# Unsloth session memory MCP

> Unsloth session memory MCP — kashyaparun25-unsloth-session-memory-mcp. Use this tool when you need to retrieve and manage earlier local chat sessions, excluding system messages and sensitive information. It provides a read-only interface to list, get, recall, and search sessions from a SQLite database, solving problems related to session history and data retrieval. Ideal for use cases requiring secure and efficient session management, with inputs of session queries and outputs of relevant chat session data.

Canonical page: https://skillsregistry.net/skills/kashyaparun25-unsloth-session-memory-mcp  
JSON: https://api.skillsregistry.net/v1/skills/kashyaparun25-unsloth-session-memory-mcp

## Description

A read-only MCP server that lets Unsloth Studio retrieve earlier local chat sessions from its SQLite database, providing tools to list, get, recall, and search sessions while excluding system messages and redacting sensitive patterns.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/kfbmp0a9zr)
- **Repository:** <https://github.com/kashyaparun25/unsloth-session-memory-mcp>

## 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": "kashyaparun25-unsloth-session-memory-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kashyaparun25-unsloth-session-memory-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kashyaparun25-unsloth-session-memory-mcp/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