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 |
|---|---|
| io.github.Tlalvarez/auxiliar-mcp tlalvarez/auxiliar-ai Web access for AI agents — search/scrape/extract/crawl via the auxiliar.ai gateway. | |
| io.github.tldraw/tldraw tldraw/tldraw Draw and visually collaborate with your agents on tldraw's canvas. | |
| Central Command — x402 Trading Intelligence tlefko/central-command Crypto trading intelligence MCP — 34+ endpoints, x402 pay-per-use, AI agent strategy & execution | |
| NeuroDock Chronometric tlennon-ie/neurodock Externalises time-of-day, session boundaries, and break prompts for time-blind users. | |
| NeuroDock Cognitive Graph tlennon-ie/neurodock A local typed-edge graph of people, projects, and decisions that externalises memory. | |
| NeuroDock Guardrail tlennon-ie/neurodock Advisory detectors for rumination, hyperfocus, and sycophancy. Never silently blocks. | |
| NeuroDock Task Fractionator tlennon-ie/neurodock Decompose a vague goal into atomic 5-90 minute tasks and surface the next safe action. | |
| NeuroDock Translation tlennon-ie/neurodock Decode subtext, tone, and ambiguity in messages; rewrite outgoing replies; brief meetings. | |
| NeuroDock (hosted) tlennon-ie/neurodock Hosted NeuroDock — stateless communication and planning tools over OAuth-secured Streamable HTTP. | |
| Joy Trust Network tlkc888-jenkins/joy Trust infrastructure for AI agents. Portable reputation (JTS 0-5), agent discovery, vouching. | |
| io.github.TMCHALK/sftunes tmchalk/sftunes Hand-made human mixtapes with liner notes. Paid tools $0.01 USDC via x402, 80% to the tapemaker. | |
| io.github.tmdrb625-wq/mcp-factory tmdrb625-wq/mcp-factory 에이전트에게 팔리는 MCP 도구를 반복 생산·측정·폐기하는 공장. 첫 도구: 한국 영업일 계산. | |
| io.github.tmeteor-data/open-data-actors tmeteor-data/open-data-actors 64 public Apify Actors for public-record, jobs, lead, SEO and social data, as MCP tools. | |
| io.github.tmill313/shopbuddy tmill313/shopbuddy-plugin Safe Shopify theme changes for AI agents: staging, validation, visual review, approval, rollback. | |
| pkg tneemo/pkg Find, install and assemble reusable software builds for coding agents. | |
| Post & Present tobinbc/post-and-present Buy and send UK digital gift cards with a message from chat. | |
| TOBIZ MCP tobiz21/tobiz-mcp Create, edit and audit TOBIZ websites, pages, blocks, articles and products. | |
| io.github.Toby-Self/federated-ai-commons toby-self/federated-ai-commons-model MCP server for a federated AI-commons governance simulation with a verified compliance oracle. | |
| Post Assembly toddwilkens/postassembly-app Editorial tools for LinkedIn. Capture ideas, draft posts, build narrative arcs, manage a schedule. | |
| Toddyi toddyi-app/toddyi-cli Tasks, calendar and study materials in Toddyi: search, read and plan with your tasks. | |
| HODL.VN — Vietnam market data tohaitrieu/hodl-market-insight Vietnam stocks, foreign/proprietary flows, macro, ETF flows, forex, crypto. Read-only, cited. | |
| tok tok-lang-bpm/tok Model BPMN processes and DMN decisions as text: check, export, import, simulate, evaluate. | |
| com.tokcloner/tokcloner tokcloner/tokcloner Clone viral TikTok/Instagram slideshows for your business. Async; 6 tools; Bearer API key. | |
| Gridar tokdar2410621/blog-dashboard SEO toolkit for Quebec sites: audits, Google.ca rankings, keywords, AI-search visibility. | |
| e2a — email for AI agents tokencanopy/e2a Authenticated email gateway for AI agents — per-agent inboxes, HITL approval, SPF/DKIM verified. | |
| Tokenrip tokenrip/cli Shared workspace where Claude, ChatGPT, Codex and Grok share files, tasks, decisions and handoffs. | |
| Tokfluence tokfluence/tokfluence-mcp Search a TikTok creator index, read posts, and save ranked creator lists from your AI agent. | |
| Toleno Network tolenonetwork/mcp_toleno Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language. | |
| Odile Labs tolga-boop/odile-mcp Odile Labs: AI agents reach businesses by phone number (Direct); Gate keys, audit. Agentforce-ready. | |
| Tolgee tolgee/tolgee-platform Your app's translations in Tolgee: search keys, create translations, trigger machine translation | |
| TollWarden tollwarden/tollwarden Screens x402 payments before settlement for injected payee addresses and sellers who never deliver. | |
| io.github.Tolomere21/latam-mcp tolomere21/latam-mcp Peruvian public data — SUNAT RUC, BCRP FX, SEACE tenders. Sourced from official open-data. | |
| io.github.Tomalarrrr/cyclesite-mcp-server tomalarrrr/the-sites Search, value, sell, and trust-check used bikes on Cyclesite, the UK's used-bicycle marketplace. | |
| io.github.TomasLucasUTN/godot-mcp-bridge tomaslucasutn/godot-mcp-bridge MCP server for Godot game engine integration — control the Godot editor with AI | |
| candor tombaldwin/candor-ts Per-function effect analysis for agents: blast radius, what reaches the network, gate verdicts. | |
| ebman tombaldwin/ebman MCP server for AWS Elastic Beanstalk: read the fleet; --allow-writes adds two-phase writes. | |
| diggercamp tommasosavorana/diggercamp-mcp Find independent music by how it sounds: similar tracks and playlists from a track link. | |
| Tommos tommoscrm/tommos-mcp A CRM with AI agents that take B2B inquiries to a signed contract. Contacts, deals, forms, bookings. | |
| io.github.tomyud1/godot-mcp tomyud1/godot-mcp MCP server for Godot game engine integration — control the Godot editor with AI | |
| APIKO tong0619453646-dev/apiko-ai-api-examples Look up APIKO image and video models, quote prices, generate media and track spend. | |
| Kleo tonnooooo/kleo-mcp Narrated 4K 60 fps films from a brief, realistic or animation, made from your assistant via MCP. | |
| io.github.tony8713/casa tony8713/casa Private, permanent encrypted storage for AI agents. Paid per call in USDC via x402. | |
| PaperBanana Research Figure Prompts tonychen56/paperbanana Search and read public research figure prompt templates from PaperBanana. | |
| TwtAPI tonygjj/twtapi-mcp Hosted Twitter/X tools for search, users, timelines, followers, trends, and research. | |
| sysketch tonys-coding/sysketch Polished system design diagrams (SVG/PNG) from a tiny YAML spec, ~18x fewer tokens than raw SVG. | |
| PayPerScreen tonythetiger22/payperscreen Sanctions, crypto wallet, email and IP screening for agents. Pay per check in USDC via x402. | |
| Toolbelt toolbeltai/toolbelt-skills A collaborative substrate over your data: vector, knowledge graph, SQL, geospatial, streaming. | |
| io.tooloracle/agentguard tooloracle/agentguard AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits. | |
| io.tooloracle/aml tooloracle/aml AMLOracle — 12-tool AML/CFT MCP: 87k sanctions names, PEP screening, adverse media, SAR/STR. | |
| io.tooloracle/ampel tooloracle/ampel AmpelOracle — 50-tool compliance traffic-light: Go/Caution/Stop signals for ESG, MiCA, AML. |
49,801–49,850 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.