cockroachdb-toolbox

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Security

Grade A, and why

cockroachdb-toolbox scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

.mcp.json · 18 lines

What it actually says

{
  "cockroachdb-toolbox": {
    "command": "toolbox",
    "args": [
      "--config",
      "${CLAUDE_PLUGIN_ROOT}/tools.yaml",
      "--stdio"
    ],
    "env": {
      "COCKROACHDB_HOST": "${COCKROACHDB_HOST}",
      "COCKROACHDB_PORT": "${COCKROACHDB_PORT}",
      "COCKROACHDB_USER": "${COCKROACHDB_USER}",
      "COCKROACHDB_PASSWORD": "${COCKROACHDB_PASSWORD}",
      "COCKROACHDB_DATABASE": "${COCKROACHDB_DATABASE}",
      "COCKROACHDB_SSLMODE": "${COCKROACHDB_SSLMODE}"
    }
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

Related

Other mcp servers, from other repositories