Skip to main content
Glama
Secure MySQL MCP Server

Secure MySQL MCP Server

by Kavi-200312

propose_write

Propose INSERT, UPDATE, DELETE, or DDL statements for review: validates SQL, previews affected-row diffs, and returns an approval token without executing immediately.

Instructions

Propose an INSERT, UPDATE, DELETE, or DDL statement. Validates SQL AST, shows preview diff of affected rows, and generates an approval token. NEVER executes immediately.

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": {
      "sql": "<sql>"
    },
    "name": "propose_write"
  }
}

Input Schema

NameRequiredDescriptionDefault
sqlYesThe SQL statement (UPDATE/DELETE require a WHERE clause).
paramsNoOptional parameterized values.
databaseNoOptional database name.
confirmBulkNoSet to true if modifying more rows than the bulk threshold.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden and does disclose the key trait: validation, diff preview, token generation, and no immediate execution. It omits important operational details such as token lifetime/expiry, required permissions, and what happens when validation fails or bulk threshold is exceeded.

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

Conciseness5/5

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

Three short sentences, each earning its place: what it does, what it produces, and the critical safety constraint front-loaded in caps at the end. No filler or repetition of the tool name.

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

Completeness4/5

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

For a 4-param mutation-proposal tool with no annotations and no output schema, the description conveys the lifecycle (validate → preview → token) that an agent needs to sequence calls correctly. The remaining gap is the approval-token contract itself: how it is consumed and how long it stays valid.

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%, so the schema already documents all four parameters including the WHERE-clause constraint and confirmBulk. The description reinforces the mutation-type scope (INSERT/UPDATE/DELETE/DDL) which frames what the sql parameter accepts, but adds no new per-parameter meaning; baseline 3 plus slight credit for the statement-type framing.

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

Purpose5/5

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

States a specific verb (propose) and resource (INSERT/UPDATE/DELETE/DDL statement), then enumerates the concrete side effects: AST validation, preview diff, approval token. This clearly separates it from execute_approved_write without naming it.

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

Usage Guidelines4/5

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

"NEVER executes immediately" implicitly establishes the propose-then-approve workflow that routes agents to execute_approved_write, and the mutation scope is clear. It stops short of explicitly naming the follow-up tool or stating when a proposal should be skipped in favor of a read path like read_query.

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