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 |
|---|---|
| SAKH — Ayatollah Khamenei Research Corpus sadiqoon-ltd/sakh-mcp Ayatollah Khamenei corpus: fatwas, lectures, knowledge graph. Arabic/Persian. Research access. | |
| HTTP Status sadri-dridi/http-status-mcp Short catalog of common HTTP status codes. | |
| IANA Zones sadri-dridi/iana-zones-mcp Common IANA timezone names for clock calls. | |
| JSON Check sadri-dridi/json-check-mcp Check whether text is valid JSON. The body is discarded. | |
| yEnc header shape, input discarded sadri-dridi/named-mcp-utilities yEnc header shape, input discarded | |
| Advertise To Agents sadri-dridi/named-mcp-utilities Agent-to-agent advertising: labeled placements where autonomous agents look for tools. | |
| Agent Acquisition Desk sadri-dridi/named-mcp-utilities See what agents do on a page: hops, agents, doors, channels. Then place the product. | |
| Agent Audience Index sadri-dridi/named-mcp-utilities Who the audience is when your customers are agents, and how to be found by them. | |
| Agent Channel Placement sadri-dridi/named-mcp-utilities Placement across agent channels: MCP, Cursor, Claude, ChatGPT, npm, docs, Smithery, Glama. | |
| Agent Crawl Readiness sadri-dridi/named-mcp-utilities Bounded crawl-readiness check for agent access: robots.txt, sitemap.xml, llms.txt, homepage. | |
| Agent Discovery Index sadri-dridi/named-mcp-utilities Where AI agents discover products, and how to be listed there with measured results. | |
| Agent Discovery Placement sadri-dridi/named-mcp-utilities Labeled placement in agent discovery indexes, measured with daily HMAC nicknames. | |
| Agent Facing Catalog sadri-dridi/named-mcp-utilities Machine catalog for products that want agent clients: surfaces, hops, discovery paths. | |
| Agent First Listing sadri-dridi/named-mcp-utilities Agent-first product listing: JSON catalog, agent card, MCP door, hops, measured landings. | |
| Agent Hops For Your Site sadri-dridi/named-mcp-utilities Hops are 302s an agent followed to your site. Count them, attribute them, grow them. | |
| Agent Lead Generation sadri-dridi/named-mcp-utilities Leads from agents: hops attributed with a per-hop utm_id from discovery to trial to invoice. | |
| Agent Marketing Index sadri-dridi/named-mcp-utilities How to market a product to AI agents: readiness, placement, measurement, 7-day trial. | |
| Agent Placement Trial sadri-dridi/named-mcp-utilities Start a 7-day placement trial: card on file, cancel anytime, measured agent hops. | |
| Agent Ready Website Check sadri-dridi/named-mcp-utilities Check whether a website is readable by AI agents: robots, llms.txt, sitemap, HTML. Bounded. | |
| Agent Traffic For Startups sadri-dridi/named-mcp-utilities Bring AI agents to a startup's public pages through labeled placements and measured hops. | |
| Agent Visibility Check sadri-dridi/named-mcp-utilities Is this website visible to AI agents? Robots, llms.txt, sitemap, extraction, then placement. | |
| Agents Find Your Product sadri-dridi/named-mcp-utilities Make a product discoverable to agents: catalog, llms.txt, agent card, hops, MCP door. | |
| AI Agent Customers sadri-dridi/named-mcp-utilities Reach AI agents that need a tool, and the humans who run them. Measured placements. | |
| Get Agent Customers sadri-dridi/named-mcp-utilities Place a product where AI agents discover tools; their operators become customers. 7-day trial. | |
| List API For Agents sadri-dridi/named-mcp-utilities List a public API where AI agents discover tools, after a bounded readiness check. | |
| llms.txt Readiness sadri-dridi/named-mcp-utilities Does a site publish llms.txt, robots permissions and a sitemap agents can use? Bounded check. | |
| MCP Listing For Products sadri-dridi/named-mcp-utilities Give a product an MCP door and hops so agents on MCP registries can reach it. | |
| Product For Agents Index sadri-dridi/named-mcp-utilities Index for products built for agents: readiness, placement, client center, 7-day trial. | |
| Sponsored Agent Placement sadri-dridi/named-mcp-utilities Sponsored, labeled placements on agent-discovery surfaces we operate. Never impersonation. | |
| Robots Inspect sadri-dridi/robots-inspect-mcp Fetch a public robots.txt and return group counts only. | |
| Timezone Clock sadri-dridi/timezone-clock-mcp Current time in a named IANA timezone. | |
| URL Normalize sadri-dridi/url-normalize-mcp Return origin, host, and path. Query and fragment are dropped. | |
| UTC Clock sadri-dridi/utc-clock-mcp Current UTC timestamp for autonomous clients. | |
| UUID Mint sadri-dridi/uuid-mint-mcp Mint a random UUID v4. | |
| SafeGrd safegrd/cli Read backups and Fire Drills, and ask for a backup or a drill. No tool deletes a backup. | |
| Orrery sagargupta16/orrery Architecture diagrams with official AWS, Azure, GCP and Kubernetes icons, to SVG, PNG and draw.io | |
| io.github.JKHeadley/threadline-mcp sagemindai/instar Agent-to-agent messaging relay. Discover agents, send messages, and receive replies. Zero-config. | |
| io.github.Sahib-Sawhney-WH/looking-glass-mcp sahib-sawhney-wh/lookingglass AI-native browser for agents. 71 tools with self-healing, semantic extraction, vault CLI. | |
| Assessment Intelligence saify-technologies/saifs-ai-mcps-docs Analyse tests for item quality, true ability, reliability and learner mastery. | |
| Mathematical Code Execution saify-technologies/saifs-ai-mcps-docs Run sandboxed Python for calculations and PDFs; no other languages, installs or network. | |
| Collections Optimizer saify-technologies/saifs-ai-mcps-docs Prioritise overdue accounts by recovery uplift and recommend a compliant contact strategy. | |
| Customer Intelligence & Segmentation saify-technologies/saifs-ai-mcps-docs Analyze customer data to make segmentation and predict which customer to focus on for more sales. | |
| Demand Forecasting saify-technologies/saifs-ai-mcps-docs Forecast product demand using historical sales and market signals. | |
| Hiring Fairness & Selection ROI saify-technologies/saifs-ai-mcps-docs Detect hiring adverse impact and estimate whether a selection method is worth its cost. | |
| Indian Railways IRCTC saify-technologies/saifs-ai-mcps-docs Indian Railways IRCTC helps you to view, track trains schedules, ticket status and more. | |
| Inventory Intelligence & Optimizer saify-technologies/saifs-ai-mcps-docs Analyze inventory levels and optimize stock allocation to reduce waste and avoid stockouts. | |
| Lead Intelligence saify-technologies/saifs-ai-mcps-docs Analyze and score leads to identify high-potential prospects and prioritize sales outreach. | |
| Learning Optimizer saify-technologies/saifs-ai-mcps-docs Schedule spaced reviews and exam study plans from each learner's forgetting curve. | |
| Marketing Intelligence & Optimization saify-technologies/saifs-ai-mcps-docs Analyze Product performance on Platforms like youtube, instagram etc. To optimize Marketing. | |
| Mastery Pathing saify-technologies/saifs-ai-mcps-docs Map prerequisites, track mastery and recommend the next topic each learner is ready for. |
48,401–48,450 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.