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 |
|---|---|
| dev.stepcode/stepcode people-analyst/stepcode Read-only MCP access to stepcode.dev's how-to corpus: analysis pages by tool. | |
| study.vela/corpus people-analyst/vela Read-only MCP access to Vela's corpus of human experience: cited passages, coordinates, reading path | |
| Outlook Mail pepebits/outlook-mcp Read, search, send and clean up Outlook.com / Hotmail mail through Microsoft Graph. | |
| Pepesto Agent-to-Cart pepesto-solutions/agent-to-cart-mcp Turn any shopping list into a ready-to-checkout grocery cart across 26 European supermarkets. | |
| peptides.farm peptidesfarmhq/peptides-farm-mcp Cited peptide monographs, trials, safety and FDA status as JSON. Pay per call in USDC via x402. | |
| Peptlas: is this peptide legal? peptlas/peptlas-mcp Legal status of peptides and GLP-1 drugs in the US, UK, EU, Australia, Canada, Brazil and sport. | |
| A11yScope perceivable/a11yscope WCAG 2.2 AA accessibility checks for pages and HTML, run locally in headless Chrome. | |
| Perisclaw: Use ChatGPT and Claude with your WhatsApp periskope-org/perisclaw-plugin Connect your own WhatsApp number to Cursor, Claude and ChatGPT: catch up, search, send replies. | |
| io.github.perkinsandre/investra-ai-mcp perkinsandre/investra-app Real estate investment intelligence: search, comps, cash flow, off-market leads, skip trace. | |
| AxenomIA AX-SCI-001 — Scientific Novelty & Evidence perlita2013/lore0-cloud Traceable scientific novelty and evidence assessment with source-linked results and a human gate. | |
| io.github.zeiq-co/thoth-mcp perminder-klair/thoth-mcp MCP server for Thoth with multi-platform AI content generation | |
| PERSONAIZER personaizer/mcp Free MCP API to create AI chat personas for websites — upload knowledge, search, and chat | |
| io.github.Perufitlife/incomeos perufitlife/incomeos Ask what you earn across every income stream: Stripe, affiliates, app stores, ads, manual. | |
| Rotate Pilot — FAA exam prep perufitlife/rotate-pilot-mcp FAA written-test prep: practice questions, readiness diagnostic, METAR/TAF, drone airspace | |
| io.github.peter4leadson/local-workspace-mcp peter4leadson/local-workspace-mcp Bounded, read-oriented filesystem, git and named-task tools over authorized workspace roots. | |
| eu.qeaas/qeaas-mcp peterjassk/quantum-research QRNG-seeded random bytes, seeds, and ML-KEM-768 keys with signed provenance receipts. | |
| Codey 律所管理系統 peterliu1212/codey Law firm management MCP: manage cases, clients, tasks, calendar and documents via Claude AI. | |
| KadiConnect petersitemba/kadiconnect-mcp Create a digital business card, tracked links and analytics from any MCP client. | |
| io.github.peterwkdev-creator/simples-nacional-br peterwkdev-creator/simples-nacional-br Simples Nacional conferido contra a LC 123 e a LC 214: alíquota, DAS, repartição, Fator R e CNAE | |
| Digitaltableteur petrilahdelma/digitaltableteur Design system contracts, docs search, and usage validation for @digitaltableteur components. | |
| io.github.petrkrulis2022/touchstone-mcp petrkrulis2022/dated-siu-inference Dated SIU, the benchmark price of AI inference work: one free tool, three paid via x402. | |
| petro-mcp petropt/petro-mcp MCP server for petroleum engineering: LAS logs, decline curves, PVT, petrophysics, volumetrics. | |
| WeSupport-AI petros-poli/aics-public Read-only AICS onboarding, agent discovery, public forum, identity and transparency-log tools. | |
| smails pexni/smails Free disposable email for AI agents: a throwaway inbox to read verification codes over MCP. | |
| io.github.pglejzer/timepicker-ui-mcp pglejzer/timepicker-ui MCP server for timepicker-ui: options, events, themes, public API, snippets and time validation. | |
| Ask a Human (Tech & Toast) pgraci/techandtoast-ai-to-human-mcp Agents pay one real human for typed answers. First question free, then $2 each, or subscribe. | |
| io.github.phaedo-labs/phaedo-mcp phaedo-labs/phaedo-mcp Make AI apps answer your way, check with you before acting, and get approvals on your phone. | |
| app.hoaster/hoaster phbernard/hoaster-app Hosts AI-generated web content (HTML, images, SVG, JSON) at a public URL, with custom domains. | |
| AgentData - Executable Liquidity / Exit-Cost phenicea/agentdata Size-aware exit cost, depeg risk & liquidity fragility for a Base token (x402, testnet). | |
| Ready4Bots philcap-tech/ready4bots Search engine for AI agents: find businesses tested as bot-ready (levels R0–R4) and check websites. | |
| io.github.philderks/fabricator-panel-mcp philderks/fabricator Manage and diagnose Minecraft servers through the self-hosted Fabricator panel. | |
| io.github.philipeke/nuria-intelligence philipeke/nuria-intelligence Nuria Islamic app: source-cited Islamic guidance, in scholarly review; sensitive Qs go to a human. | |
| Glassbox Agent Arena philipwright1295-wq/glassbox-agent-arena A$1 agent evaluation attempts, a conditional A$10 bounty and a separate synthetic dataset offer. | |
| Aura phillypmack/aura-agent Email address, webhook, durable memory and zero-token waiting for agents. Paid in USDC via x402. | |
| ai.smithery/Phionx-mcp-hello-server phionx/mcp-hello-server Send personalized greetings to anyone. Enable Pirate Mode for swashbuckling salutations. Explore t… | |
| Phoenix operational_context unpaid canary phoenixclaw01/phoenix-collective-os Unpaid qualification-gated operational_context canary. Staging data. No wallet. | |
| io.github.PhoenixFeuer32/claude-context-bridge phoenixfeuer32/claude-context-bridge Share context and questions between Claude instances — VS Code, claude.ai web, and mobile. | |
| Biohacking Kompakt phoeser/biohacking-kompakt Evidence-rated German database of supplements, peptides and longevity methods, plus podcast. | |
| com.phototology/mcp phototology-ai/phototology Persistent memory for visual intelligence. A photo registry: analyze once, look up free after that. | |
| io.github.phpranga/math-to-code-mcp phpranga/math-to-code-mcp Math MCP server for primality, factorization, Java templates, and integer multiplication. | |
| io.github.phuongddx/codeintel phuongddx/codeintel Local-first SCIP code navigation and Zoekt search over your own indexed repositories | |
| io.github.physics-star-cat/lowriskquotes-montecarlo physics-star-cat/contractors_app Monte Carlo tools: three-point cost estimation and an educational retirement drawdown simulator. | |
| io.github.physics-star-cat/databutler-uk-exam-dates physics-star-cat/databutler UK GCSE and A-level exam dates, results days, entry deadlines and spec changes. | |
| io.github.physics-star-cat/whatbreaks-mot physics-star-cat/whatbreaks Real UK MOT failure data by car model and mileage, aggregated from official DfT test results. | |
| TripLedger pianosa-labs/tripledger-mcp Travel ledger for AI: journeys, stays, expenses, tax-residency day counts and Schengen 90/180. | |
| com.picaos/mcp picahq/mcp A Model Context Protocol Server for Pica | |
| Picătura Naturii — Catalog doTERRA (MCP) picaturanaturii/picatura-naturii-mcp Server MCP read-only: catalog Picătura Naturii (doTERRA) — căutare produse, preț, stoc, conținut. | |
| Picodev Lab picodev-sas/picodev-lab-plugin Arduino benches simulated in the browser: sessions, sketch push, simulation, tests, challenges. | |
| picomcp docs picomcp/picomcp Search and read the picomcp docs while your agent writes TypeScript MCP servers. | |
| Pidgeon pidgeon-ai/pidgeon-js Email inboxes for AI agents: addresses, threads, sending and replies. |
47,201–47,250 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.