mcpField
M
mcp-psycopg2

mcp-psycopg2

Local
github.com/daedalusDatabases0Updated 27w ago
Repository

About mcp-psycopg2

mcp-psycopg2 exposes psycopg2 PostgreSQL adapter functions as an MCP server for clients that connect to and operate on databases. It covers transactions, cursors, COPY, type registration, and large objects.

Key features

  1. 01Manage database connections and transactions
  2. 02Execute SQL and retrieve results
  3. 03Compose SQL with parameters
  4. 04Register JSON, hstore, and composite types
  5. 05Use COPY and large-object operations
  6. 06Inspect server and session information

Use cases

  1. 01Run PostgreSQL queries through a client
  2. 02Control transactions and iterate over results
  3. 03Import or export table data in bulk

MCP support

As an MCP server, it provides MCP clients with psycopg2 tools for connecting to PostgreSQL, executing queries, managing transactions, and handling data.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "daedalus-mcp-psycopg2": {
      "command": "uvx",
      "args": [
        "mcp-psycopg2"
      ]
    }
  }
}
Run commanduvx mcp-psycopg2

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-psycopg20.1.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-psycopg2

MCP server exposing psycopg2 PostgreSQL database adapter functionality.

PyPI Python Ruff

mcp-name: io.github.daedalus/mcp-psycopg2

Install

pip install mcp-psycopg2

Usage

from mcp_psycopg2 import mcp

# Run the MCP server
mcp.run()

MCP Tools

The server exposes the following tools for interacting with PostgreSQL databases:

Connection Management
  • connect - Create a new database connection
  • close_connection - Close an existing connection
  • get_connection_info - Get connection details
Transaction Management
  • begin_transaction - Start a new transaction
  • commit_transaction - Commit the current transaction
  • rollback_transaction - Rollback the current transaction
  • set_isolation_level - Set transaction isolation level
Cursor Operations
  • create_cursor - Create a new cursor
  • close_cursor - Close a cursor
  • execute_query - Execute a SQL query
  • execute_many - Execute a query with multiple parameter sets
  • fetch_one - Fetch one row
  • fetch_many - Fetch multiple rows
  • fetch_all - Fetch all remaining rows
SQL Composition
  • quote_identifier - Quote an SQL identifier
  • mogrify - Return query string after parameter binding
Type Registration
  • register_json - Register JSON type adapter
  • register_hstore - Register hstore type adapter
  • register_composite - Register composite type adapter
COPY Operations
  • copy_from - Copy data from file to table
  • copy_to - Copy data from table to file
  • copy_expert - Execute custom COPY statement
Server-Side Cursors
  • create_named_cursor - Create a server-side named cursor
  • scroll_cursor - Scroll through cursor results
Large Objects
  • create_large_object - Create or open a large object
  • read_large_object - Read from a large object
  • write_large_object - Write to a large object
Information
  • get_server_version - Get PostgreSQL server version
  • get_backend_pid - Get backend process ID
  • get_dsn_parameters - Get connection parameters
  • get_notices - Get database notices
  • parse_dsn - Parse a connection string
  • make_dsn - Create a connection string
Utility
  • cancel_query - Cancel the current database operation
  • set_session - Set session parameters
  • list_connections - List all active connections
  • list_cursors - List all active cursors

Development

git clone https://github.com/daedalus/mcp-psycopg2.git
cd mcp-psycopg2
pip install -e ".[test]"

# run tests
pytest

# format
ruff format src/ tests/

# lint
ruff check src/ tests/

# type check
mypy src/

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.