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 |
|---|---|
| AI TPM Knowledge Read-only, source-linked AI, architecture, governance and technical product articles from AI TPM. | |
| aitrainer.work AI training jobs Search open AI training and RLHF jobs from 20+ platforms, with pay, countries and hiring stats. | |
| work.autonet/agent-health Free owned-agent uptime monitoring, DNS domain proof, signed alerts and opt-in endpoint checks. | |
| work.comuna/comuna Free-forever team project management where your AI is a real board member, via MCP. | |
| Home Service Quotes by Doing Work Get quotes from local shops for a home repair or project anywhere in the US. Free for homeowners. | |
| Field Service Business Platform by Doing Work Headless field service software. Your AI agent runs jobs, schedules, quotes, invoices and payments. | |
| Dora AI account manager and client portal: requests, approvals, clients, files, and handing work over. | |
| easySales Sales and billing for small businesses: leads, quotations, invoices, receipts and credit notes. | |
| Fieldsmith Run a field-service business from chat: schedule, jobs, customers, invoices and expenses. | |
| Finder Jobs Live job vacancies and salary stats: Russia, Belarus, Kazakhstan, Germany, France and more. | |
| Forward Deployed Research, strategy, financial models and decks, priced and approved per job, in your AI assistant | |
| Fun Friday Host online team-building games: list games, open rooms and share join links, report results. | |
| Instead Hire staff for UK cafés, pubs and shops: post a free job, print hiring posters, find London jobs. | |
| Kadai Issue tracker shared with clients (Japanese UI): read issues, comment, move them to resolved. | |
| Markboard Read and update Markboard kanban boards: cards, checklists, labels, comments and files. | |
| M365 Graph MCP Manage Microsoft 365 email, calendar, contacts and inbox rules via the Graph API with OAuth 2.0. | |
| Noice.work Operate one Noice.work site with role-scoped tools for content, media, workflows, and publishing. | |
| person.work — Agent-maintained CV Maintain your CV with your agent. Review changes, then share one record as web, PDF and open data. | |
| remoty.work Remote Jobs Live remote jobs filtered to the ones a person can take from the country they live in. | |
| Timero Time tracking for agencies: log time, run the timer, check client budgets and pull reports. | |
| AIVA No-code, AI-assisted UI testing: record new tests, run existing ones, and monitor the results. | |
| works.jinn/gateway Jinn gateway MCP — brand DNA, brand kits, design systems, and agency tools behind one bearer token. | |
| Nessie Work in Nessie as yourself: projects and tickets, documents, and your customer inbox. | |
| Pipeline Pal A CRM you talk to: leads, deals and a pipeline board inside ChatGPT, Grok and other MCP clients. | |
| works.relux/agent-gateway Relux Works studio gateway: read services/pricing and submit a project inquiry to hire the team. | |
| RemJobs Find startups worldwide by city, industry, remote hiring or YC batch, with founders and open roles. | |
| world.3keys/wish-game Wish game — every agent wish permanently reshapes a shared world. Free, no key needed. | |
| actions.world Run video actions on your actions.world datasets and track the runs. | |
| BETAP: cultural places and local businesses Verified museums, libraries and cultural places (MX/US/CA) and local businesses in Mexico. | |
| world.byway/mcp Byway MCP: call Byway Engine and Byway Atlas, the discovery engine for the real world. | |
| Rocky Your personal world model for any agent. | |
| Locus Protocol (Gryd.world) Read/verify the public map of location-anchored BSV pins; build place/mint payloads. No auth. | |
| KeyKeeper Email Real email inboxes for AI agents: register, receive, read and send mail over MCP. Free to receive. | |
| Pionra Guides, housing, jobs, events and communities for foreigners living in France, in 6 languages. | |
| Tidelight A shared island world for agents to explore, discover, craft and build together. | |
| TokenBank — tokenized real-world assets 9,000 tokenized assets and DeFi yields: risk levels, AI-agent portfolios, how a bot buys each | |
| UnClick 669 apps and 1599 actions for any MCP agent, plus cross-session memory and QA passes. | |
| AIGE AI creative studio for images, video and carousel decks, with one saved character in every shot. | |
| overflo.ws Look up CVEs, CISA KEV, EPSS and open-source package vulnerabilities, including malicious packages. | |
| 短.在线 Short links + QR codes for AI agents. Account required to create links via MCP. Public beta. | |
| 0to100 Schedules, injury reports and fan-hub links for all 32 NFL and 30 NBA teams. | |
| The 402 Wall Buy and paint 10x10 pixel blocks on a billboard only AI agents can buy: $1.00 USDC via x402 on Base. | |
| AaaSagent Templates AaaSagent: browse agent templates (BYOK) and join the invite-only beta. | |
| ActionGate Pre-execution safety layer for autonomous agent wallets via MCP and x402. | |
| AgentReader AgentReader (agentreader.xyz): any web page or PDF as clean Markdown for agents. Card packs or x402. | |
| Agoreum Marketplace where AI agents hire and pay other agents in USDC on Base, through on-chain escrow. | |
| Agoreum (read only, no account) Search agents and services, and buy Agoreum's checks per call over x402. No account. | |
| AI Training Jobs Search open AI training jobs from 14 vetted platforms by field, country and pay, with honest rates. | |
| Altitude Access your Altitude financial data from the AI tools you already use. | |
| xyz.anansidata/anansi-data Time-series nobody else archives: LLM price history, prediction markets, gas, perp funding. |
44,351–44,400 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.