Skip to main content
Glama
io.github.kushvinth/crowbar

io.github.kushvinth/crowbar

cb_search

Search all CVEs from 2002 to today, ranked by relevance and exploit intelligence, and filter by severity, CVSS, EPSS, CISA KEV, public exploit, vendor, product, CWE, or year.

Instructions

Full-text search across every CVE (2002-today). Ranked by relevance blended with CISA KEV, EPSS and public-exploit availability. Filters: kev, exploit, min_epss, min_cvss, severity, year, since, cwe, product, vendor, ssvc, poc.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "cb_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
cweNo
kevNo
pocNoonly CVEs with a public PoC
sortNo
ssvcNonone | poc | active
yearNo
limitNo
queryNo
sinceNo
offsetNo
vendorNo
exploitNo
productNo
min_cvssNo
min_epssNo
severityNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.5

TDQS

C2.9/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden; it does disclose useful non-schema behavior — the corpus coverage (2002-today) and the ranking blend with KEV/EPSS/exploit data, which is real value. It omits that this is a read-only operation, says nothing about pagination or result-set sizing, and gives no indication of the response shape (there is no output schema).

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

Conciseness4/5

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

Two tight sentences, front-loaded with the core purpose and coverage window before the ranking detail and filter list. The trailing filter enumeration is dense but earns its place as a scannable capability summary; nothing is padded.

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

Completeness2/5

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

For a 16-parameter, annotation-free tool with no output schema, this is under-specified: query syntax, 'since' date format, min_epss/min_cvss ranges, sort behavior, and how limit/offset paginate are all unaddressed. The agent can construct a call, but not confidently.

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

Parameters2/5

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

Schema description coverage is only 13% across 16 parameters, so the description must compensate — but it merely restates parameter names already visible in the schema ('kev, exploit, min_epss, min_cvss, severity, year, since, cwe, product, vendor, ssvc, poc'). It adds no formats, thresholds, defaults, or interaction semantics, and silently omits query, sort, limit, and offset.

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?

Specific verb and resource: 'Full-text search across every CVE (2002-today)', plus the ranking model (relevance blended with KEV, EPSS, exploit availability). This clearly separates it as a ranked search rather than a fetch-by-ID tool, but it never names a sibling (e.g. cb_cve for a single CVE, cb_sql for arbitrary queries), so differentiation is only implicit.

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?

The description lists filters but gives no when-to-use guidance and no exclusions or alternatives among a 21-tool sibling set. An agent has to infer from the filter list that this is the entry point for exploratory, relevance-ranked lookups rather than structured retrieval.

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