SeedBase Test Data
Generate realistic, FK-consistent synthetic test data for your databases from your AI assistant.
我該用這個嗎
品質與安全性
A
發現項目（1）
- LOWTool 'fetch_generation' suggests web access but openWorldHint=false在 fetch_generation 中
根據工具定義與協定合規性的自動化分析。
上下文成本
~1,284Token（工具定義）
~1.8 KB典型回應大小
中等的注意力影響（128k 上下文的 1.00%）
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"seedbase": {
"command": "npx",
"args": [
"@seedbase/client"
]
}
}
}可執行的套件
npm@seedbase/client
0.2.2stdio遠端端點
https://seedba.se/mcpstreamable-http它能做什麼
工具清單
工具（6）
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢list_projects
List your SeedBase projects (id, name, database type). Use this first to find the project to work with.
輸入結構描述
{
"type": "object",
"properties": {},
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"projects": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"db_type": {
"type": "string"
}
},
"required": [
"id",
"name",
"db_type"
]
}
}
},
"required": [
"projects"
]
}🟢get_ddl(project, dialect)
Get a project's schema as CREATE TABLE statements. Accepts a project id or name and an optional SQL dialect (postgresql, mysql, sqlite, mssql).
輸入結構描述
{
"type": "object",
"properties": {
"project": {
"type": "string",
"description": "Project id (UUID) or project name"
},
"dialect": {
"type": "string",
"enum": [
"postgresql",
"mysql",
"sqlite",
"mssql"
],
"description": "SQL dialect for the DDL (default: the project's database type)"
}
},
"required": [
"project"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"ddl": {
"type": "string"
},
"dialect": {
"type": "string"
}
},
"required": [
"ddl",
"dialect"
]
}🟡generate_test_data(project, rows, seed)
Generate a fresh synthetic dataset for a project and return it as SQL INSERT statements. Optionally set rows per table. The data is foreign-key consistent.
輸入結構描述
{
"type": "object",
"properties": {
"project": {
"type": "string",
"description": "Project id (UUID) or project name"
},
"rows": {
"type": "integer",
"minimum": 1,
"description": "Rows per table (optional; plan limits apply)"
},
"seed": {
"type": "integer",
"description": "Seed for deterministic output (optional)"
}
},
"required": [
"project"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"completed",
"running"
]
},
"generation_id": {
"type": "string"
},
"sql": {
"type": "string",
"description": "Complete SQL INSERTs. Absent when the result is too large — download it from download_url instead; no partial SQL is ever returned."
},
"truncated": {
"type": "boolean",
"description": "True when the SQL was too large to inline. The response then contains NO sql; fetch the complete file from download_url."
},
"download_url": {
"type": "string",
"description": "Authenticated download endpoint for the complete SQL (send your API key as 'Authorization: Bearer …')."
},
"sql_chars": {
"type": "integer"
}
},
"required": [
"status",
"generation_id"
]
}🟢fetch_generation(generation_id)
Fetch a previously started generation by id: returns its status, and the SQL INSERT statements once completed. Use this when generate_test_data reported the generation as still running.
輸入結構描述
{
"type": "object",
"properties": {
"generation_id": {
"type": "string",
"description": "The generation id (UUID) reported by generate_test_data"
}
},
"required": [
"generation_id"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"completed",
"running"
]
},
"generation_id": {
"type": "string"
},
"sql": {
"type": "string",
"description": "Complete SQL INSERTs. Absent when the result is too large — download it from download_url instead; no partial SQL is ever returned."
},
"truncated": {
"type": "boolean",
"description": "True when the SQL was too large to inline. The response then contains NO sql; fetch the complete file from download_url."
},
"download_url": {
"type": "string",
"description": "Authenticated download endpoint for the complete SQL (send your API key as 'Authorization: Bearer …')."
},
"sql_chars": {
"type": "integer"
}
},
"required": [
"status",
"generation_id"
]
}🟡create_project(name, db_type)
Create a new, empty SeedBase project. Use import_schema afterwards to add the schema.
輸入結構描述
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Project name"
},
"db_type": {
"type": "string",
"enum": [
"postgresql",
"mysql",
"sqlite",
"mssql"
],
"description": "Target database type (default: postgresql)"
}
},
"required": [
"name"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"db_type": {
"type": "string"
}
},
"required": [
"id",
"name",
"db_type"
]
}🔴import_schema(project, content, format)
Import a database schema into a project from pasted content: SQL DDL (CREATE TABLE …, raw pg_dump/mysqldump schema output works), SQL INSERT dumps, CSV/TSV, JSON, or ORM model code (Django, Prisma, SQLAlchemy, …). Replaces the project's current schema.
輸入結構描述
{
"type": "object",
"properties": {
"project": {
"type": "string",
"description": "Project id (UUID) or project name"
},
"content": {
"type": "string",
"description": "The schema source text (e.g. the DDL)"
},
"format": {
"type": "string",
"description": "Optional hint: sql, csv, tsv, json, or an ORM name (django, prisma, sqlalchemy, …). Auto-detected when omitted."
}
},
"required": [
"project",
"content"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"table_count": {
"type": "integer"
},
"fk_count": {
"type": "integer"
},
"tables": {
"type": "array",
"items": {
"type": "string"
}
},
"warnings": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"table_count",
"fk_count"
]
}社群
證據
近期觀測
已驗證未記錄版本6 個工具
已驗證未記錄版本6 個工具