Tinplate Edge AI Safety, Security & EU Compliance

tinplate_command_sql_guard

Read-onlyIdempotent

Agent Shell Command & SQL Query Safety Firewall API: Audit agent shell commands and Text-to-SQL queries for RCE, reverse shells, and destructive SQL. (Endpoint: POST /v1/command-sql-guard)

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": {
      "input": "<input>",
      "mode": "<mode>"
    },
    "name": "tinplate_command_sql_guard"
  }
}

Input Schema

Name	Required	Description
`mode`	Yes	Parameter 'mode' (e.g. "auto")
`input`	Yes	Parameter 'input' (e.g. "SELECT id, email FROM users WHERE active = 1; DROP TABLE use")
`sql_policy`	No	Parameter 'sql_policy' (e.g. "read_only")

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered and the description does not contradict it. The description adds the detection scope and the endpoint path, but leaves out what actually happens on a hit (block vs. report-only) and what verdict the caller gets back, which matters for a 'firewall' tool.

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 compact sentences, front-loaded with the purpose and ending with the endpoint, with no filler. Minor redundancy in restating the title's phrase 'Agent Shell Command & SQL Query Safety Firewall', but nothing wasteful.

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?

With no output schema, the description should explain the shape of the response (allow/deny verdict, findings, risk categories) and it does not. For a 3-parameter security-evaluation tool the purpose is adequately conveyed, but the agent cannot predict what it will get back or how 'mode'/'sql_policy' affect the outcome.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3, and the description adds no meaning beyond the schema for 'mode', 'input', or 'sql_policy'. Notably it never explains what 'auto' mode does or how 'sql_policy' (e.g. read_only) changes the verdict, information the schema placeholders do not convey either.

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 specific verb (audit) and two concrete resources (agent shell commands and Text-to-SQL queries), plus the threat classes it targets (RCE, reverse shells, destructive SQL). It is clear enough to distinguish from generic guard siblings, though it never names or contrasts with the closest alternative, tinplate_agent_code_guard.

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

Usage Guidelines3/5

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

Usage is only implied by naming the artifacts it inspects; an agent can infer it should call this when it has a shell command or SQL string to vet. There is no explicit when-to-use/when-not guidance, no prerequisites, and no direction on choosing between this and sibling guard tools.

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

All Tinplate Edge AI Safety, Security & EU Compliance 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?