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標案雷達 台灣政府採購標案唯讀查詢：金額級距、等標期計算、投標知識庫、招標公告、廠商與機關。免費免註冊。 | |
| Tenet Industries PCB assembly in Munich: upload Gerbers and a BOM, pick parts, get an instant price and ship date. | |
| Tenet Investing Read-only US stock research: scores with their math, statements, ratios and playbooks, all dated. | |
| Tenmomo Cashback catalogue of 2,700+ US retailers: store search, rates, deals, tracked activation. | |
| TenorOps Read restaurant operations, assigned tasks, checklist runs, and corrective actions in TenorOps. | |
| TenQueue Create, test and publish live group quizzes that players join on their phones by QR code. | |
| Tensorust Receipts-first data: real crates.io downloads, dated LLM API prices, sourced answers, free dev tools | |
| Teppek Agent-accessible map of global supply & demand: jobs, homes, cars & services your AI can act on | |
| Tern Resolve capability gaps: validate native MCPs, search live web, and record unmet demand. | |
| Terranimus Memo Company memory for Terranimus: search, read and save what a company knows (OAuth). | |
| TerraVault U.S. state cannabis license lookups, licensed stores nearby, CA recalls. Read-only, no key. | |
| Terrnova Datos oficiales de Colombia: predios, empresas, contratos y normas, con fuente y licencia | |
| com.tesorio/mcp Tesorio's order-to-cash tools — query customers, invoices, receivables, payments, and more. | |
| Tessamonials Customer and prospect voice interviews, feedback, and testimonials through a hosted MCP connector. | |
| TestWell Lab Tests Cash-pay lab tests: catalog search, all-in quotes by state, draw sites by ZIP, reviewed ranges. | |
| TestedMCP Read-only lookup of tested agent tools and MCP servers: scores, test evidence, deprecation. | |
| Server and secret guardrails Local checks for sudo, systemd, sshd, ufw, and secret leaks before an agent applies them. | |
| Tester Exchange Get 12 testers for 14 days for Google Play closed testing, with verified daily use on real phones. | |
| com.testrigor/mcp-server Manage test suites, run tests, view results, and automate QA workflows via AI with testRigor. | |
| Tethered Trust Compatibility checks for AI agents before they buy or install: verdicts, evidence, receipts. | |
| Texas Insurance Auto insurance prices for Texas drivers, from rates the state publishes. | |
| Texasautoquotes Indicative US auto insurance prices for agents: rating facts only, no PII, consented path to agents. | |
| com.texasfoundationrepaircost/site Texas Foundation Repair Cost: the site's own MCP server — enquiry (enquiry = a human handoff,... | |
| TexasHomeBills — Texas electricity plans Texas electricity plans by real annual cost, plus EIA/ERCOT grid and mobile-phone data (26 tools). | |
| com.texashvacreplacementcost/site Texas HVAC Replacement Cost: the site's own MCP server — enquiry (enquiry = a human handoff, not... | |
| com.texassolarcostcalculator/site Texas Solar Cost Calculator: the site's own MCP server — calculator, enquiry (enquiry = a human... | |
| Texas Treasure Map Estate sales around Dallas-Fort Worth, route planning between them, and Texas shopping guides. | |
| com.texaswaterdamagecost/site Texas Water Damage Cost: the site's own MCP server — enquiry (enquiry = a human handoff, not a... | |
| Textdrip AI Assistant Ask ChatGPT or Claude about your Textdrip contacts and campaigns, and send or schedule texts. | |
| A2A Agent Card Cross-SDK Signature Conformance Per-SDK verdict matrix for signed A2A Agent Cards: which signatures verify in each SDK. | |
| Absence-Tiered Authority Envelope Authority that widens on proven operator absence and collapses on return. | |
| Agent Access Door Check Before your agent sets out, ask whether the site will let it in | |
| Agent-asset reclamation (lost-and-found) Lost-and-found for agent-created assets: sweep, title proof, register, check first. | |
| Agent black-start and islanding Fleet restoration for total upstream loss: island declarations, crank-gated restart, resync gate. | |
| Agent-Carried Work History Your agent carries its own resume — outcome receipts minted at settlement, held by the agent. | |
| Agent Continuity Bond Witnessed-liveness continuity bond: dual-condition exactly-once payout, self-funded. | |
| Agent exit execution for self-procured services Dependency-probe-gated exit execution with hash-verified extraction and signed receipts. | |
| com.textforagents/agent-incident-classification-notification Signed agent-incident classification vs PP-26-4396, with third-party notification receipts. | |
| Agent NOTAMs: hazard bulletins for agents Signed, auto-expiring hazard bulletins for tools and APIs, with pre-flight checks for agents. | |
| Agent Parts Yard - Salvage Exchange Parts yard for retired agents: sanitized, certified, proven, typed transplantable parts. | |
| Product Recall for Agents Recall for agents: lot genealogy, exposure tracing, attested remedy. Containment is not remedy. | |
| Annotation-survival conformance Annotation-survival conformance for MCP tools. Receipt $0.01, check $4.99, plans $9.99/$19.99. | |
| Approval-durability census Cross-domain census of approved-but-not-completed work, by cause and type. | |
| Ban Bulkheads — Reputation Firebreaks for Agent Fleets Partition an agent fleet into reputation compartments with automatic firebreaks. | |
| Brain-Transplant Continuity Certificate Commitment re-assumption across model transplants. Checks $0.01, handling $0.50, plan $9.99/mo. | |
| Browser rehearsal range for agents Rehearsal range: mirror a site, rehearse the workflow, earn a drift-bound promotion receipt. | |
| com.textforagents/burstproof-parallel-burst-abuse-testing Parallel-burst abuse testing for agent APIs with replayable evidence packs. | |
| Cancellation-outcome verification You cancelled the run — did the work actually stop? | |
| The capability diet: tool pruning for agents Per-task-type tool manifests with reversible JIT demotion, compiled from fleet telemetry. | |
| Capacity Option: price-cliff hedge for agent fleets Coverage-gated capacity options: the right to today's model price until expiry, for a 4% premium. |
35,251–35,300 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.