Veto — SQL Safety & Cost Oracle
Deterministic safety, correctness & cost gate that vets Postgres SQL before your AI agent runs it.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"veto": {
"url": "https://vetosql.com/mcp"
}
}
}远程端点
https://vetosql.com/mcpstreamable-http它能做什么
工具清单
工具（3）
🟡analyze_sql(sql, schema, rowCountHints, dialect)
Analyze Postgres SQL/migrations for destructive operations, locking risk, correctness traps (NULL handling that silently returns wrong results), anti-patterns, and query cost. Returns a deterministic verdict (ok/warn/block) with findings. Pass the optional `schema` argument (your CREATE TABLE/INDEX DDL) to also get EXPLAIN-based cost analysis run on a throwaway scratch Postgres — no separate tool or DB connection needed.
输入模式
{
"type": "object",
"properties": {
"sql": {
"type": "string",
"description": "The SQL to analyze (one or more statements)."
},
"schema": {
"type": "string",
"description": "Optional CREATE TABLE/INDEX DDL. Providing it enables EXPLAIN-based cost analysis (seq scans on large tables, etc.) on a throwaway scratch Postgres; omit it for static safety analysis only."
},
"rowCountHints": {
"type": "object",
"additionalProperties": {
"type": "number"
},
"description": "Optional map of table name to estimated row count for realistic cost estimates."
},
"dialect": {
"type": "string",
"const": "postgres"
}
},
"required": [
"sql"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🔴set_policies(policies)
Replace the stored custom org policy set for your Pro key (this is also how you update or clear them: send the full new set to update, or an empty array to remove all). Each policy blocks or warns on an operation against matching tables (e.g. no DELETE on payments). Policies are declarative data — validated, never executed — and apply transparently to every later analyze_sql call made with this key. Use get_policies to read the current set.
输入模式
{
"type": "object",
"properties": {
"policies": {
"type": "array",
"items": {
"type": "object",
"properties": {
"table": {
"type": "string",
"description": "Exact table name or glob, e.g. \"payments\", \"audit_*\", \"*\"."
},
"operations": {
"type": "array",
"items": {
"type": "string",
"enum": [
"select",
"insert",
"update",
"delete",
"truncate",
"drop",
"alter"
]
},
"description": "Operations this rule applies to."
},
"action": {
"type": "string",
"enum": [
"block",
"warn"
]
},
"message": {
"type": "string",
"description": "Optional human message shown in the finding."
}
},
"required": [
"table",
"operations",
"action"
],
"additionalProperties": false
},
"description": "The full policy set (replaces any previously stored set; max 50)."
}
},
"required": [
"policies"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡get_policies
Return the custom org policy set currently stored for your Pro key — the same rules analyze_sql enforces on top of the built-ins. Read-only; returns an empty list if none are set. Use set_policies to change them.
输入模式
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}社区
证据