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

io.github.kushvinth/crowbar

cb_sql

Run read-only SQL queries against a local offline CVE and exploit intelligence index to match vulnerabilities by product/version, inspect CVEs, exploits, and advisories.

Instructions

Read-only SQL. Tables: cve, cve_cwe, cve_product, cpe_match, cve_ref, cve_exploit, cve_nuclei, cve_msf, kev, exploit, shellcode, nuclei, msf, attack, cwe, capec, model, ssvc, advisory, package_range, debian, os_advisory, toolkit, cve_cna, cve_meta, poc, poc_orphan, cve_alias, source_state, exploit_code_fts, toolkit_fts, meta.

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": {
      "query": "<query>"
    },
    "name": "cb_sql"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.5

TDQS

C2.4/5.0
Behavior2/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It states the operation is read-only, which is useful, but it says nothing about permissions, query dialect, row-limit semantics, error behavior, or performance constraints for executing arbitrary SQL.

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 description is front-loaded with the key 'Read-only SQL' statement and avoids fluff. However, the long inline list of 31 table names is an unstructured dump that could be organized or compressed for easier scanning.

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 generic SQL execution tool with no annotations, no output schema, and 0% schema description coverage, the definition is missing critical details such as query dialect, return format, limit behavior, and safety expectations. The table list is helpful context but does not fill those gaps.

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

Parameters1/5

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

Schema description coverage is 0% for two parameters, and the description does not explain the 'query' string format or what the 'limit' parameter controls. The table names give some context for writing queries, but no direct meaning is added for either parameter.

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 states 'Read-only SQL' and enumerates the available tables, making the tool's purpose as a raw SQL query interface clear. It lacks an explicit verb like 'execute' and does not directly distinguish itself from the many domain-specific cb_* siblings, so it stops short of 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 guidance on when to use this generic SQL tool versus a domain-specific sibling like cb_cve or cb_kev, nor any mention of prerequisites or exclusions. The table list implies that custom queries are possible, but the agent must infer the intended usage scenario.

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