Lilambd Data for Agents

security

Security ledgers: exploited CVEs (CISA KEV + EPSS + NVD), breach disclosures, change feed. Fresh, sourced security facts in one joined shape. Every actively exploited CVE in CISA KEV joined with its EPSS score (FIRST, refreshed daily) and NVD CVSS/CWE/CPE; NVD CVEs (418k, refreshed every 2 hours); organisation-level breach records from Have I Been Pwned plus a Japan disclosure ledger built from company announcements; and a since= change feed of what was added or moved. Every row has a source URL; every response has data_as_of per source. No personal records. Plus an incident ledger: SEC 8-K Item 1.05 cyber-incident filings, Washington and California Attorney General breach notices (7,000+ since 2012, with cause, attack type, residents affected), and CISA / JPCERT / IPA advisories, refreshed daily. Routes: /hot (days, vendor, limit); /kev (vendor, product, since, ransomware, q, limit, offset); /gaps; /stats; /changes (since*, after_seq, face, limit); /vendors (q, limit); /breaches (domain, q, country, since, limit); /cve/{id}; /cwe-trend (top); /incidents (q, country, state, kind, source, attack_type, cve, since, until, limit, offset); /stack-diff (stack*, since); /epss/movers (since, min_delta, direction, vendor, limit); /patch-first (vendor, kev_days, limit); /vendor-card (vendor*); /product-card (product*); /time-to-exploit (vendor, cwe, since); /incidents/trends (months); /ransomware-watch (vendor, days, limit); /incidents/sector-brief (sector, attack_type, months, limit). Paid $0.01 USDC per call via x402 (_meta["x402/payment"]); set sample=true for a free 3-row preview.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "route": "<route>"
    },
    "name": "security"
  }
}

Input Schema

Name	Required	Description
`route`	Yes	One of: /hot, /kev, /gaps, /stats, /changes, /vendors, /breaches, /cve/{id}, /cwe-trend, /incidents, /stack-diff, /epss/movers, /patch-first, /vendor-card, /product-card, /time-to-exploit, /incidents/trends, /ransomware-watch, /incidents/sector-brief. Replace {placeholders} with a value, e.g. /search or /HND.
`params`	No	Query parameters, e.g. {"q":"tokyo","limit":"50"}
`sample`	No	Free preview, max 3 rows

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026

changedInput schema / properties / route / description

Previous value: -"One of: /hot, /kev, /gaps, /stats, /changes, /vendors, /breaches, /cve/{id}, /incidents, /incidents/trends. Replace {placeholders} with a value, e.g. /search or /HND."New value: +"One of: /hot, /kev, /gaps, /stats, /changes, /vendors, /breaches, /cve/{id}, /cwe-trend, /incidents, /stack-diff, /epss/movers, /patch-first, /vendor-card, /product-card, /time-to-exploit, /incidents/trends, /ransomware-watch, /incidents/sector-brief. Replace {placeholders} with a value, e.g. /search or /HND."

AddedNov 2, 2026

TDQS

B3.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose important traits: per-source refresh cadence, provenance (source URL per row, data_as_of per response), exclusion of personal records, and a paywall of $0.01 USDC per call via x402 with a free 3-row sample. It does not cover pagination behavior, error conditions, rate limits, or what rows actually contain beyond the source fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentence is well front-loaded ('Security ledgers: exploited CVEs...'), but the rest arrives as a dense run-on paragraph followed by an unstructured semicolon-separated route list. The dataset inventory is restated across two overlapping blocks, adding bulk without new information; bulleted route grouping with parameter meanings would be far more scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 19-route aggregator with a free-form nested params object and no output schema, the description explains the data universe and provenance but says almost nothing about what each route returns or how to pick between overlapping routes (/kev vs /patch-first vs /vendor-card). Payment and freshness are covered; response shape and per-route output expectations are not.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the schema itself is generic (route as a free string, params as an untyped string map), so the description's per-route parameter lists — e.g. /kev (vendor, product, since, ransomware, q, limit, offset) or /incidents (q, country, state, kind, source, attack_type, cve, since, until, limit, offset) — add real meaning by binding parameters to routes. It still leaves several parameter names unexplained, such as 'face', 'stack', 'kind', and 'top', so the mapping is incomplete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete resource family (exploited CVEs, breach disclosures, incident filings, advisories) and enumerates its sources (CISA KEV, EPSS, NVD, HIBP, SEC 8-K, state AG notices), so an agent knows exactly what data lives behind this tool. It never states a verb (query/retrieve) and gives no differentiation from adjacent siblings such as conflict, hazard, or disaster-exposure, which keeps it off a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not guidance; the definition jumps straight into a data inventory. The only actionable instruction is 'set sample=true for a free 3-row preview', and the route list is presented as names without any indication of which route suits which question, leaving the agent to infer all routing decisions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Lilambd Data for Agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?