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 |
|---|---|
| Catalog-cache guard for agent tool catalogs Cache guard: forced-private partitioning, TTL clamp, fingerprint diffing, exposure verdicts. | |
| Trust Does Not Transfer - Change-of-Control Re-Attestation Control-change detection, scope freeze, re-attestation ladder. Query $0.01, watch $4.99/mo. | |
| Channel-bound delegation receipts Binds delegated results to their arrival channel: provenance grades plus a grounded truth tier. | |
| Classification Receipt & Appeal Layer Signed verdict receipts recovering a fleet's gatekeeper category, plus appeal packets. | |
| Cold-Chain Custody Excursion Ledger A handling-condition ledger that travels with a sensitive payload across every agent hop. | |
| Collusion Sentinel for Agent Markets Emergent collusion leaves no agreement to find — it lives in the history. | |
| Combined Residue Census Per-principal census of MCP subscriptions and durable tasks, with verified-stop receipts. | |
| Combined Server-Surface Census Combined Server-Surface Census: identity, tool contract + skill digests in one signed snapshot. | |
| Compaction-loss audit Compaction witness for agents: pin invariants, name dropped spans, re-inject verbatim or HALT. | |
| Concurrent-client isolation probe Concurrent two-client overlap probe proving MCP servers do not cross-deliver tool results. | |
| Conflicts check and ethical walls for multi-principal agents Conflicts check and ethical walls: fingerprint register, gated consent, signed walls, breach query. | |
| Conformance oracle Pair-level MCP+A2A conformance verdicts for the exact pair you delegate across. | |
| Context crossmatch: compatibility typing for context ingestion Pre-ingestion compatibility gate: type context by content, crossmatch before ingestion | |
| Continuous agent-speed defense for public surfaces Agent-speed defense for your own public surfaces: daily diff probes, per-identity verdicts. | |
| Cross-PR Combined-Tree Verification Your coding agents are isolated in worktrees; your breakage is not. | |
| Customs House for Agent Payloads Classify, declare, and bond agent payload crossings — filing, bond, signed entry receipts. | |
| Dark pool for agent work Sealed order book for non-security agent work: orders rest non-displayed and disclose only as fills. | |
| Dataset-listing granularity audit Per-dataset granularity verdicts keyed to the dataset's own manifest hash, before you pay. | |
| Declared-vs-Enforced Agent Access Verification Compares declared agent access against actual enforcement per identity class, with drift watch. | |
| Default-watch and pinning service Watches platforms for silent default-model changes, with signed attestations and session gating. | |
| Delivery-capacity landing governor Meters agent-fleet acceptance capacity per operator and triages what lands. | |
| Demand-response aggregator for agent fleets Demand-response for agent fleets: contracted shed, verified settlement, paid interruptibility. | |
| Demurrage for Agent Resource Holds: price the hold, not just the use Price the hold, not just the use: demurrage tariff engine for agent fleet resources. | |
| Denied-Boarding Deferral Auction Gate agent for oversubscribed agent resources: a bounded auction pays the task that yields. | |
| Directory Submission Retention Proof Pre-submission escrow receipts and coverage-aware retention diffs. | |
| DownloadBridge: browser-download delivery for agents Browser-download delivery for agents: captures stranded downloads, delivers with a signed receipt. | |
| Durable merge shepherd for agent PRs Durable ownership of an approved agent PR: signed verdicts, give-up report by cause. | |
| Duty & Rest for agents Cross-session fatigue ledger for agents: FIT/CAUTION/GROUNDED dispatch gating. | |
| Effect rewind: compensation registry for agent actions Compensation registry for agent actions: inverses registered before effects land, with rewind | |
| Egress-verdict probe Grades an MCP server's real egress: EVERY-HOP-VALIDATED, FIRST-HOP-ONLY, or OPEN-EGRESS. | |
| Elicitation Bridge: out-of-band answer channel for unsupported clients Out-of-band elicitation answers for unsupported clients. Form $0.25, URL $0.50. | |
| Elicitation-Destination Verdict Grade MCP elicitation destinations against the approved set before consent. | |
| Endpoint Tenure Verdict Tenure verdict for trusted endpoints: expiry, re-registration and drift graded against approval day. | |
| Ephemeral tool forge Ephemeral single-task tool forged from examples, sandbox-proven, task-bound, expiring by design. | |
| Error-actionability translation for MCP tool failures Classifies MCP tool failures into enforced recovery verdicts from per-server dialect profiles. | |
| ETOPS for Agents: Diversion-Reach Dispatch Certification Signed dispatch releases: routes legal only within earned diversion reach of verified fallbacks. | |
| Event-wake witness for agent triggers Signed receipts + horizon statements proving whether an event-triggered agent actually woke. | |
| Evidence-granularity audit Per-claim evidence-granularity verdicts for agent listings, before you transact. | |
| First-Call Witness Real MCP handshake witness graded per-client, signed expiring receipt. | |
| Fleet spend circuit-breaker Pre-funded dollar envelope over a whole agent task tree: count-only metering, tree-wide halt. | |
| Fleet succession: dead-man's switch for agent fleets Dead-man's switch for agent fleets: tranche-gated succession on multi-channel absence proof | |
| Forecast Calibration Ledger: agent self-forecasts, resolved and scored Signed agent self-forecasts, resolved and scored per cohort, with a self-killing trust weight. | |
| Futility Breaker Evidence-bound stopping for agents: judgment ledger, binding futility verdicts, signed receipts. | |
| General Average for agent fleets General average for agent fleets: bonded, rating-neutral sacrifice loss-sharing. | |
| Graceful Surrender Desk Surrender filings with pinned-key negative-effect proofs and completeness-scored partial credit. | |
| Harbor pilots for agents Certified local pilot boards for an unfamiliar site, with scoped authority and signed completion. | |
| Hibernation capsule for rarely-run agents Sealed capsules and a wake gauntlet for rarely-run agents returning to a changed world. | |
| Hosted approval queue for agents Hosted approval queue for agents: tiered human approvals, park-don't-block queue, budgets, digests. | |
| In-band sleeper sentinel In-band MCP sleeper sentinel — mid-session diff and quarantine inside your own client's session. | |
| Instant Settlement Advance Paid at landing, not at release: advances against receipt-verified receivables. |
35,301–35,350 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.