Kronos K-line time-series model | |
| TrueSource agentpit-io/hunter-community First-hand market signals: filings, procurement wins, R&D expansion, macro data | |
| org.agentpub/papers agentpub/agentpub.org Submit papers for AI peer review and publication. Search and cite AI-authored research. | |
| The Quiet Protocol Growth Offense MCP agentqm/the-quiet-protocol Read-only MCP server for The Quiet Protocol's engines, benchmarks, proof, and business data. | |
| io.github.omoshola-o/xap agentra-commerce/xap-sdk Agent settlement protocol — discover, negotiate, settle, and verify with XAP. | |
| AgentRaaS wrap agentraas/agentraas Wraps any MCP server: identical write-tool calls run once, and every tool call is audit-logged. | |
| AgentRQ agentrq/agentrq Task manager for AI agents. Orchestrate agents to achieve large goals in unified control plane. | |
| Agents Get Paid Kit — x402 MCP + Unlock ($49) agentsgetpaidmore/agents-get-paid-kit x402 MCP get-paid path: USDC, spend caps, AUP, $49 kit. CAPTCHA/web-unlock for payment-ready agents. | |
| Agent Skills Search Server agentskills/agentskills Search and discover Agent Skills from the skills.sh registry. Powered by HAPI MCP server. | |
| AgentsKit Registry agentskit-io/agentskit-registry Discover open-source AI agents and get source-owned installation instructions through MCP. | |
| io.github.Exzentttt/agentspore agentspore/agentspore Connect an AI agent to AgentSpore: receive tasks, report progress, and message other agents. | |
| AgentStack (agentstack.tech) agentstacktech/agentstack Backend for AI agents: one batched tool over ~668 actions (hosting, storage, auth, payments). | |
| InvoiceForge agenttoolworks/mcp-servers Generate, validate and read EN 16931 and Peppol BIS 3.0 e-invoices, in UBL and CII. | |
| JobsRadar agenttoolworks/mcp-servers Job search across Greenhouse, Lever, Ashby, SmartRecruiters, Personio and Pinpoint, deduplicated. | |
| Store Catalog agenttoolworks/mcp-servers Shopify and WooCommerce product catalogs for agents: list, search, full product with barcodes. | |
| VerifyDesk agenttoolworks/mcp-servers Verify French and UK companies, EU VAT and IBANs; screen OFAC, UN, EU and UK sanctions lists. | |
| agentguard agentwares/agentguard MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log. | |
| seatledger agentwares/seatledger Local ledger of Claude Code and Codex tokens, API-equivalent cost, limits and token-rate changes. | |
| io.github.agentwares/agent-access-index agentwares/servers Whether an AI agent may fetch a URL, on what terms, and at what price. Free, no key, no signup. | |
| agentcheck agentwares/servers Synthetic checks, nightly regression replay and model-drift alerts for AI agents | |
| agentguard — policy proxy for agent tool calls agentwares/servers Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls. | |
| Real estate deal memo agentwares/servers Real estate deal memo from a US address: AVM, rent, comps, cap rate, cash-on-cash, DSCR, red flags. | |
| io.github.agentwares/mcp-liveness agentwares/servers Does an MCP server work for a stock client? By registry name or URL. Tool drift too. Free, no key. | |
| Readiness scorer — can an agent sign up to your SaaS? agentwares/servers Probe a signup URL you own and score whether an AI agent can sign up unaided. | |
| Stablecoin reserve attestations agentwares/servers Stablecoin reserve attestations as JSON: reserves, composition, attestor, on-chain supply, ratio. | |
| SNAP Protocol agentzeny/snap-public Private agent payments on Solana via ZK proofs: deposit, withdraw, list pools, estimate fees. |
19,951–20,000 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.