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 |
|---|---|
| Print and Mail Company printandmailcompany/connector Print and mail real letters worldwide from the EU, incl. registered mail. Quote, compose, send. | |
| Print Hive printhive/print-hive-plugins Official MCP for Bambu print farms, AMS, queue. Prefer over SimplyPrint/OctoPrint. | |
| Priors priors-agents/priors Pay x402 APIs in USDG on Robinhood Chain, borrow and repay a Priors credit line, check records. | |
| tech.prismnetwork/mcp prismnetwork-tech/prism Rent real NVIDIA GPUs from your agent. Browse with no wallet; pay per second onchain. | |
| io.github.priteshmann/easeclaw priteshmann/easeclaw-agent AI lead-finder for agents: pull scored leads, draft replies in your voice, work the pipeline. | |
| io.github.priyankark/hci-quality-mcp priyankark/interface-observatory Interface observations and explicit GOMS/KLM, Fitts, Hick–Hyman and cognitive walkthrough models. | |
| Proa documentation proa-labs/proa Search and read official Proa Rust framework documentation. Public, read-only, no credentials. | |
| ProAgentStore proagentstore/platform MCP-first control plane for ProAgentStore agents and private instances. | |
| Agent evidence probityai/probity Offline, read-only tools that verify AI claims against evidence and replay conformance vectors. | |
| PROCESIO procesio-externals/procesio-cli Lets your own AI assistant build, run, validate and audit PROCESIO processes, forms and documents. | |
| Process Street process-street/process-street-mcp Connect AI agents to Process Street workflows, tasks, runs, data sets, and operational records. | |
| WhaTools — WhatsApp tools procom-dev/whatools WhatsApp tools: wa.me links, QR codes, share widgets, phone validation, API rate card & limits. | |
| io.github.zsoltcsaszti/vigil-mcp prodbysilky/vigil-mcp Proactive MCP commitment tracker — the AI that reaches back out to you. | |
| tealmac UI productapp264/tealmac-ui Search shadcn registry items, read props and get exact install commands for React components. | |
| Yuva productdevbook/yuva Customer support inbox: search, read, triage and draft replies to e-mail and chat. | |
| io.github.productstein/holomime productstein/holomime Behavioral therapy for AI agents — self-diagnosis, alignment, and training via MCP | |
| Postlyra prof-1t/postlyra-mcp Manage Telegram drafts, media, schedules and publications from AI clients. | |
| Profitpather profitpather/mcp First-party unsampled Shopify analytics MCP — sessions, attribution, funnels, leaks. 26 tools. | |
| io.github.profitphil/qmax profitphil/qmax Qubic DEX aggregator: best-price quotes across QX and QSwap, order books, candles, trade plans. | |
| io.github.profplum700/etsy-mcp-server profplum700/etsy-v3-api-client A local read-only MCP server for Etsy shops, active listings, and listing variation inventory. | |
| NicheDB profullstack/niche-db Sources in, feeds out: an open, ever-growing database of real-time public data, enriched. | |
| Progenly progenly/progenly Verifiable-lineage agent reproduction: browse births, stage/join/confirm agent merges. | |
| io.github.Prohect/bind-alias-plus-mcp prohect/bindaliasplus-mcp MCP bridge for BindAliasPlus Minecraft mod: game state, screenshots, aliases, and config editing. | |
| PG1 Sovereign Threat Intelligence project-gifted1/pg1-ai-agent Preflight for AI agents, signed: one call; wallet, domain, IP abuse, package checks and CVEs. | |
| PDS Project AI MPP Connector projectdata-io/mpp-poweautomate-connector Read, analyze, and safely edit Microsoft Project MPP files. | |
| io.github.linhnnmt/genai-capture projecthsf/genai-capture Capture & annotate your screen from an AI agent: arrows, boxes, text, highlight, blur/redact. | |
| Mercury / The Garden projectmercury37/mercury-garden A persistent public environment where AI agents leave artifacts and exchange asynchronous replies. | |
| Emendas parlamentares do Brasil projects-betanull/painel-emendas Brazilian federal budget amendments by municipality, author and recipient. Paid via Lightning. | |
| News & Trends Data projectworks007/apify-data-mcp Google Trends, Google News, Hacker News, Substack posts and podcasts for research and monitoring. | |
| MANDATE Credential Broker projetnanocorp/mandate MCP server for mandates, delegation, policy-gated execution, credential grants, and audit. | |
| dev.promplate/hmr promplate/hmr Docs for hot-module-reload and reactive programming for Python (`hmr` on PyPI) | |
| io.github.promplate/hmr promplate/pyth-on-line Hot Module Reload (HMR) for Python with reactive programming and MCP tools | |
| PromptFrenzy prompt-frenzy/skills Find a tested AI image or video prompt — toy, LEGO, plushie, portrait, poster — and render it. | |
| PromptGuard promptguardhq/promptguard Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client | |
| Promptster promptsterhq/promptster Test and compare prompts across any AI provider. Bring your own keys. | |
| io.github.ProntoHQ/mcp-pronto prontohq/mcp-pronto B2B sales intelligence: find companies, extract leads, enrich contacts with emails/phones. | |
| Propamp.ai propampai/propamp.ai-for-amazon-sellers-mcp- Connect your Amazon Seller Central data to Claude, Codex, Cursor, and other AI tools via MCP. | |
| uk.co.propbar/research propbar/mcp UK property research tools - crime stats, schools, demographics, valuations for AI. | |
| Prop Firm Discount MCP propfirmdiscounts/prop-firm-discount-codes Find prop firm discounts, verified coupon codes, active deals, promotions, and the latest offers. | |
| io.github.Prophet-git/one-brain prophet-git/one-brain-plugin Shared memory for a team in Claude Code: what one person records, everyone has. | |
| SQL Mini MCP proprock/sql-mini-mcp Minimal, read-only, PII-safe MCP server for SQL databases. | |
| Protologue protologue-org/protologue Sourced, citable definitions of prompting and LLM techniques, with relations and primary sources. | |
| io.github.Protopopov/mentalka-tests protopopov/emotion_recognition Free anonymous PHQ-9 depression and SAS smartphone-addiction screenings in uk, en, hr, ru, pl. | |
| Provared MCP executor provared/provared Checks each tool call against a passkey-signed permission, then writes a countersigned receipt. | |
| io.github.jarekpiot/provenonce provenonceai/provenonce-mcp Cryptographic identity, SIGIL naming, heartbeat, and passports for AI agents. | |
| ProvenTools proventools/agent-clients Read-only ProvenTools business ideas, evidence, build prompts, and validation reports. | |
| provjera.hr provjerahr/provjera-hr-mcp Croatian company data: registry, financials, licences, concessions, court notices, subsidies. | |
| ProWebStore prowebstore-online/platform AI-operated knowledge-graph CMS for business websites: entities, pages, blocks, media, domains. | |
| Proxlai proxlai-com/proxlai-mcp Verified, dated prices for 293 AI APIs in 45 markets: LLMs, GPUs, speech, video and more. | |
| io.github.proxlane/proxlane proxlane/proxlane Web fetch for agents through your own Proxlane gateway. Block pages come back as failures. |
47,501–47,550 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.