# Memory PostgreSQL

> Use this tool when you need to implement long-term memory capabilities for AI assistants, enabling semantic search and recall of information across conversations. It solves problems of context loss and information retrieval, accepting text inputs and generating embeddings for efficient vector similarity search. Ideal for use cases requiring conversation context maintenance, it provides outputs such as search results, tagged memories, and confidence scores.

Canonical page: https://skillsregistry.net/skills/sdimitrov-memory-postgresql  
JSON: https://api.skillsregistry.net/v1/skills/sdimitrov-memory-postgresql

## Description

MCP Memory Server provides long-term memory capabilities for AI assistants using PostgreSQL with pgvector for efficient vector similarity search. The implementation uses the Xenova/all-MiniLM-L6-v2 model to automatically generate embeddings for stored memories, enabling semantic search across different memory types. It exposes tools for creating, searching, and listing memories with support for tagging, confidence scoring, and filtering, making it particularly valuable for AI assistants that need to maintain context and recall information across conversations without losing important details.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/sdimitrov-memory-postgresql)
- **Repository:** <https://github.com/sdimitrov/mcp-memory>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "sdimitrov-memory-postgresql"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sdimitrov-memory-postgresql` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sdimitrov-memory-postgresql/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt