PostgMem MCP Server

MCP server to store memories in postgres

Local serverstdio

What is the PostgMem MCP server?

PostgMem MCP server exists for a simple reason — assistants are far more useful when they can act on PostgMem directly instead of describing what you should do. MCP server to store memories in postgres.

What you get

A Model Context Protocol (MCP) server implementation that provides vector memory storage using PostgreSQL and pgvector for AI applications.

PostgMem is a .NET-based service that allows AI agents to store, retrieve, and search through memories using vector embeddings. It leverages PostgreSQL with the pgvector extension to provide efficient similarity search capabilities.

What the assistant can call

Once PostgMem is connected, these are the calls the assistant has available:

  • Store — Parameters: - type (string): The type of memory (e.g., 'conversation', 'document', etc.) - content (string): The content of the memory as a JSON
  • Search — Parameters: - query (string): The text to search for similar memories - limit (int): Maximum number of results to return (default: 10) -
  • Delete — The Delete tool exposed by this server

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Configuration and credentials

  • .NET 9.0 SDK - PostgreSQL database with pgvector extension installed - Text embedding API (default configuration uses Ollama)

Choosing this one

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. PostgMem's toolset — Store, Search, Delete — is a fair guide to whether it matches your workflow. It is maintained by dariogriffo; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the postgmem mcp server does with a few real requests.

Available tools

ToolWhat it does
StoreParameters: - type (string): The type of memory (e.g., 'conversation', 'document', etc.) - content (string): The content of the memory as a JSON object - source (string): The source of the memory (e.g., 'user', 'system',
SearchParameters: - query (string): The text to search for similar memories - limit (int): Maximum number of results to return (default: 10) - minSimilarity (double): Minimum similarity threshold (0.0 to 1.0) (default: 0.7) -
DeleteThe Delete tool exposed by this server.

Configuration

  • .NET 9.0 SDK - PostgreSQL database with pgvector extension installed - Text embedding API (default configuration uses Ollama)

Example prompts to try

  • Use PostgMem to Store.
  • Use PostgMem to Search.
  • Use PostgMem to Delete.

Frequently asked questions

You need .NET 9.0 SDK, a PostgreSQL database with the pgvector extension installed, and a text embedding API (the default configuration uses Ollama).