ai-agents-mcp-pg
github详情内容
PostgreSQL MCP 服务器
这是一个提供访问PostgreSQL数据库的模型上下文协议服务器。该服务器使LLM能够与数据库交互，以检查模式、执行查询以及对数据库条目进行CRUD（创建、读取、更新、删除）操作。这个仓库是对PostgreSQL MCP 服务器的功能扩展，提供了创建表、插入条目、更新条目、删除条目和删除表的功能。
安装
要安装PostgreSQL MCP 服务器，请按照以下步骤操作：
- 安装Docker和Claude Desktop
- 克隆仓库：
git clone https://github.com/vignesh-codes/ai-agents-mcp-pg.git - 运行PG Docker容器
docker run --name postgres-container -e POSTGRES_USER=admin -e POSTGRES_PASSWORD=admin_password -e POSTGRES_DB=mydatabase -p 5432:5432 -d postgres:latest - 构建mcp服务器：
docker build -t mcp/postgres -f src/Dockerfile . - 打开Claude Desktop并通过更新
claude_desktop_config.json中的mcpServers字段来连接到MCP服务器：
与Claude Desktop一起使用
要将此服务器与Claude Desktop应用程序一起使用，请在您的claude_desktop_config.json的"mcpServers"部分中添加以下配置：
Docker
- 在macOS上运行Docker时，如果服务器运行在主机网络（例如localhost），请使用
host.docker.internal。 - 用户名/密码可以通过
postgresql://user:password@host:port/db-name的形式添加到PostgreSQL URL中。
{
"mcpServers": {
"postgres": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"mcp/postgres",
"postgresql://username:password@host.docker.internal:5432/mydatabase"
]
}
}
}
确保在更新配置文件后重新启动Claude桌面应用。
新增功能
现有功能
- query
- 对已连接的数据库执行只读SQL查询。
- 输入：
sql(字符串): 要执行的SQL查询。 - 所有查询都在一个只读事务中执行。
新增功能
-
创建表
- 通过提供表名和列定义动态创建新表。
- 来自 Claude Desktop 的输入：
{ "tableName": "example_table", "columns": [ { "name": "id", "type": "SERIAL PRIMARY KEY" }, { "name": "name", "type": "VARCHAR(255)" }, { "name": "age", "type": "INTEGER" } ] }
-
插入条目
- 向指定表中插入新的条目。
- 来自 Claude Desktop 的输入：
{ "tableName": "example_table", "values": { "name": "John Doe", "age": 30 } }
-
更新条目
- 根据条件更新表中的现有条目。
- 来自 Claude Desktop 的输入：
{ "tableName": "example_table", "values": { "age": 35 }, "conditions": "name = 'John Doe'" }
-
删除条目
- 根据条件删除表中的特定条目。
- 来自 Claude Desktop 的输入：
{ "tableName": "example_table", "conditions": "name = 'John Doe'" }
-
删除表
- 从数据库中删除现有的表。
- 来自 Claude Desktop 的输入：
{ "tableName": "example_table" }
资源
服务器为数据库中的每个表提供模式信息：
- 表模式 (
postgres://<host>/<table>/schema)- 每个表的 JSON 模式信息。
- 包括列名和数据类型。
- 自动从数据库元数据中发现。
示例
输入到 Claude Desktop
lets create three tables - users, payments and orders tables. Each table must have a unique id and other required columns. Payments table must have user id as foreign key. Orders table must have payment id as foreign key. Add some sample data to these tables
从 Claude Desktop 输出
I'll help you create these three interconnected tables and populate them with sample data. Let's create them one by one. 1. First, let's create the users table: { `columns`: [ { `name`: `id`, `type`: `INTEGER PRIMARY KEY` }, { `name`: `name`, `type`: `TEXT` }, { `name`: `email`, `type`: `TEXT` }, { `name`: `created_at`, `type`: `TEXT` } ], `tableName`: `users` } 2. Now, let's create the payments table with a foreign key reference to users: { `columns`: [ { `name`: `id`, `type`: `INTEGER PRIMARY KEY` }, { `name`: `user_id`, `type`: `INTEGER` }, { `name`: `amount`, `type`: `REAL` }, { `name`: `status`, `type`: `TEXT` }, { `name`: `payment_date`, `type`: `TEXT` } ], `tableName`: `payments` } 3. Finally, let's create the orders table with a foreign key reference to payments: { `columns`: [ { `name`: `id`, `type`: `INTEGER PRIMARY KEY` }, { `name`: `payment_id`, `type`: `INTEGER` }, { `name`: `product_name`, `type`: `TEXT` }, { `name`: `quantity`, `type`: `INTEGER` }, { `name`: `order_date`, `type`: `TEXT` } ], `tableName`: `orders` } Now, let's add some sample data to these tables. First, let's add some users: { `values`: { `id`: `1`, `name`: `John Doe`, `email`: `john@example.com`, `created_at`: `2024-01-01` }, `tableName`: `users` } { `values`: { `id`: `2`, `name`: `Jane Smith`, `email`: `jane@example.com`, `created_at`: `2024-01-05` }, `tableName`: `users` } Now, let's add some payments for these users: { `values`: { `id`: `1`, `amount`: `99.99`, `status`: `completed`, `user_id`: `1`, `payment_date`: `2024-01-10` }, `tableName`: `payments` } { `values`: { `id`: `2`, `amount`: `149.99`, `status`: `completed`, `user_id`: `2`, `payment_date`: `2024-01-12` }, `tableName`: `payments` } Finally, let's add some orders linked to these payments: { `values`: { `id`: `1`, `quantity`: `1`, `order_date`: `2024-01-10`, `payment_id`: `1`, `product_name`: `Laptop` }, `tableName`: `orders` } { `values`: { `id`: `2`, `quantity`: `2`, `order_date`: `2024-01-12`, `payment_id`: `2`, `product_name`: `Smartphone` }, `tableName`: `orders` } Let's verify the data by querying each table: { `sql`: `SELECT * FROM users;` } { `sql`: `SELECT * FROM payments;` } { `sql`: `SELECT * FROM orders;` } Great! We have now created three interconnected tables with sample data. Here's a summary of what we've set up: 1. Users table with basic user information 2. Payments table linked to users through user_id 3. Orders table linked to payments through payment_id The data shows two users who have each made one payment and placed one order. We can now perform various queries to analyze the relationships between these tables. Would you like to see any specific queries or add more data?
输入到 Claude Desktop
add few more users with IN_PROGRESS and UNSUCCESSFUL payment status
从 Claude Desktop 输出
I'll add a few more users with different payment statuses. First, let's add new users: { `values`: { `id`: `3`, `name`: `Mike Johnson`, `email`: `mike@example.com`, `created_at`: `2024-01-08` }, `tableName`: `users` } { `values`: { `id`: `4`, `name`: `Sarah Wilson`, `email`: `sarah@example.com`, `created_at`: `2024-01-09` }, `tableName`: `users` } { `values`: { `id`: `5`, `name`: `Tom Brown`, `email`: `tom@example.com`, `created_at`: `2024-01-11` }, `tableName`: `users` } Now, let's add payments with IN_PROGRESS and UNSUCCESSFUL statuses for these users: { `values`: { `id`: `3`, `amount`: `299.99`, `status`: `IN_PROGRESS`, `user_id`: `3`, `payment_date`: `2024-01-13` }, `tableName`: `payments` } { `values`: { `id`: `4`, `amount`: `199.99`, `status`: `UNSUCCESSFUL`, `user_id`: `4`, `payment_date`: `2024-01-13` }, `tableName`: `payments` } { `values`: { `id`: `4`, `amount`: `199.99`, `status`: `UNSUCCESSFUL`, `user_id`: `4`, `payment_date`: `2024-01-13` }, `tableName`: `payments` } { `values`: { `id`: `5`, `amount`: `399.99`, `status`: `IN_PROGRESS`, `user_id`: `5`, `payment_date`: `2024-01-13` }, `tableName`: `payments` } Let's add orders for the IN_PROGRESS payments (note that we won't add orders for the UNSUCCESSFUL payment): { `values`: { `id`: `3`, `quantity`: `1`, `order_date`: `2024-01-13`, `payment_id`: `3`, `product_name`: `Gaming Console` }, `tableName`: `orders` } { `values`: { `id`: `4`, `quantity`: `1`, `order_date`: `2024-01-13`, `payment_id`: `5`, `product_name`: `4K TV` }, `tableName`: `orders` } Let's verify the data by checking all payments with their status: { `sql`: `SELECT u.name, p.amount, p.status, p.payment_date FROM users u JOIN payments p ON u.id = p.user_id ORDER BY p.payment_date;` } Now we have a good mix of payment statuses in our database: - 2 completed payments (John and Jane) - 2 in-progress payments (Mike and Tom) - 1 unsuccessful payment (Sarah) The orders table only contains entries for completed and in-progress payments, as it makes sense not to create orders for unsuccessful payments. Would you like to see any specific queries or add more data?
输入到 Claude Desktop
Fetch the users info who have IN_PROGRESS payment status
从 Claude Desktop 输出
I'll write a query to fetch user information for those who have payments with IN_PROGRESS status. { `sql`: ` SELECT u.*, p.amount, p.payment_date FROM users u JOIN payments p ON u.id = p.user_id WHERE p.status = 'IN_PROGRESS' ORDER BY u.id; ` } We can see that two users have payments in progress: 1. Mike Johnson (attempting to pay $299.99) 2. Tom Brown (attempting to pay $399.99) Both payments were initiated on January 13, 2024. Would you like to see any additional information about these users or their orders?
输入到 Claude Desktop
Lets update the payment status to completed for Mike Johnson
从 Claude Desktop 输出
I'll update Mike Johnson's payment status from IN_PROGRESS to completed. { `values`: { `status`: `completed` }, `tableName`: `payments`, `conditions`: { `user_id`: `3` } } Let's verify the update by checking all payments again: { `sql`: ` SELECT u.name, p.amount, p.status, p.payment_date FROM users u JOIN payments p ON u.id = p.user_id ORDER BY p.status, p.payment_date; ` } The update was successful. Now we have: - 3 completed payments (John, Jane, and Mike) - 1 in-progress payment (Tom) - 1 unsuccessful payment (Sarah) Would you like to make any other updates to the data?
数据库条目
mydatabase=# SELECT * FROM users; id | name | email | created_at ----+--------------+-------------------+------------ 1 | John Doe | john@example.com | 2024-01-01 2 | Jane Smith | jane@example.com | 2024-01-05 3 | Mike Johnson | mike@example.com | 2024-01-08 4 | Sarah Wilson | sarah@example.com | 2024-01-09 5 | Tom Brown | tom@example.com | 2024-01-11 (5 rows) mydatabase=# SELECT * FROM payments; id | user_id | amount | status | payment_date ----+---------+--------+--------------+-------------- 1 | 1 | 99.99 | completed | 2024-01-10 2 | 2 | 149.99 | completed | 2024-01-12 4 | 4 | 199.99 | UNSUCCESSFUL | 2024-01-13 5 | 5 | 399.99 | IN_PROGRESS | 2024-01-13 3 | 3 | 299.99 | completed | 2024-01-13 (5 rows) mydatabase=# SELECT * FROM orders; id | payment_id | product_name | quantity | order_date ----+------------+----------------+----------+------------ 1 | 1 | Laptop | 1 | 2024-01-10 2 | 2 | Smartphone | 2 | 2024-01-12 3 | 3 | Gaming Console | 1 | 2024-01-13 4 | 5 | 4K TV | 1 | 2024-01-13 (4 rows)
许可证
此 MCP 服务器根据 MIT 许可证授权。这意味着您可以在 MIT 许可证的条款和条件下自由使用、修改和分发该软件。有关更多详细信息，请参阅项目仓库中的 LICENSE 文件。
腾讯云开发者
